Model library

Every model, one studio

461 models from 66 providers, synced live with pricing, context windows, and capabilities. New models appear within minutes of release. Search, filter, and open any one.

461

models

66

providers

359

text

65

image

4

audio

33

video

Most used on GenMagic

The models the most GenMagic accounts generated with in the last 90 days, with how long each took to deliver. Counted in aggregate, only for models with at least 10 generations from at least 3 accounts. How long every measured model takes

  1. #1 · videoMiniMax: H3 Max52 accounts · median 14 s
  2. #2 · imageGoogle: Nano Banana 2.137 accounts · median 14 s
  3. #3 · imageOpenAI: GPT Image 2.5 Sunburst32 accounts · median 18 s
  4. #4 · videoKling: Video v3.0 Standard27 accounts · median 130 s
  5. #5 · videoGoogle: Veo 3.1 Lite24 accounts · median 46 s
  6. #6 · imageGoogle: Nano Banana 2 (Gemini 3.1 Flash Image)22 accounts · median 11 s
  7. #7 · videoByteDance: Seedance 2.0 Mini13 accounts · median 144 s
  8. #8 · textGoogle: Gemini 3.5 Flash12 accounts · median 4.5 s

Showing 461 models

MiniMax H3 Image Highspeed

Image

MiniMax

MiniMax H3 Image Highspeed is the faster version of MiniMax's H3 Image model. It takes the same inputs and limits as MiniMax H3 Image: it creates images from text prompts...

Vision
4K context4K output~$0.015/image

MiniMax H3 Image

Image

MiniMax

MiniMax H3 Image is MiniMax's image generation and editing model. It creates images from text prompts and edits or composes images from 1 to 16 reference images, with output up...

Vision
4K context4K output~$0.0074/image

ERNIE-5.5-Flash-Preview

Text

Baidu

ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total...

ReasoningToolsJSON
1M context922K output$0.42/1M in

ERNIE-Light-DT-1.0

Text

Baidu

ERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It features Baidu Sparse Attention (BSA), a unique sparse attention mechanism developed by...

ReasoningToolsJSON
1M context131K output$1.70/1M in

Gemini 4 Carbon

Text

Google

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...

ReasoningVisionToolsJSON
Intelligence60
1M context944K output$3.00/1M in

Nex-N2.6

Text

NEX-AGI

Nex-N2.6 is an agentic model from Nex AGI, built on GLM-5.3-Flash with about 321B parameters. It is suited for computer use, coding, and long-horizon tasks that involve tools. Compared with...

ReasoningVisionToolsJSON
262K context236K output$0.18/1M in
TH

Inkling 2 Small (free)

Text

Thinkingmachines

Inkling 2 Small is a multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second Inkling...

ReasoningVisionTools
Intelligence31
1M context131K outputFree

Claude Fable 5.2

Text

Anthropic

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...

ReasoningVisionToolsJSON
Intelligence65
1M context128K output$12.00/1M in

Muse Ember

Text

Meta

Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,...

ReasoningVisionToolsJSON
1M context944K output$0.15/1M in

LFM3-1.7B

Text

Liquid AI

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...

ReasoningToolsJSON
262K context8K output$0.12/1M in

LFM3-1.7B (free)

Text

Liquid AI

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...

ReasoningToolsJSON
262K context8K outputFree

Gemini Omni 1.2 Flash

Video

Google

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native...

ReasoningVision
131K context66K output$0.035–$0.31/sec
KT

Mi:dm K 3.0 Pro

Text

Kt

Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.

ReasoningJSON
262K context236K output$0.30/1M in

GPT Image 2.6 Sunburst

Image

OpenAI

GPT Image 2.6 Sunburst is OpenAI's image generation and editing model optimized for detail: dense compositions, text-heavy layouts, and edits that keep details consistent from one edit to the next...

VisionJSON
400K context360K output~$0.058/image

GPT Image 2.6 Flare

Image

OpenAI

GPT Image 2.6 Flare is OpenAI's image generation and editing model optimized for speed: fast iteration and interactive text-to-image and image-to-image workflows, generating about 50% faster than GPT Image 2.5....

VisionJSON
400K context360K output~$0.058/image

Gemini Omni 1.1 Flash

Video

Google

Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and...

ReasoningVision
131K context66K output$0.051–$0.46/sec
RI

Ripple 65B Preview

Text

Ricursiveai

Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.

ReasoningToolsJSON
1M context131K output$0.30/1M in

Hy4

Text

Tencent

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...

ReasoningVisionToolsJSON
Intelligence35
1M context66K output$0.63/1M in
MT

Motif 3

Text

Motif Technologies

Motif 3 is a Mixture-of-Experts language model from Motif Technologies, with 314B total and 13.2B active parameters. It is a general-purpose multilingual model for English and Korean, particularly strong at...

ReasoningJSON
Coding64
Agentic28
262K context236K output$0.45/1M in

GLM 5.3 FlashX Legal

Text

Z.AI

GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...

ReasoningVisionToolsJSON
1M context131K output$0.56/1M in
TB

mischief 1

Video

Tbc

TBC mischief 1 is the world's first neuron-derived video model from The Biological Computing Co. It supports image to video and is a fast and affordable way to bring ideas...

Vision
$0.0075–$0.015/sec

Riverflow V2.6 Pro

Image

Sourceful

Riverflow 2.6 Pro is the flagship model of Sourceful's Riverflow 2.6 lineup, a unified text-to-image and image-to-image family that treats generation as a production workflow: an integrated reasoning model plans...

ReasoningVision
33K context29K output~$0.19/image
PA

Particle-1

Text

Particle Ai

Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...

ReasoningVisionToolsJSON
1M context131K output$0.075/1M in

GPT-6.1 Terra Pro

Text

OpenAI

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...

ReasoningVisionToolsJSON
1.1M context128K output$1.50/1M in

GPT-6.1 Terra

Text

OpenAI

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...

ReasoningVisionToolsJSON
Intelligence51
1.1M context128K output$1.50/1M in

Kimi K3.1 Pro

Text

Moonshot AI

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

ReasoningVisionToolsJSON
Intelligence47
1M context944K output$3.00/1M in
RE

Flint (free)

Text

Recursive

Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...

ReasoningToolsJSON
262K context236K outputFree

MiniMax M3.1 Flash

Text

MiniMax

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...

ReasoningVisionToolsJSON
Intelligence29
1M context524K output$0.23/1M in

DeepSeek V4.1 Flash 1017

Text

DeepSeek

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model...

ReasoningVisionToolsJSON
Intelligence29
1M context944K output$0.009/1M in
EL

Glimpse

Text

Elorian

Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...

ReasoningVisionToolsJSON
262K context256K output$0.90/1M in

Qwen Image 2.1 Turbo

Image

Qwen

Qwen Image 2.1 Turbo is the fast, lower-cost tier of the Qwen Image 2.1 series from Qwen, for image generation and editing where throughput and price matter more than peak...

VisionJSON
66K context59K output~$0.028/image

Qwen Image 2.1 Pro

Image

Qwen

Qwen Image 2.1 Pro is an image generation and editing model from Qwen, the higher-quality tier of the Qwen Image 2.1 series. Choose it over Qwen Image 2.1 Turbo when...

VisionJSON
66K context59K output~$0.069/image
RE

Beam 1.0 501B A23B

Text

Reflection

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...

ReasoningToolsJSON
Intelligence18
1M context944K outputcutoff 2026-06-30$0.45/1M in
PM

Ternary Bonsai 2 9B

Text

Prism Ml

Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...

ReasoningVisionToolsJSON
262K context66K output$0.12/1M in
KR

Krea K3 Edit

Image

Krea

Krea K3 Edit is an image-to-image editing model from Krea. It takes one to eight reference images plus a text prompt and returns a single edited image, following instructions that...

Vision
66K context59K output~$0.045/image
MO

Moondream 3 Preview

Text

Moondream

Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...

ReasoningVision
32K context4K output$0.45/1M in
MO

Moondream 3.1

Text

Moondream

Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...

ReasoningVision
32K context4K output$0.45/1M in

Muse Spark Open

Text

Meta

Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...

ReasoningVisionToolsJSON
Intelligence25
1M context262K output$1.88/1M in

FLUX 3 Image Klein

Image

Black Forest Labs

FLUX 3 Image Klein is an open-weights image generation and editing model from Black Forest Labs. It is suited for text-to-image, multi-reference editing that keeps characters and subjects consistent across...

Vision
47K context42K output~$0.014/image

Nemotron 3.5 Super VL

Text

NVIDIA

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

ReasoningVisionToolsJSON
Intelligence14
1M context944K output$0.23/1M in

Nemotron 3.5 Super VL (free)

Text

NVIDIA

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

ReasoningVisionToolsJSON
Intelligence14
1M context131K outputFree
UN

Pareto 26.10

Text

Unbiased

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

VisionTools
1M context131K output$1.20/1M in
UN

Pareto Latest

Text

Unbiased

This model always redirects to the latest model in the Pareto family.

VisionTools
1M context131K output$1.20/1M in
UN

Pareto 26.9

Text

Unbiased

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

VisionToolsJSON
262K context131K output$3.75/1M in

LFM2.5-24B-A2B

Text

Liquid AI

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...

ReasoningToolsJSON
128K context8K output$0.075/1M in

Gemini 4 Argon

Text

Google

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

ReasoningVisionToolsJSON
Intelligence50
1M context944K output$3.00/1M in
SC

Summarize

Text

Scaledown

Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...

Vision
1M context4K output$0.06/1M in
SC

Extract

Text

Scaledown

Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through provider.options.scaledown.entities, and the...

Vision
1M context900K output$0.06/1M in

Muse Wonder

Text

Meta

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...

ReasoningVisionToolsJSON
Intelligence44
1M context944K output$6.00/1M in

Step 5 Preview

Text

StepFun

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...

ReasoningVisionToolsJSON
Intelligence29
1M context64K output$1.50/1M in

Claude Haiku 5.5

Text

Anthropic

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

ReasoningVisionToolsJSON
Intelligence37
1M context128K output$0.15/1M in

Grok Imagine Video 1.5 Lite

Video

xAI

Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXAI, distilled from Grok Imagine Video 1.5. It supports text-to-video and image-to-video, trading some quality for speed...

VisionJSON
$0.03–$0.21/sec

Nano Banana 2.1

Image

Google

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...

ReasoningVisionToolsJSON
66K context59K output~$0.058/image

Mistral Large 4

Text

Mistral AI

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...

ReasoningVisionToolsJSON
Intelligence26
1M context262K output$1.05/1M in

Hy Image 3.5 Preview

Image

Tencent

Hy Image 3.5 Preview is a unified image generation and editing model from Tencent. It handles text-to-image, image-to-image, and multi-turn editing through one endpoint, taking up to 20 reference images...

Vision
100K context90K output~$0.036/image

Ling 3.1 Flash

Text

inclusionAI

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

ReasoningToolsJSON
1M context262K output$0.068/1M in

Seedream 5.0 Flash

Image

ByteDance

Seedream 5.0 Flash is an image generation and editing model from ByteDance Seed. It is the fast, cost-efficient tier of the Seedream 5.0 family, suited for high-volume production and interactive...

Vision
~$0.027/image

FLUX 3 Image

Image

Black Forest Labs

FLUX.3 Image is Black Forest Labs' flagship image generation and editing model. It handles text-to-image and multi-reference editing with up to 10 input images, and renders at fixed resolution tiers...

Vision
47K context42K output~$0.072/image
HE

HeyGen Video

Video

Heygen

HeyGen Video is a general-purpose video generation model from HeyGen. It renders short clips with synthesized audio (dialogue, ambience, and sound effects) in a single call, working from a text...

Vision
$0.015–$0.075/sec

GPT-6.1 Sol Pro

Text

OpenAI

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...

ReasoningVisionToolsJSON
1.1M context128K output$3.00/1M in

GPT-6.1 Sol

Text

OpenAI

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...

ReasoningVisionToolsJSON
Intelligence55
1.1M context128K output$3.00/1M in

Claude Sonnet 5.5

Text

Anthropic

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...

ReasoningVisionToolsJSON
Intelligence55
1M context128K output$3.00/1M in

Perceptron Mk1.5

Text

Perceptron

Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...

ReasoningVisionToolsJSON
37K context8K output$0.23/1M in
FI

Ember-1

Text

Fireworks

Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...

ReasoningVisionToolsJSON
1M context944K output$4.50/1M in

GLM 5.3 Prime

Text

Z.AI

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...

ReasoningToolsJSON
1M context131K output$4.20/1M in

Qwen3.8 Max Prime

Text

Qwen

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...

ReasoningVisionToolsJSON
1M context131K output$6.00/1M in

Recraft V4.1 Flash

Image

Recraft

Recraft V4.1 Flash is a text-to-image model from Recraft, the speed and cost tier of the V4.1 family. It generates ~1K raster images in about 1.5 seconds end to end,...

66K context59K output~$0.011/image

Aion 3.5 Mini

Text

AionLabs

Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...

ReasoningToolsJSON
262K context33K output$1.05/1M in

Aion 3.5

Text

AionLabs

Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...

ReasoningToolsJSON
262K context33K output$4.50/1M in

Solar Mini 4

Text

Upstage

Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...

ReasoningToolsJSON
524K context131K output$0.075/1M in

Command A+

Text

Cohere

Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...

ReasoningVisionToolsJSON
Intelligence6
Coding28
Agentic1
192K context64K output$0.45/1M in

GPT-6 Luna Pro

Text

OpenAI

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...

ReasoningVisionToolsJSON
1.1M context128K output$0.15/1M in

GPT-6 Luna

Text

OpenAI

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

ReasoningVisionToolsJSON
Intelligence28
1.1M context128K output$0.15/1M in

GPT-6 Sol Pro

Text

OpenAI

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...

ReasoningVisionToolsJSON
1.1M context128K output$3.00/1M in

GPT-6 Sol

Text

OpenAI

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...

ReasoningVisionToolsJSON
Intelligence44
1.1M context128K output$3.00/1M in

Claude Opus 5.5

Text

Anthropic

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...

ReasoningVisionToolsJSON
Intelligence59
1M context128K output$6.00/1M in

MiMo-V2.6-Pro-UltraSpeed

Text

Xiaomi

MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...

ReasoningVisionToolsJSON
1M context131K output$6.53/1M in

MiMo-V2.6-Flash

Text

Xiaomi

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...

ReasoningVisionToolsJSON
Intelligence27
1.1M context131K output$0.21/1M in

MiMo-V2.6-Pro

Text

Xiaomi

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...

ReasoningVisionToolsJSON
Intelligence30
1.1M context131K output$0.65/1M in

Grok 4.7

Text

xAI

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

ReasoningVisionToolsJSON
Intelligence36
500K context450K output$3.00/1M in

Qwen3.8 Omni Flash

Text

Qwen

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

ReasoningVisionToolsJSON
1M context131K output$0.23/1M in
PM

Ternary Bonsai 2 27B

Text

Prism Ml

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...

ReasoningVisionToolsJSON
262K context33K output$0.11/1M in

GLM 5.3 FlashX

Text

Z.AI

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...

ReasoningVisionToolsJSON
1M context131K output$0.56/1M in

DeepSeek Pro Latest

Text

DeepSeek

This model always redirects to the latest model in the DeepSeek Pro family.

ReasoningToolsJSON
1M context393K output$0.15/1M in

DeepSeek Flash Latest

Text

DeepSeek

This model always redirects to the latest model in the DeepSeek Flash family.

ReasoningVisionToolsJSON
1M context944K output$0.009/1M in
IN

Schematron V2 Turbo

Text

Inference Net

Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...

JSON
128K context8K output$0.045/1M in
IN

Schematron V2 Small

Text

Inference Net

Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...

JSON
128K context8K output$0.075/1M in

GPT Astra Latest

Text

OpenAI

This model always redirects to the latest model in the GPT Astra family.

ReasoningVisionToolsJSON
1.1M context128K output$15.00/1M in

GPT Sol Latest

Text

OpenAI

This model always redirects to the latest model in the GPT Sol family.

ReasoningVisionToolsJSON
1.1M context128K output$3.00/1M in

GPT Terra Latest

Text

OpenAI

This model always redirects to the latest model in the GPT Terra family.

ReasoningVisionToolsJSON
1.1M context128K output$1.50/1M in

GPT Luna Latest

Text

OpenAI

This model always redirects to the latest model in the GPT Luna family.

ReasoningVisionToolsJSON
1.1M context128K output$0.15/1M in

Fugu Ultra v2

Text

Sakana AI

Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...

ReasoningVisionToolsJSON
1M context128K outputcutoff 2026-08-28$7.50/1M in

Fugu Max

Text

Sakana AI

Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

ReasoningVisionToolsJSON
1M context128K output$3.00/1M in

FLUX Video Edit

Video

Black Forest Labs

FLUX Video Edit [fast] takes a source video and an edit prompt and returns a precisely edited video. Add, remove, or replace objects and characters, rebuild the setting, edit on-screen...

$0.045/sec

Ling 3.0 Flash VL

Text

inclusionAI

Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...

ReasoningVisionToolsJSON
Coding57
Agentic29
131K context33K output$0.09/1M in

DeepSeek V4.1 Flash

Text

DeepSeek

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

ReasoningVisionToolsJSON
1M context944K output$0.076/1M in

GPT Image 2.5 Sunburst

Image

OpenAI

GPT Image 2.5 Sunburst is an image generation and editing model from OpenAI, positioned as the precision-oriented tier of the GPT Image 2.5 series. It is suited to detailed creative...

VisionJSON
400K context360K output~$0.015/image

GPT Image 2.5 Flare

Image

OpenAI

GPT Image 2.5 Flare is an image generation and editing model from OpenAI, positioned as the speed-oriented tier of the GPT Image 2.5 series. It is suited to high-volume everyday...

VisionJSON
400K context360K output~$0.058/image

Nex-N2.5-Mini

Text

NEX-AGI

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...

ReasoningVisionJSON
262K context236K output$0.037/1M in

Nex-N2.5-Pro

Text

NEX-AGI

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...

ReasoningVisionToolsJSON
262K context236K output$0.11/1M in

GPT-6 Astra

Text

OpenAI

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...

ReasoningVisionToolsJSON
Intelligence57
Coding77
Agentic51
1.1M context128K output$15.00/1M in

GPT-6 Astra Pro

Text

OpenAI

GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...

ReasoningVisionToolsJSON
1.1M context128K output$15.00/1M in

MAI-Image-2.6

Image

Microsoft

MAI-Image-2.6 is an image generation and editing model from Microsoft AI, the precision tier of the MAI-Image-2.6 family alongside the faster MAI-Image-2.6 Flash. It is suited for design-ready visuals and...

Vision
4K context1K output~$0.058/image

MAI-Image-2.6 Flash

Image

Microsoft

MAI-Image-2.6 Flash is the lower-latency, lower-cost member of the MAI-Image-2.6 family from Microsoft AI, built for latency-sensitive, high-throughput production image generation and editing at comparable quality to the precision tier....

Vision
4K context1K output~$0.037/image

Qwen3.8 Max (0902)

Text

Qwen

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...

ReasoningVisionToolsJSON
Intelligence34
Coding76
Agentic56
1M context131K output$3.00/1M in

Muse Spark 1.3 Contributor

Text

Meta

Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...

ReasoningVisionToolsJSON
1M context944K output$0.15/1M in

Muse Spark 1.3

Text

Meta

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...

ReasoningVisionToolsJSON
Intelligence37
Coding76
Agentic56
1M context944K output$1.88/1M in

Gemini 3.8 Flash

Text

Google

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

ReasoningVisionToolsJSON
Intelligence31
Coding76
Agentic40
1M context66K output$1.24/1M in

MiniMax H3 Max

Video

MiniMax

MiniMax H3 Max is a video-generation model from MiniMax. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with...

Vision
$0.075–$0.12/sec

Claude Fable 5.1

Text

Anthropic

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...

ReasoningVisionToolsJSON
Intelligence50
Coding81
Agentic57
1M context128K output$15.00/1M in

Granite 4.2 8B

Text

IBM Granite

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...

ReasoningToolsJSON
Intelligence5
Coding22
Agentic1
131K context118K output$0.09/1M in

Hy4 preview

Text

Tencent

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

ReasoningToolsJSON
1M context64K output$1.25/1M in

Wan 3.0 Prime

Video

Alibaba

Wan 3.0 Prime is a fast-mode variant of Wan 3.0 from Alibaba. It supports text-to-video and first-frame image-to-video generation.

VisionJSON
$0.10–$0.42/sec

GLM Flash Latest

Text

Z.AI

This model always redirects to the latest model in the GLM Flash family.

ReasoningVisionToolsJSON
1M context131K output$0.06/1M in

Qwen3.8 Flash

Text

Qwen

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

ReasoningVisionToolsJSON
1M context131K output$0.23/1M in

Muse Image

Image

Meta

Muse Image is an agentic image generation model from Meta that generates and edits images from text and reference images. Unlike single-pass image models, it reasons before it renders, breaking...

Vision
66K context59K output~$0.015/image

GLM 5.3 Flash

Text

Z.AI

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

ReasoningVisionToolsJSON
Intelligence28
Coding72
Agentic51
1M context131K output$0.06/1M in

Recraft V4 Styles Pro

Image

Recraft

Recraft V4 Styles Pro is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the reference's...

Vision
66K context59K output~$0.15/image

Recraft V4 Styles Vector

Image

Recraft

Recraft V4 Styles Vector is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the reference's...

Vision
66K context59K output~$0.075/image

Recraft V4 Styles Pro Vector

Image

Recraft

Recraft V4 Styles Pro Vector is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the...

Vision
66K context59K output~$0.18/image

Recraft V4 Styles

Image

Recraft

Recraft V4 Styles is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the reference's rendering...

Vision
66K context59K output~$0.052/image

Wan 3.0

Video

Alibaba

Wan 3.0 is a video generation model from Alibaba for text-to-video, image-to-video, and reference-guided video generation. It produces 480p, 720p, or 1080p video with durations from 2 to 30 seconds.

VisionJSON
$0.064–$0.26/sec
HE

Avatar IV

Video

Heygen

HeyGen: Avatar IV is an image-to-video model that animates a single photo into an expressive, lip-synced talking-head video. Rather than only matching mouth shapes to words, it interprets the vocal...

Vision
$0.075/sec

Muse Spark 1.2 Contributor

Text

Meta

Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...

ReasoningVisionToolsJSON
1M context944K output$0.15/1M in

DeepSeek V4 Flash Vision Exp

Text

DeepSeek

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

ReasoningVisionToolsJSON
Coding65
Agentic48
1M context944K output$0.66/1M in

Hy-MT2-1.8B

Text

Tencent

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...

8K context4K output$0.066/1M in

Hy-MT2-30B-A3B

Text

Tencent

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...

JSON
8K context4K output$0.11/1M in

FLUX Video Upscale

Video

Black Forest Labs

FLUX Video Upscale is a video upscaling model from Black Forest Labs. It enlarges a single source video by 1.5× to 3× while preserving its duration, with an optional prompt...

$0.048/sec

GLM Latest

Text

Z.AI

This model always redirects to the latest GLM model from Z.ai.

ReasoningToolsJSON
1M context944K output$0.10/1M in

Hy-MT2-7B

Text

Tencent

Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

JSON
8K context4K output$0.11/1M in

GLM 5.3

Text

Z.AI

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

ReasoningToolsJSON
Intelligence32
Coding75
Agentic53
1M context944K output$0.10/1M in

Qwen3.8 27B

Text

Qwen

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

ReasoningVisionToolsJSON
Intelligence20
Coding68
Agentic46
1M context236K output$0.23/1M in
DS

Dots3-Note Preview (free)

Text

Dots Studio

Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...

ReasoningVisionToolsJSON
512K context461K outputFree

Seedream 5.0 Lite

Image

ByteDance

Seedream 5.0 Lite is an image generation model from ByteDance Seed. It is suited for professional visual creation that benefits from web-connected retrieval, complex-prompt comprehension, visual references, and broad knowledge...

Vision
~$0.052/image

Gemini 3.7 Flash

Text

Google

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

ReasoningVisionToolsJSON
Coding76
Agentic35
1M context66K output$1.13/1M in

Seedream 5.0 Pro

Image

ByteDance

Seedream 5.0 Pro is an image generation and editing model from ByteDance Seed. It is suited for commercial visual-production workflows that require precise editing control, lifelike scenes, and natural rendering.

Vision
~$0.068/image

Seedance 2.0 Mini

Video

ByteDance

Seedance 2.0 Mini is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video with image, video, and audio inputs. It...

Vision
$0.05–$0.11/sec

Seed 2.1 Turbo

Text

ByteDance

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...

ReasoningVisionToolsJSON
262K context236K output$0.75/1M in

Qwen3.8 2.4T A95B

Text

Qwen

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is...

ReasoningToolsJSON
Coding72
Agentic50
1M context131K output$3.00/1M in

Seed-2.0-Code

Text

ByteDance

Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...

ReasoningVisionToolsJSON
262K context131K output$0.75/1M in

DeepSeek V4 Pro 0813

Text

DeepSeek

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

ReasoningToolsJSON
Intelligence23
Coding69
Agentic41
1M context944K output$0.17/1M in

Grok 4.6

Text

xAI

Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.

ReasoningVisionToolsJSON
Intelligence31
Coding76
Agentic53
500K context450K output$3.00/1M in

Grok Imagine Image 2.0

Image

xAI

Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and...

VisionJSON
66K context59K output~$0.09/image

LFM2.5-2.6B

Text

Liquid AI

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...

ReasoningToolsJSON
Coding8
128K context8K output$0.53/1M in

LFM2.5-2.6B (free)

Text

Liquid AI

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...

ReasoningToolsJSON
Coding8
66K context8K outputFree

Nemotron 3.5 Lightning

Text

NVIDIA

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

ReasoningToolsJSON
Intelligence6
Coding27
Agentic4
262K context236K output$0.10/1M in

Nemotron 3.5 Lightning (free)

Text

NVIDIA

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

ReasoningTools
Intelligence6
Coding27
Agentic4
1M context66K outputFree

Sakana Namazu

Text

Sakana AI

Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...

ReasoningVisionToolsJSON
262K context66K output$1.43/1M in

Solar Pro 4

Text

Upstage

Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...

ReasoningToolsJSON
Intelligence28
Coding53
524K context131K output$0.23/1M in

Muse Glimmer 30B

Text

Meta

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

ReasoningVisionToolsJSON
Intelligence6
Coding49
Agentic9
131K context16K output$0.45/1M in

Seedance 2.5

Video

ByteDance

Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and first-and-last-frame control, up...

Vision
$0.15–$0.35/sec

Ling 3.0 Tiny

Text

inclusionAI

Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...

ReasoningToolsJSON
Coding27
Agentic4
262K context250K output$0.022/1M in

Muse Spark 1.2

Text

Meta

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....

ReasoningVisionToolsJSON
Coding72
Agentic43
1M context944K output$1.88/1M in

Qwen Image 3

Image

Qwen

Qwen Image 3 is a unified image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with a richer world...

VisionJSON
66K context59K output~$0.045/image

Qwen Image 3 Pro

Image

Qwen

Qwen Image 3 Pro is an image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with richer world knowledge...

VisionJSON
66K context59K output~$0.06/image

FLUX 3 Video

Video

Black Forest Labs

FLUX.3 Video is a video generation model from Black Forest Labs. It supports text-to-video, image-guided generation with opening and closing keyframes, and video continuation workflows, making it suited for controlled...

Vision
$0.26–$0.61/sec

DeepSeek V4 Flash Latest

Text

DeepSeek

This model always redirects to the latest model in the DeepSeek V4 Flash family.

ReasoningToolsJSON
1M context944K output$0.065/1M in

DeepSeek V4 Flash 0731

Text

DeepSeek

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

ReasoningToolsJSON
Coding69
Agentic41
1M context944K output$0.065/1M in
TH

Inkling Small

Text

Thinkingmachines

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

ReasoningVisionTools
Intelligence13
Coding53
Agentic24
524K context262K output$0.68/1M in

MiniMax H3

Video

MiniMax

MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and...

Vision
$0.20/sec
RU

Aleph 2.0

Video

Runway

Runway Aleph 2.0 is an in-context video editing model from Runway. It applies text instructions and keyframe-guided edits across existing footage while preserving details that are not meant to change....

Vision
$0.42/sec
RU

Gen-4.5

Video

Runway

Runway Gen-4.5 is a video generation model from Runway for text-to-video and image-to-video workflows. It is designed for cinematic scene creation with strong motion quality, visual fidelity, and prompt adherence....

Vision
$0.18/sec

Qwen3.7 Flash

Text

Qwen

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...

ReasoningVisionToolsJSON
1M context66K output$0.045/1M in

Claude Opus 5

Text

Anthropic

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

ReasoningVisionToolsJSON
Intelligence44
Coding78
Agentic57
1M context128K output$7.50/1M in

MAI-Image-2.5 Pro

Image

Microsoft

Microsoft AI's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.

Vision
4K context1K output~$0.21/image

Ling 3.0 Flash

Text

inclusionAI

Ling-3.0-flash is a 124B-parameter Mixture-of-Experts (MoE) model, with approximately 5.1B parameters activated per token. The model is designed with token efficiency and production-scale agentic inference as key priorities, enabling developers...

ReasoningToolsJSON
Coding51
Agentic19
262K context33K output$0.032/1M in

Gemini 3.6 Flash

Text

Google

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

ReasoningVisionToolsJSON
Coding69
Agentic29
1M context66K output$1.13/1M in

Gemini 3.5 Flash Lite

Text

Google

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

ReasoningVisionToolsJSON
Intelligence12
Coding49
Agentic14
1M context66K output$0.45/1M in
KR

Krea 2 Large

Image

Krea

Krea 2 Large is Krea's high-capability image generation model, more than twice the size of Krea 2 Medium. Its lighter post-training gives images a rawer, more textured, and flexible character,...

Vision
66K context59K output~$0.09/image
KR

Krea 2 Medium

Image

Krea

Krea 2 Medium is Krea's balanced, cost-efficient image generation model and a practical starting point for a broad range of use cases. Its extensive post-training supports stable, consistent generations, with...

Vision
66K context59K output~$0.045/image
KR

Krea 2 Medium Turbo

Image

Krea

Krea 2 Medium Turbo is a distilled, speed-focused variant of Krea 2 Medium from Krea. It is designed for rapid iteration and graphic design exploration where fast generation is the...

Vision
66K context59K output~$0.023/image
ME

LongCat 2.0

Text

Meituan

LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...

ReasoningTools
Coding45
Agentic14
1M context262K output$0.45/1M in

Grok Imagine Video 1.5

Video

xAI

Grok Imagine Video 1.5 is a video generation model from SpaceXAI. It creates videos from text prompts, with an optional starting image to guide the scene. It can direct subject...

VisionJSON
$0.12–$0.38/sec
TH

Inkling

Text

Thinkingmachines

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

ReasoningVisionTools
Intelligence13
Coding52
Agentic23
524K context472K output$1.50/1M in

Kimi K3

Text

Moonshot AI

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

ReasoningVisionToolsJSON
Intelligence17
Coding72
Agentic29
1M context944K output$0.29/1M in

Muse Spark 1.1

Text

Meta

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....

ReasoningVisionToolsJSON
Coding71
Agentic26
1M context944K output$1.88/1M in

GPT-5.6 Luna Pro

Text

OpenAI

GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...

ReasoningVisionToolsJSON
1.1M context128K outputcutoff 2026-02-16$0.30/1M in

GPT-5.6 Luna

Text

OpenAI

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

ReasoningVisionToolsJSON
Intelligence24
Coding71
Agentic42
1.1M context128K outputcutoff 2026-02-16$0.30/1M in

GPT-5.6 Terra Pro

Text

OpenAI

GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...

ReasoningVisionToolsJSON
1.1M context128K outputcutoff 2026-02-16$3.00/1M in

GPT-5.6 Terra

Text

OpenAI

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...

ReasoningVisionToolsJSON
Intelligence32
Coding77
Agentic43
1.1M context128K outputcutoff 2026-02-16$3.00/1M in

GPT-5.6 Sol Pro

Text

OpenAI

GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...

ReasoningVisionToolsJSON
1.1M context128K outputcutoff 2026-02-16$6.00/1M in

GPT-5.6 Sol

Text

OpenAI

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...

ReasoningVisionToolsJSON
Coding78
Agentic47
1.1M context128K outputcutoff 2026-02-16$6.00/1M in

Grok 4.5

Text

xAI

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

ReasoningVisionToolsJSON
Coding72
Agentic41
500K context450K output$3.00/1M in

Grok Latest

Text

xAI

This model always redirects to the latest Grok model from xAI.

ReasoningVisionToolsJSON
500K context450K output$3.00/1M in

Aion-3.0-Mini

Text

AionLabs

Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...

ReasoningToolsJSON
131K context33K output$1.05/1M in

Aion-3.0

Text

AionLabs

Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...

ReasoningToolsJSON
131K context33K output$4.50/1M in

Hy3

Text

Tencent

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

ReasoningToolsJSON
262K context128K output$0.20/1M in

Claude Sonnet 5

Text

Anthropic

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

ReasoningVisionToolsJSON
Coding72
Agentic44
1M context128K output$3.00/1M in

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Image

Google

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

ReasoningVisionJSON
66K context59K outputcutoff 2025-01-01~$0.058/image

Fugu Ultra

Text

Sakana AI

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

ReasoningVisionToolsJSON
1M context128K output$7.50/1M in

HappyHorse 1.1

Video

Alibaba

HappyHorse 1.1 is a video generation model from Alibaba. It generates short videos from a text prompt, a single starting image, or a set of reference images, with output up...

VisionJSON
$0.15–$0.19/sec

GPT Image 2

Image

OpenAI

OpenAI's latest image generation model. Supports high-fidelity image generation and editing via the dedicated Images API.

VisionJSON
400K context360K output~$0.058/image

GPT Image 1

Image

OpenAI

OpenAI's GPT Image 1 generates and edits images via the dedicated Images API. Features accurate text rendering, transparent backgrounds, and up to 16 reference images for edits.

VisionJSON
400K context360K output~$0.077/image

GPT Image 1 Mini

Image

OpenAI

A cost-efficient variant of GPT Image 1 for high-quality image generation at reduced latency and cost via OpenAI's dedicated Images API.

VisionJSON
400K context360K output~$0.031/image

HappyHorse 1.0

Video

Alibaba

HappyHorse 1.0 is a video generation model from Alibaba. It generates short videos from a text prompt, a single starting image, or a set of reference images, with output up...

VisionJSON
$0.15–$0.25/sec

Nano Banana 2 (Gemini 3.1 Flash Image)

Image

Google

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

ReasoningVisionJSON
131K context33K output~$0.12/image

Nano Banana Pro (Gemini 3 Pro Image)

Image

Google

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

ReasoningVisionToolsJSON
131K context33K output~$0.23/image

North Mini Code (free)

Text

Cohere

North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...

ReasoningTools
Intelligence3
Coding37
Agentic1
256K context64K outputFree

GLM 5.2

Text

Z.AI

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

ReasoningToolsJSON
Coding69
Agentic38
1M context944K output$0.011/1M in

Kimi K2.7 Code

Text

Moonshot AI

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

ReasoningVisionToolsJSON
Coding61
Agentic21
262K context236K output$0.90/1M in

Claude Fable Latest

Text

Anthropic

This model always redirects to the latest model in the Claude Fable family.

ReasoningVisionToolsJSON
1M context128K output$12.00/1M in

Claude Fable 5

Text

Anthropic

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

ReasoningVisionToolsJSON
Coding77
Agentic51
1M context128K output$15.00/1M in

Riverflow V2.5 Pro

Image

Sourceful

Riverflow V2.5 Pro is the most powerful variant of Sourceful's Riverflow 2.5 lineup, best for top-tier control and quality-sensitive outputs. The Riverflow 2.5 series is a unified text-to-image and image-to-image...

ReasoningVision
33K context29K output~$0.19/image

Riverflow V2.5 Fast

Image

Sourceful

Riverflow V2.5 Fast is the speed-optimized variant of Sourceful's Riverflow 2.5 lineup, best for production deployments and latency-critical workflows. The Riverflow 2.5 series is a unified text-to-image and image-to-image family...

ReasoningVision
33K context29K output~$0.028/image

Nemotron 3.5 Content Safety

Text

NVIDIA

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

ReasoningVision
131K context118K output$0.30/1M in

Nemotron 3 Ultra

Text

NVIDIA

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

ReasoningToolsJSON
Intelligence12
Coding49
Agentic20
262K context183K output$0.90/1M in

Nemotron 3 Ultra (free)

Text

NVIDIA

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

ReasoningTools
Intelligence12
Coding49
Agentic20
1M context66K outputFree

Qwen3.7 Plus

Text

Qwen

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...

ReasoningVisionToolsJSON
Coding56
Agentic18
1M context131K output$0.48/1M in

MAI-Image-2.5

Image

Microsoft

Microsoft AI's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.

Vision
4K context1K output~$0.091/image

MiniMax M3

Text

MiniMax

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

ReasoningVisionToolsJSON
Intelligence19
Coding59
Agentic30
1M context512K output$0.45/1M in

Step 3.7 Flash

Text

StepFun

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

ReasoningVisionToolsJSON
Coding40
262K context230K output$0.30/1M in

Claude Opus 4.8

Text

Anthropic

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

ReasoningVisionToolsJSON
Coding74
Agentic42
1M context128K output$7.50/1M in

Qwen3.7 Max

Text

Qwen

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...

ReasoningToolsJSON
Coding66
Agentic23
1M context131K output$2.21/1M in

Grok Build 0.1

Text

xAI

Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...

ReasoningVisionToolsJSON
Coding52
256K context230K output$1.50/1M in

Gemini 3.5 Flash

Text

Google

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

ReasoningVisionToolsJSON
Coding70
Agentic26
1M context66K outputcutoff 2025-01-01$2.25/1M in

Grok Imagine Video

Video

xAI

Grok Imagine Video is SpaceXAI's fast, text-, image-, and reference-conditioned video generation model. It produces short videos (1–15 seconds, 24 fps) at 480p or 720p across seven aspect ratios -...

VisionJSON
$0.075–$0.10/sec

Recraft V4.1 Pro Vector

Image

Recraft

Recraft V4.1 Pro Vector is the vector (SVG) variant of Recraft V4.1 Pro, tuned for high aesthetics. It supports text and image inputs and produces higher-resolution SVG image output across...

Vision
66K context59K output~$0.45/image

Recraft V4.1 Vector

Image

Recraft

Recraft V4.1 Vector is the vector (SVG) variant of Recraft V4.1, tuned for high aesthetics. It supports text and image inputs and produces SVG image output across multiple aspect ratios,...

Vision
66K context59K output~$0.12/image

Recraft V4.1 Utility Pro

Image

Recraft

Recraft V4.1 Utility Pro is a general-purpose image generation model from Recraft. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios — double...

Vision
66K context59K output~$0.32/image

Recraft V4.1 Utility

Image

Recraft

Recraft V4.1 Utility is a general-purpose image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios, with typical generation...

Vision
66K context59K output~$0.052/image

Recraft V4.1 Pro

Image

Recraft

Recraft V4.1 Pro is an image generation model from Recraft tuned for high aesthetics. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios...

Vision
66K context59K output~$0.32/image

Recraft V4.1

Image

Recraft

Recraft V4.1 is an image generation model from Recraft tuned for high aesthetics. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios, with...

Vision
66K context59K output~$0.052/image

Recraft V4 Pro Vector

Image

Recraft

Recraft V4 Pro Vector is the vector (SVG) variant of Recraft V4 Pro. It supports text and image inputs and produces vector image output across multiple aspect ratios at the...

Vision
66K context59K output~$0.45/image

Recraft V4 Vector

Image

Recraft

Recraft V4 Vector is the vector (SVG) variant of Recraft V4. It supports text and image inputs and produces vector image output across multiple aspect ratios. Compared to the raster...

Vision
66K context59K output~$0.12/image

Perceptron Mk1

Text

Perceptron

Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...

ReasoningVisionJSON
33K context8K output$0.23/1M in

Recraft V4 Pro

Image

Recraft

Recraft V4 Pro is an image generation model from Recraft. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios, double the resolution of...

Vision
66K context59K output~$0.38/image

Recraft V4

Image

Recraft

Recraft V4 is an image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios. It delivers stronger compositional judgment,...

Vision
66K context59K output~$0.06/image

Recraft V3

Image

Recraft

Recraft V3 is an image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios. Supports the following image_config parameters:...

Vision
66K context59K output~$0.06/image

Gemini 3.1 Flash Lite

Text

Google

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...

ReasoningVisionToolsJSON
1M context66K output$0.38/1M in

GPT Chat Latest

Text

OpenAI

GPT Chat Latest points to OpenAI's stable API alias chat-latest that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...

VisionToolsJSON
400K context128K output$7.50/1M in

Grok 4.3

Text

xAI

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

ReasoningVisionToolsJSON
Coding42
Agentic16
1M context900K output$1.88/1M in

Mistral Medium 3.5

Text

Mistral AI

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

ReasoningVisionToolsJSON
Intelligence5
Coding47
Agentic7
262K context210K output$2.25/1M in

Kling Video v3.0 Pro

Video

Kuaishou

Kling v3.0 Pro is Kuaishou's premium video generation model, offering higher visual quality than the Standard tier. It supports text-to-video and image-to-video workflows, with first-frame and last-frame control for precise...

Vision
$0.25/sec

Kling Video v3.0 Standard

Video

Kuaishou

Kling v3.0 Standard is a video generation model from Kuaishou. It supports text-to-video and image-to-video workflows, with first-frame and last-frame control for guided scene composition. Clips range from 3 to...

Vision
$0.19/sec

Nemotron 3 Nano Omni (free)

Text

NVIDIA

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

ReasoningVisionTools
Coding14
256K context66K outputFree

Claude Haiku Latest

Text

Anthropic

This model always redirects to the latest model in the Claude Haiku family.

ReasoningVisionToolsJSON
1M context128K output$0.15/1M in

GPT Mini Latest

Text

OpenAI

This model always redirects to the latest model in the GPT Mini family.

ReasoningVisionToolsJSON
400K context128K outputcutoff 2025-08-31$1.13/1M in

Gemini Pro Latest

Text

Google

This model always redirects to the latest model in the Gemini Pro family.

ReasoningVisionToolsJSON
1M context944K output$3.00/1M in

Kimi Latest

Text

Moonshot AI

This model always redirects to the latest model in the Kimi family.

ReasoningVisionToolsJSON
1M context944K output$0.27/1M in

Gemini Flash Latest

Text

Google

This model always redirects to the latest model in the Gemini Flash family.

ReasoningVisionToolsJSON
1M context66K output$1.13/1M in

Claude Sonnet Latest

Text

Anthropic

This model always redirects to the latest model in the Claude Sonnet family.

ReasoningVisionToolsJSON
1M context128K output$3.00/1M in

Qwen3.5 Plus 2026-04-20

Text

Qwen

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...

ReasoningVisionToolsJSON
1M context66K output$0.45/1M in

Qwen3.6 Flash

Text

Qwen

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window.

ReasoningVisionToolsJSON
1M context66K output$0.28/1M in

Qwen3.6 35B A3B

Text

Qwen

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

ReasoningVisionToolsJSON
Coding42
Agentic13
262K context236K output$0.15/1M in

Qwen3.6 27B

Text

Qwen

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

ReasoningVisionToolsJSON
Coding54
Agentic19
262K context82K output$0.48/1M in

GPT-5.5 Pro

Text

OpenAI

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...

ReasoningVisionToolsJSON
1.1M context128K outputcutoff 2025-12-01$45.00/1M in

GPT-5.5

Text

OpenAI

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

ReasoningVisionToolsJSON
Coding75
Agentic36
1.1M context128K outputcutoff 2025-12-01$7.50/1M in

DeepSeek V4 Pro 0423

Text

DeepSeek

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

ReasoningToolsJSON
Intelligence13
1M context384K output$1.43/1M in

DeepSeek V4 Flash 0423

Text

DeepSeek

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

ReasoningToolsJSON
Coding56
Agentic22
1M context393K output$0.14/1M in

Veo 3.1 Fast

Video

Google

Google's mid-tier video generation model balancing speed and quality. Veo 3.1 Fast generates high-quality video from text or image prompts with native synchronized audio, offering faster turnaround than Veo 3.1...

VisionJSON
$0.15–$0.45/sec

Veo 3.1 Lite

Video

Google

Google's most cost-effective video generation model, designed for high-volume applications and rapid iteration. Veo 3.1 Lite generates 720p and 1080p video from text or image prompts with native synchronized audio...

VisionJSON
$0.075–$0.12/sec

Hy3 preview

Text

Tencent

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

ReasoningTools
Coding59
Agentic24
262K context236K output$0.27/1M in

MiMo-V2.5-Pro

Text

Xiaomi

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....

ReasoningToolsJSON
Coding60
Agentic21
1M context236K output$0.72/1M in

MiMo-V2.5

Text

Xiaomi

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

ReasoningVisionToolsJSON
Coding57
Agentic16
1M context66K output$0.60/1M in

GPT-5.4 Image 2

Image

OpenAI

GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...

ReasoningVisionJSON
272K context128K output~$0.058/image

Claude Opus Latest

Text

Anthropic

This model always redirects to the latest model in the Claude Opus family.

ReasoningVisionToolsJSON
1M context128K output$6.00/1M in

Kling Video O1

Video

Kuaishou

Kling Video O1 is a video generation model from Kuaishou. It supports text and image inputs with video output, enabling text-to-video and image-to-video workflows. It is suited for cinematic content...

Vision
$0.17/sec

Hailuo 2.3

Video

MiniMax

Hailuo 2.3 is a video generation model from MiniMax. It accepts text prompts and reference images as input and generates video output, supporting both text-to-video and image-to-video workflows. It is...

Vision
$0.12/sec

Kimi K2.6

Text

Moonshot AI

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

ReasoningVisionToolsJSON
Coding62
Agentic21
262K context236K output$0.97/1M in

Claude Opus 4.7

Text

Anthropic

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...

ReasoningVisionToolsJSON
Coding74
Agentic39
1M context128K output$7.50/1M in

Wan 2.7

Video

Alibaba

Wan 2.7 is a video generation model from Alibaba. It supports text-to-video, image-to-video with first and last frame control, and reference-to-video, where multiple reference images guide the style and content...

Vision
$0.15/sec

Seedance 2.0

Video

ByteDance

Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency,...

Vision
$0.10–$1.17/sec

Seedance 2.0 Fast

Video

ByteDance

Seedance 2.0 Fast is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It prioritizes generation speed and lower cost...

Vision
$0.061–$0.14/sec

GLM 5.1

Text

Z.AI

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...

ReasoningToolsJSON
Coding56
Agentic24
205K context131K output$2.00/1M in

Gemma 4 26B A4B

Text

Google

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

ReasoningVisionToolsJSON
Coding39
Agentic3
262K context128K output$0.12/1M in

Gemma 4 26B A4B (free)

Text

Google

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

ReasoningVisionToolsJSON
Coding39
Agentic3
262K context33K outputFree

Gemma 4 31B

Text

Google

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

ReasoningVisionToolsJSON
Intelligence4
Coding43
Agentic4
262K context16K output$0.30/1M in

Gemma 4 31B (free)

Text

Google

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

ReasoningVisionToolsJSON
Intelligence4
Coding43
Agentic4
262K context33K outputFree

Qwen3.6 Plus

Text

Qwen

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

ReasoningVisionToolsJSON
Coding55
1M context66K output$0.49/1M in

GLM 5V Turbo

Text

Z.AI

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...

ReasoningVisionToolsJSON
203K context131K output$1.80/1M in

Grok 4.20 Multi-Agent

Text

xAI

Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...

ReasoningVisionJSON
2M context1.8M outputcutoff 2025-09-01$1.88/1M in

Grok 4.20

Text

xAI

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

ReasoningVisionToolsJSON
2M context1.8M outputcutoff 2025-09-01$1.88/1M in

Lyria 3 Pro Preview

Audio

Google

Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...

VisionJSON
1M context66K output~$0.12

Lyria 3 Clip Preview

Audio

Google

Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...

VisionJSON
1M context66K output~$0.06

Wan 2.6

Video

Alibaba

Alibaba's most advanced video generation model, supporting over 10 visual creation capabilities in a unified system. Wan 2.6 generates 1080p video at 24fps from text, images, reference videos, or audio,...

Vision
$0.12–$0.18/sec

Seedance 1.5 Pro

Video

ByteDance

ByteDance's next-generation audio-visual generation model with a 4.5B parameter Dual-Branch Diffusion Transformer architecture. Seedance 1.5 Pro generates video and audio simultaneously in a single unified pass — eliminating the timing...

Vision
$0.035–$0.17/sec

Veo 3.1

Video

Google

Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio —...

VisionJSON
$0.60–$0.90/sec

Reka Edge

Text

Reka

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...

VisionToolsJSON
16K context15K output$0.15/1M in

MiniMax M2.7

Text

MiniMax

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

ReasoningToolsJSON
Coding53
Agentic15
197K context177K output$0.32/1M in

GPT-5.4 Nano

Text

OpenAI

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

ReasoningVisionToolsJSON
Coding56
Agentic16
400K context128K outputcutoff 2025-08-31$0.30/1M in

GPT-5.4 Mini

Text

OpenAI

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...

ReasoningVisionToolsJSON
Coding56
Agentic18
400K context128K outputcutoff 2025-08-31$1.13/1M in

Mistral Small 4

Text

Mistral AI

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

ReasoningVisionToolsJSON
Intelligence4
Coding27
Agentic1
262K context210K output$0.23/1M in

GLM 5 Turbo

Text

Z.AI

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...

ReasoningToolsJSON
203K context131K output$1.80/1M in

Nemotron 3 Super

Text

NVIDIA

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

ReasoningToolsJSON
Coding38
Agentic2
1M context16K output$0.11/1M in

Seed-2.0-Lite

Text

ByteDance

Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...

ReasoningVisionToolsJSON
262K context131K output$0.38/1M in

Qwen3.5-9B

Text

Qwen

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...

ReasoningVisionToolsJSON
Coding29
Agentic1
262K context236K output$0.26/1M in

GPT-5.4 Pro

Text

OpenAI

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...

ReasoningVisionToolsJSON
1.1M context128K output$45.00/1M in

GPT-5.4

Text

OpenAI

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

ReasoningVisionToolsJSON
Coding71
1.1M context128K output$3.75/1M in

Gemini 3.1 Flash Lite Preview

Text

Google

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...

ReasoningVisionToolsJSON
Intelligence6
Coding35
Agentic2
1M context66K output$0.38/1M in

Seed-2.0-Mini

Text

ByteDance

Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...

ReasoningVisionToolsJSON
262K context131K output$0.15/1M in

Nano Banana 2 (Gemini 3.1 Flash Image Preview)

Image

Google

Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...

ReasoningVisionJSON
66K context59K output~$0.12/image

Qwen3.5-35B-A3B

Text

Qwen

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...

ReasoningVisionToolsJSON
Coding37
262K context82K output$0.21/1M in

Qwen3.5-27B

Text

Qwen

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...

ReasoningVisionToolsJSON
262K context82K output$0.39/1M in

Qwen3.5-122B-A10B

Text

Qwen

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...

ReasoningVisionToolsJSON
Coding46
Agentic8
262K context66K output$0.39/1M in

Qwen3.5-Flash

Text

Qwen

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...

ReasoningVisionToolsJSON
1M context66K output$0.098/1M in

Gemini 3.1 Pro Preview Custom Tools

Text

Google

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...

ReasoningVisionToolsJSON
1M context66K output$3.00/1M in

GPT-5.3-Codex

Text

OpenAI

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...

ReasoningVisionToolsJSON
400K context128K output$2.63/1M in

Aion-2.0

Text

AionLabs

Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....

ReasoningToolsJSON
131K context33K output$1.20/1M in

Gemini 3.1 Pro Preview

Text

Google

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

ReasoningVisionToolsJSON
Coding69
Agentic8
1M context66K output$3.00/1M in

Claude Sonnet 4.6

Text

Anthropic

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...

ReasoningVisionToolsJSON
Coding63
Agentic32
1M context128K output$4.50/1M in

Qwen3.5 Plus 2026-02-15

Text

Qwen

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

ReasoningVisionToolsJSON
1M context66K output$0.39/1M in

Qwen3.5 397B A17B

Text

Qwen

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

ReasoningVisionToolsJSON
Coding48
Agentic8
262K context64K output$0.90/1M in

MiniMax M2.5

Text

MiniMax

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

ReasoningToolsJSON
200K context59K output$0.45/1M in

GLM 5

Text

Z.AI

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

ReasoningToolsJSON
205K context131K output$1.50/1M in

Claude Opus 4.6

Text

Anthropic

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

ReasoningVisionToolsJSON
1M context128K output$7.50/1M in

Qwen3 Coder Next

Text

Qwen

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

ToolsJSON
Coding36
Agentic1
262K context236K output$0.18/1M in

Riverflow V2 Pro

Image

Sourceful

Riverflow V2 Pro is the most powerful variant of Sourceful's Riverflow 2.0 lineup, best for top-tier control and perfect text rendering. The Riverflow 2.0 series represents SOTA performance on image...

Vision
8K context7K output~$0.23/image

Riverflow V2 Fast

Image

Sourceful

Riverflow V2 Fast is the fastest variant of Sourceful's Riverflow 2.0 lineup, best for production deployments and latency-critical workflows. The Riverflow 2.0 series represents SOTA performance on image generation and...

Vision
8K context7K output~$0.03/image

Step 3.5 Flash

Text

StepFun

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

ReasoningTools
262K context66K output$0.15/1M in

Kimi K2.5

Text

Moonshot AI

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

ReasoningVisionToolsJSON
Coding47
262K context66K output$0.80/1M in

Palmyra X5

Text

Writer

Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...

1M context8K output$0.90/1M in

GPT Audio

Audio

OpenAI

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.

ToolsJSON
128K context16K output$0.12/min

GPT Audio Mini

Audio

OpenAI

A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.

ToolsJSON
128K context16K output$0.0045/min

GLM 4.7 Flash

Text

Z.AI

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...

ReasoningToolsJSON
200K context118K output$0.091/1M in

FLUX.2 Klein 4B

Image

Black Forest Labs

FLUX.2 [klein] 4B is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality.

Vision
41K context37K output~$0.021/image

GPT-5.2-Codex

Text

OpenAI

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

ReasoningVisionToolsJSON
400K context128K output$2.63/1M in

Seedream 4.5

Image

ByteDance

Seedream 4.5 is the latest in-house image generation model developed by ByteDance. Compared with Seedream 4.0, it delivers comprehensive improvements, especially in editing consistency, including better preservation of subject details,...

Vision
4K context4K output~$0.06/image

Seed 1.6 Flash

Text

ByteDance

Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...

ReasoningVisionToolsJSON
262K context33K output$0.11/1M in

Seed 1.6

Text

ByteDance

Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.

ReasoningVisionToolsJSON
262K context33K output$0.38/1M in

GLM 4.7

Text

Z.AI

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

ReasoningToolsJSON
Coding45
205K context131K output$0.90/1M in

Gemini 3 Flash Preview

Text

Google

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

ReasoningVisionToolsJSON
1M context66K output$0.75/1M in

FLUX.2 Max

Image

Black Forest Labs

FLUX.2 [max] is the new top-tier image model from Black Forest Labs, pushing image quality, prompt understanding, and editing consistency to the highest level yet.

Vision
47K context42K output~$0.11/image

Nemotron 3 Nano 30B A3B

Text

NVIDIA

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

ReasoningToolsJSON
Coding14
Agentic1
262K context236K output$0.09/1M in

GPT-5.2 Chat

Text

OpenAI

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...

VisionToolsJSON
128K context32K output$2.63/1M in

GPT-5.2 Pro

Text

OpenAI

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...

ReasoningVisionToolsJSON
400K context128K output$31.50/1M in

GPT-5.2

Text

OpenAI

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...

ReasoningVisionToolsJSON
400K context128K output$2.63/1M in

Devstral 2 2512

Text

Mistral AI

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

ToolsJSON
Coding31
Agentic2
262K context210K output$0.60/1M in

Relace Search

Text

Relace

The relace-search model uses 4-12 view_file and grep tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...

ToolsJSON
256K context128K output$1.50/1M in

GLM 4.6V

Text

Z.AI

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...

ReasoningVisionToolsJSON
131K context33K output$0.45/1M in

GPT-5.1-Codex-Max

Text

OpenAI

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...

ReasoningVisionToolsJSON
400K context128K output$1.88/1M in

Nova 2 Lite

Text

Amazon

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...

ReasoningVisionTools
Coding23
1M context66K output$0.45/1M in

Ministral 3 14B 2512

Text

Mistral AI

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

VisionToolsJSON
Coding14
Agentic1
262K context210K output$0.30/1M in

Ministral 3 8B 2512

Text

Mistral AI

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

VisionToolsJSON
Coding10
Agentic1
262K context210K output$0.23/1M in

Ministral 3 3B 2512

Text

Mistral AI

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

VisionToolsJSON
Coding5
Agentic1
131K context105K output$0.15/1M in

Mistral Large 3 2512

Text

Mistral AI

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

VisionToolsJSON
Coding20
Agentic1
262K context210K output$0.75/1M in

DeepSeek V3.2

Text

DeepSeek

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

ReasoningToolsJSON
Coding44
164K context147K output$0.39/1M in

FLUX.2 Flex

Image

Black Forest Labs

FLUX.2 [flex] excels at rendering complex text, typography, and fine details, and supports multi-reference editing in the same unified architecture.

Vision
67K context61K output~$0.09/image

FLUX.2 Pro

Image

Black Forest Labs

A high-end image generation and editing model focused on frontier-level visual quality and reliability. It delivers strong prompt adherence, stable lighting, sharp textures, and consistent character/style reproduction across multi-reference inputs....

Vision
47K context42K output~$0.045/image

Claude Opus 4.5

Text

Anthropic

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

ReasoningVisionToolsJSON
200K context64K output$7.50/1M in

Nano Banana Pro (Gemini 3 Pro Image Preview)

Image

Google

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

ReasoningVisionJSON
66K context33K output~$0.23/image

GPT-5.1

Text

OpenAI

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...

ReasoningVisionToolsJSON
Coding49
400K context128K output$1.88/1M in

GPT-5.1-Codex

Text

OpenAI

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

ReasoningVisionToolsJSON
400K context128K output$1.88/1M in

GPT-5.1-Codex-Mini

Text

OpenAI

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

ReasoningVisionToolsJSON
400K context128K output$0.38/1M in

Kimi K2 Thinking

Text

Moonshot AI

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

ReasoningToolsJSON
Coding21
262K context98K output$0.90/1M in

Nova Premier 1.0

Text

Amazon

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

VisionTools
1M context32K output$3.75/1M in

Sonar Pro Search

Text

Perplexity

Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis.

ReasoningVisionJSON
200K context8K output$4.50/1M in

Voxtral Small 24B 2507

Text

Mistral AI

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...

ToolsJSON
33K context26K output$0.15/1M in

gpt-oss-safeguard-20b

Text

OpenAI

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...

ReasoningToolsJSON
131K context66K output$0.11/1M in

GPT-5 Image Mini

Image

OpenAI

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...

ReasoningVisionJSON
400K context128K output~$0.015/image

Claude Haiku 4.5

Text

Anthropic

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

ReasoningVisionToolsJSON
Intelligence7
Coding44
Agentic8
200K context64K output$1.50/1M in

Qwen3 VL 8B Instruct

Text

Qwen

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

VisionToolsJSON
262K context236K output$0.38/1M in

GPT-5 Image

Image

OpenAI

GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...

ReasoningVisionJSON
400K context128K output~$0.077/image

Nano Banana (Gemini 2.5 Flash Image)

Image

Google

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...

VisionJSON
33K context8K outputcutoff 2025-01-31~$0.058/image

Qwen3 VL 30B A3B Thinking

Text

Qwen

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...

ReasoningVisionToolsJSON
262K context236K outputcutoff 2025-03-31$0.43/1M in

Qwen3 VL 30B A3B Instruct

Text

Qwen

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...

VisionToolsJSON
262K context16K outputcutoff 2025-03-31$0.23/1M in

GPT-5 Pro

Text

OpenAI

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...

ReasoningVisionToolsJSON
400K context128K outputcutoff 2024-09-30$22.50/1M in

GLM 4.6

Text

Z.AI

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...

ReasoningToolsJSON
Coding46
205K context131K outputcutoff 2025-03-31$0.75/1M in

Claude Sonnet 4.5

Text

Anthropic

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

ReasoningVisionToolsJSON
Coding52
Agentic16
1M context64K outputcutoff 2025-01-31$4.50/1M in

DeepSeek V3.2 Exp

Text

DeepSeek

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

ReasoningToolsJSON
164K context147K outputcutoff 2025-07-31$0.41/1M in
TD

Cydonia 24B V4.1

Text

TheDrummer

Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

JSON
131K context118K outputcutoff 2024-04-30$0.45/1M in

Relace Apply 3

Text

Relace

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...

256K context128K output$1.27/1M in

Qwen3 VL 235B A22B Instruct

Text

Qwen

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

VisionToolsJSON
262K context33K outputcutoff 2025-03-31$0.32/1M in

DeepSeek V3.1 Terminus

Text

DeepSeek

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

ReasoningToolsJSON
Coding44
Agentic7
164K context147K outputcutoff 2025-03-31$0.41/1M in

Qwen3 Coder Flash

Text

Qwen

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...

ToolsJSON
1M context66K outputcutoff 2025-06-30$0.29/1M in

Qwen3 Next 80B A3B Instruct

Text

Qwen

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

ToolsJSON
262K context16K outputcutoff 2025-09-30$0.14/1M in

Kimi K2 0905

Text

Moonshot AI

Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

ToolsJSON
262K context98K outputcutoff 2024-12-31$0.90/1M in

Hermes 4 405B

Text

Nous Research

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...

ReasoningJSON
131K context118K outputcutoff 2024-08-31$1.50/1M in

DeepSeek V3.1

Text

DeepSeek

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

ReasoningToolsJSON
164K context147K outputcutoff 2025-03-31$0.38/1M in

Mistral Medium 3.1

Text

Mistral AI

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...

VisionToolsJSON
Coding21
Agentic2
131K context105K outputcutoff 2025-06-30$0.60/1M in

GLM 4.5V

Text

Z.AI

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

ReasoningVisionToolsJSON
66K context16K outputcutoff 2024-12-31$0.90/1M in

GPT-5

Text

OpenAI

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

ReasoningVisionToolsJSON
Coding38
400K context128K outputcutoff 2024-09-30$1.88/1M in

GPT-5 Mini

Text

OpenAI

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

ReasoningVisionToolsJSON
Coding16
Agentic7
400K context128K outputcutoff 2024-05-31$0.38/1M in

GPT-5 Nano

Text

OpenAI

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

ReasoningVisionToolsJSON
400K context128K outputcutoff 2024-05-31$0.075/1M in

gpt-oss-120b

Text

OpenAI

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

ReasoningToolsJSON
Intelligence4
Coding30
Agentic4
131K context66K outputcutoff 2024-06-30$0.23/1M in

gpt-oss-20b

Text

OpenAI

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

ReasoningToolsJSON
Coding21
Agentic1
131K context118K outputcutoff 2024-06-30$0.045/1M in

Claude Opus 4.1

Text

Anthropic

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

ReasoningVisionTools
200K context32K outputcutoff 2025-01-31$22.50/1M in

Codestral 2508

Text

Mistral AI

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Blog Post

ToolsJSON
256K context205K outputcutoff 2025-03-31$0.45/1M in

Qwen3 Coder 30B A3B Instruct

Text

Qwen

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

ToolsJSON
262K context236K outputcutoff 2025-06-30$0.23/1M in

Qwen3 30B A3B Instruct 2507

Text

Qwen

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

ToolsJSON
262K context236K outputcutoff 2025-06-30$0.15/1M in

GLM 4.5

Text

Z.AI

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

ReasoningToolsJSON
131K context98K outputcutoff 2024-12-31$0.90/1M in

GLM 4.5 Air

Text

Z.AI

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...

ReasoningTools
131K context98K outputcutoff 2024-12-31$0.30/1M in

Qwen3 235B A22B Thinking 2507

Text

Qwen

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

ReasoningTools
Coding22
Agentic1
128K context16K outputcutoff 2025-06-30$0.68/1M in

Qwen3 Coder 480B A35B

Text

Qwen

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

ToolsJSON
262K context66K outputcutoff 2025-06-30$0.45/1M in

UI-TARS 7B

Text

ByteDance

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...

VisionJSON
128K context2K outputcutoff 2025-01-31$0.15/1M in

Gemini 2.5 Flash Lite

Text

Google

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

ReasoningVisionToolsJSON
1M context66K outputcutoff 2025-01-31$0.15/1M in

Qwen3 235B A22B Instruct 2507

Text

Qwen

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

ToolsJSON
262K context118K outputcutoff 2025-06-30$0.21/1M in

Kimi K2 0711

Text

Moonshot AI

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

Tools
131K context98K outputcutoff 2024-12-31$0.85/1M in

Uncensored

Text

Cognitive Computations

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

JSON
128K context8K outputcutoff 2024-04-30$0.30/1M in

Hunyuan A13B Instruct

Text

Tencent

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...

ReasoningJSON
131K context118K outputcutoff 2025-03-31$0.21/1M in

Morph V3 Large

Text

Morph

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

JSON
262K context131K output$1.35/1M in

Morph V3 Fast

Text

Morph

Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...

JSON
262K context131K output$1.20/1M in

Mistral Small 3.2 24B

Text

Mistral AI

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

VisionToolsJSON
256K context26K outputcutoff 2023-10-31$0.15/1M in

Gemini 2.5 Flash

Text

Google

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

ReasoningVisionToolsJSON
1M context66K outputcutoff 2025-01-31$0.45/1M in

Gemini 2.5 Pro

Text

Google

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

ReasoningVisionToolsJSON
Coding33
Agentic2
1M context66K outputcutoff 2025-01-31$1.88/1M in

OpenAI o3 Pro

Text

OpenAI

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...

ReasoningVisionToolsJSON
200K context100K outputcutoff 2024-06-30$30.00/1M in

Gemini 2.5 Pro Preview 06-05

Text

Google

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

ReasoningVisionToolsJSON
1M context66K outputcutoff 2025-01-31$1.88/1M in

DeepSeek R1 0528

Text

DeepSeek

May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

ReasoningToolsJSON
164K context33K outputcutoff 2025-03-31$0.75/1M in

Mistral Medium 3

Text

Mistral AI

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

VisionToolsJSON
131K context105K outputcutoff 2025-03-31$0.60/1M in

Llama Guard 4 12B

Text

Meta

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

Vision
164K context16K outputcutoff 2024-08-31$0.27/1M in

Qwen3 30B A3B

Text

Qwen

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

ReasoningToolsJSON
41K context16K outputcutoff 2025-03-31$0.18/1M in

Qwen3 14B

Text

Qwen

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

ReasoningToolsJSON
Coding14
Agentic1
41K context37K outputcutoff 2025-03-31$0.15/1M in

Qwen3 32B

Text

Qwen

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

ReasoningToolsJSON
Coding15
Agentic1
131K context16K outputcutoff 2025-03-31$0.12/1M in

OpenAI o3

Text

OpenAI

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

ReasoningVisionToolsJSON
200K context100K outputcutoff 2024-06-30$3.00/1M in

GPT-4.1

Text

OpenAI

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

VisionToolsJSON
1M context33K outputcutoff 2024-06-30$3.00/1M in

GPT-4.1 Mini

Text

OpenAI

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

VisionToolsJSON
Coding20
1M context33K outputcutoff 2024-06-30$0.60/1M in

GPT-4.1 Nano

Text

OpenAI

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

VisionToolsJSON
Coding11
1M context943K outputcutoff 2024-06-30$0.15/1M in

Llama 4 Maverick

Text

Meta

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

VisionToolsJSON
Coding16
Agentic1
524K context33K outputcutoff 2024-08-31$0.53/1M in

Llama 4 Scout

Text

Meta

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

VisionToolsJSON
Coding8
Agentic1
1.3M context16K outputcutoff 2024-08-31$0.15/1M in

DeepSeek V3 0324

Text

DeepSeek

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...

ToolsJSON
Coding21
Agentic1
164K context115K outputcutoff 2024-07-31$0.43/1M in

Mistral Small 3.1 24B

Text

Mistral AI

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...

VisionToolsJSON
128K context102K outputcutoff 2023-10-31$0.53/1M in

Gemma 3 4B

Text

Google

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

VisionJSON
Coding3
131K context16K outputcutoff 2024-08-31$0.075/1M in

Gemma 3 12B

Text

Google

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

VisionToolsJSON
Coding6
Agentic0
131K context16K outputcutoff 2024-08-31$0.075/1M in

Command A

Text

Cohere

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

ToolsJSON
256K context8K outputcutoff 2024-08-31$3.75/1M in

Reka Flash 3

Text

Reka

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...

ReasoningJSON
66K context59K outputcutoff 2025-01-31$0.15/1M in

Gemma 3 27B

Text

Google

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

VisionToolsJSON
Coding10
Agentic0
131K context118K outputcutoff 2024-08-31$0.12/1M in
TD

Skyfall 36B V2

Text

TheDrummer

Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.

JSON
33K context29K outputcutoff 2024-06-30$0.82/1M in

Sonar Reasoning Pro

Text

Perplexity

Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...

ReasoningVision
128K context115K output$3.00/1M in

Sonar Pro

Text

Perplexity

For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...

Vision
200K context8K output$4.50/1M in

Sonar Deep Research

Text

Perplexity

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

Reasoning
128K context115K output$3.00/1M in

Saba

Text

Mistral AI

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...

ToolsJSON
33K context26K outputcutoff 2024-09-30$0.30/1M in

Aion-RP 1.0 (8B)

Text

AionLabs

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

33K context29K outputcutoff 2023-12-31$1.20/1M in

Qwen2.5 VL 72B Instruct

Text

Qwen

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

VisionJSON
128K context115K outputcutoff 2024-06-30$1.20/1M in

Qwen-Plus

Text

Qwen

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

ToolsJSON
1M context33K outputcutoff 2025-03-31$0.39/1M in

Mistral Small 3

Text

Mistral AI

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

JSON
33K context16K outputcutoff 2023-10-31$0.075/1M in

Sonar

Text

Perplexity

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...

Vision
127K context114K output$1.50/1M in

Phi 4

Text

Microsoft

Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

JSON
16K context15K outputcutoff 2024-06-30$0.10/1M in

DeepSeek V3

Text

DeepSeek

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

ToolsJSON
164K context16K outputcutoff 2024-07-31$0.48/1M in

Command R7B (12-2024)

Text

Cohere

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

ToolsJSON
128K context4K outputcutoff 2024-08-31$0.056/1M in

Llama 3.3 70B Instruct

Text

Meta

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

ToolsJSON
Coding12
131K context115K outputcutoff 2023-12-31$1.06/1M in

Nova Lite 1.0

Text

Amazon

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...

VisionTools
300K context5K outputcutoff 2024-10-31$0.09/1M in

Nova Micro 1.0

Text

Amazon

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...

Tools
128K context5K outputcutoff 2024-10-31$0.052/1M in

Nova Pro 1.0

Text

Amazon

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...

VisionTools
300K context5K outputcutoff 2024-10-31$1.20/1M in

GPT-4o (2024-11-20)

Text

OpenAI

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...

VisionToolsJSON
128K context16K outputcutoff 2023-10-31$3.75/1M in

Mistral Large 2407

Text

Mistral AI

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here....

ToolsJSON
131K context105K outputcutoff 2024-03-31$3.00/1M in

Qwen2.5 Coder 32B Instruct

Text

Qwen

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in code generation, code reasoning...

JSON
33K context29K outputcutoff 2024-06-30$0.99/1M in
TD

UnslopNemo 12B

Text

TheDrummer

UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.

JSON
1M context819K outputcutoff 2024-04-30$0.60/1M in

Magnum v4 72B

Text

Anthracite

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet( and Opus( The model is fine-tuned on top of Qwen2.5 72B.

JSON
33K context4K outputcutoff 2024-06-30$3.75/1M in

Llama 3.2 1B Instruct

Text

Meta

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...

60K context54K outputcutoff 2023-12-31$0.041/1M in

Llama 3.2 3B Instruct

Text

Meta

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

JSON
131K context118K outputcutoff 2023-12-31$0.075/1M in

Qwen2.5 72B Instruct

Text

Qwen

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

ToolsJSON
33K context16K outputcutoff 2024-06-30$0.54/1M in

Command R (08-2024)

Text

Cohere

command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...

ToolsJSON
128K context4K outputcutoff 2024-03-31$0.23/1M in

Command R+ (08-2024)

Text

Cohere

command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...

ToolsJSON
128K context4K outputcutoff 2024-03-31$3.75/1M in
S1

Llama 3.1 Euryale 70B v2.2

Text

Sao10K

Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1.

JSON
131K context16K outputcutoff 2023-12-31$1.27/1M in
S1

Llama 3 8B Lunaris

Text

Sao10K

Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....

JSON
8K context7K outputcutoff 2023-12-31$0.06/1M in

GPT-4o (2024-08-06)

Text

OpenAI

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more here. GPT-4o ("o" for "omni") is...

VisionToolsJSON
128K context16K outputcutoff 2023-10-31$3.75/1M in

Llama 3.1 70B Instruct

Text

Meta

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...

131K context8K outputcutoff 2023-12-31$1.08/1M in

Llama 3.1 8B Instruct

Text

Meta

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...

ToolsJSON
Coding5
131K context16K outputcutoff 2023-12-31$0.03/1M in

Mistral Nemo

Text

Mistral AI

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

ToolsJSON
131K context16K outputcutoff 2024-04-30$0.043/1M in

GPT-4o-mini

Text

OpenAI

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

VisionToolsJSON
Coding11
128K context16K outputcutoff 2023-10-31$0.23/1M in

GPT-4o-mini (2024-07-18)

Text

OpenAI

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

VisionToolsJSON
128K context16K outputcutoff 2023-10-31$0.23/1M in

Gemma 2 27B

Text

Google

Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of...

JSON
8K context2K outputcutoff 2024-06-30$0.97/1M in

GPT-4o

Text

OpenAI

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as...

VisionToolsJSON
128K context16K outputcutoff 2023-10-31$3.75/1M in

GPT-4o (2024-05-13)

Text

OpenAI

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as...

VisionToolsJSON
Coding24
128K context4K outputcutoff 2023-10-31$7.50/1M in

Mixtral 8x22B Instruct

Text

Mistral AI

Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...

ToolsJSON
66K context52K outputcutoff 2024-01-31$3.00/1M in

Mistral Large

Text

Mistral AI

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here....

ToolsJSON
128K context102K outputcutoff 2024-11-30$3.00/1M in

GPT-3.5 Turbo (older v0613)

Text

OpenAI

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

ToolsJSON
4K context4K outputcutoff 2021-09-30$1.50/1M in

GPT-3.5 Turbo 16k

Text

OpenAI

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...

ToolsJSON
16K context4K outputcutoff 2021-09-30$4.50/1M in

Weaver (alpha)

Text

Mancer

An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.

JSON
8K context6K outputcutoff 2023-06-30$0.45/1M in
U9

ReMM SLERP 13B

Text

Undi95

A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge

JSON
6K context6K outputcutoff 2023-06-30$0.45/1M in

MythoMax 13B

Text

Gryphe

One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge

JSON
8K context4K outputcutoff 2023-06-30$0.12/1M in

GPT-4

Text

OpenAI

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...

ToolsJSON
Coding13
8K context4K outputcutoff 2021-09-30$45.00/1M in