Try DeepSeek V4 Pro 0813
Generate with DeepSeek V4 Pro 0813 right here. Verify your email to start with free credits.
Specifications
Context window
1M tokens
Max output
944K tokens
Input price
$0.17 / 1M tokens
Output price
$6.66 / 1M tokens
Cached input
$0.15 / 1M tokens
Benchmarks
How DeepSeek V4 Pro 0813 scores on public benchmarks. Each card links to the benchmark explainer and to the original source.
Compare against every model in the full benchmark matrix.
Capabilities
Reasoning
Works through multi-step problems before answering, for harder tasks.
Tool use
Can call functions and tools, enabling agentic and structured workflows.
Structured output
Returns validated JSON that conforms to a schema you define.
Use DeepSeek V4 Pro 0813 through the API
The model id is deepseek/deepseek-v4-pro-0813. Requests bill your GenMagic balance at the price above, and each response reports what it cost.
curl https://genmagic.co/api/v1/chat/completions \
-H "Authorization: Bearer $GENMAGIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-pro-0813",
"messages": [{ "role": "user", "content": "Explain vector databases in two sentences." }]
}'from openai import OpenAI
client = OpenAI(base_url="https://genmagic.co/api/v1", api_key="YOUR_GENMAGIC_API_KEY")
resp = client.chat.completions.create(
model="deepseek/deepseek-v4-pro-0813",
messages=[{"role": "user", "content": "Explain vector databases in two sentences."}],
)
print(resp.choices[0].message.content)From an AI agent, call generate_text with "model": "deepseek/deepseek-v4-pro-0813" on the GenMagic MCP server. Keys, limits and every endpoint are in the API documentation.
Use DeepSeek V4 Pro 0813 in n8n
- In n8n, open the nodes panel, search for GenMagic and install it (a verified community node), then add it to your workflow.
- Set Resource to Text and Operation to Generate.
- In Model Name or ID, pick DeepSeek: DeepSeek V4 Pro 0813, or enter
deepseek/deepseek-v4-pro-0813as an expression. - Connect your GenMagic API key (get one free). Each run is billed at the price above, and the node returns what it cost.
Ready-to-import workflows that already use the node are on GenMagic for n8n.
Similar-priced text models from other providers
Other text models GenMagic runs at a comparable price, on the same balance and API key.
| Model | Provider | Price | Context |
|---|---|---|---|
| DeepSeek: DeepSeek V4 Pro 0813 (this model) | DeepSeek | $0.17 in / $6.66 out per 1M tokens | 1M |
| Google: Gemini 3.7 Flash | $1.13 in / $5.63 out per 1M tokens | 1M | |
| Qwen: Qwen3.5 397B A17B | Qwen | $0.90 in / $5.40 out per 1M tokens | 262K |
| Z.ai: GLM 5 | Z.AI | $1.50 in / $4.80 out per 1M tokens | 205K |
| Sakana: Sakana Namazu | Sakana AI | $1.43 in / $6.00 out per 1M tokens | 262K |
| Thinking Machines: Inkling | Thinkingmachines | $1.50 in / $6.08 out per 1M tokens | 524K |
Compare DeepSeek V4 Pro 0813
More from DeepSeek
All 17 DeepSeek modelsDeepSeek: DeepSeek V4.1 Flash 1017
TextDeepSeek 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...
View modelDeepSeek: DeepSeek Pro Latest
TextThis model always redirects to the latest model in the DeepSeek Pro family.
View modelDeepSeek: DeepSeek Flash Latest
TextThis model always redirects to the latest model in the DeepSeek Flash family.
View modelDeepSeek: DeepSeek V4.1 Flash
TextDeepSeek 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...
View modelDeepSeek: DeepSeek V4 Flash Vision Exp
TextDeepSeek 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,...
View modelDeepSeek: DeepSeek V4 Flash Latest
TextThis model always redirects to the latest model in the DeepSeek V4 Flash family.
View modelPrice and listing history
Every change GenMagic has recorded for DeepSeek V4 Pro 0813 since it began tracking the model on Oct 29, 2026. Prices are GenMagic's, the same the studio and the API charge.
| Date | Change | Before | After |
|---|---|---|---|
| Nov 9, 2026 | Price down 0% | $0.17 in / $6.66 out per 1M tokens | $0.17 in / $6.66 out per 1M tokens |
| Nov 8, 2026 | Price down 5% | $0.17 in / $6.99 out per 1M tokens | $0.17 in / $6.66 out per 1M tokens |
| Nov 7, 2026 | Price up 5% | $0.17 in / $6.66 out per 1M tokens | $0.17 in / $6.99 out per 1M tokens |
| Nov 6, 2026 | Price up 4% | $0.16 in / $6.42 out per 1M tokens | $0.17 in / $6.66 out per 1M tokens |
| Nov 5, 2026 | Price down 7% | $0.17 in / $6.90 out per 1M tokens | $0.16 in / $6.42 out per 1M tokens |
| Nov 4, 2026 | Price down 0% | $0.17 in / $6.00 out per 1M tokens | $0.17 in / $6.90 out per 1M tokens |
| Nov 1, 2026 | Price down 76% | $0.73 in / $2.18 out per 1M tokens | $0.17 in / $6.00 out per 1M tokens |
| Nov 1, 2026 | Updated: max output | - | - |
| Oct 31, 2026 | Price down 50% | $1.45 in / $4.36 out per 1M tokens | $0.73 in / $2.18 out per 1M tokens |
Where these figures come from
- Price: GenMagic's own price, what the studio and the API charge, recomputed from the provider's price list every few minutes and recorded daily. How pricing works.
- Specs and description: as DeepSeek publishes them (model card on Hugging Face), checked daily.
- Benchmarks: 24 scores from Artificial Analysis and OpenRouter, Epoch AI, LMArena, re-read daily. Each score above links to its source.
- Changes: the data on this page last changed on Nov 9, 2026, tracked since Oct 29, 2026. Every model's new listings, price changes and retirements are in the model changes log, and how every figure on GenMagic is sourced is on our sources page.
Generate with DeepSeek V4 Pro 0813 today
One GenMagic plan unlocks DeepSeek V4 Pro 0813 and every other model across text, image, audio, and video.