Specifications
Context window
131K tokens
Max output
16K tokens
Knowledge cutoff
2023-12-31
Input price
$1.05 / 1M tokens
Output price
$1.05 / 1M tokens
Capabilities
Structured output
Returns validated JSON that conforms to a schema you define.
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 |
|---|---|---|---|
| Nous: Hermes 3 70B Instruct (this model) | Nous Research | $1.05 in / $1.05 out per 1M tokens | 131K |
| OpenAI: GPT-5.6 Luna Pro | OpenAI | $0.30 in / $1.80 out per 1M tokens | 1.1M |
| Meta: Llama 3.3 70B Instruct | Meta | $1.06 in / $1.06 out per 1M tokens | 131K |
| DeepSeek: DeepSeek V3 0324 | DeepSeek | $0.43 in / $1.71 out per 1M tokens | 164K |
| StepFun: Step 3.7 Flash | StepFun | $0.30 in / $1.73 out per 1M tokens | 262K |
| TheDrummer: Skyfall 36B V2 | TheDrummer | $0.82 in / $1.20 out per 1M tokens | 33K |
More from Nous Research
Price and listing history
Every change GenMagic has recorded for Hermes 3 70B Instruct 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 3, 2026 | Retired | $1.05 in / $1.05 out per 1M tokens | - |
| Nov 1, 2026 | Price up 36% | $0.77 in / $0.77 out per 1M tokens | $1.05 in / $1.05 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 Nous Research publishes them (model card on Hugging Face), checked daily.
- Changes: the data on this page last changed on Nov 3, 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.
Models you can use instead of Hermes 3 70B Instruct
One GenMagic plan runs every current model across text, image, audio and video.