DeepSeek · Tools · Structured output · Reasoning controls · Sampling controls · Output limits · Released Apr 24, 2026
Provider pricing
Published rates for providers serving this model. Open any source to see where and when the price was checked.
| Provider | Input | Output | Cached input | Batch input | Evidence |
|---|---|---|---|---|---|
| $0.091/ 1M | $0.182/ 1M | $0.018 | Not published | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
| |
| $0.09/ 1M | $0.18/ 1M | $0.018 | Not published | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
| |
| $0.14/ 1M | $0.28/ 1M | $0.028 | Not published | Sourcehttps://app.fireworks.ai/api/models See where this value came from and when it was checked.
| |
| $0.44/ 1M | $1.32/ 1M | $0.014 | Not published | Sourcehttps://api-docs.deepseek.com/quick_start/pricing See where this value came from and when it was checked.
| |
| $0.288/ 1M | $0.556/ 1M | $0.144 | Not published | Sourcehttps://api.intelligence.io.solutions/api/v1/models See where this value came from and when it was checked.
| |
| $0.068/ 1M | $0.168/ 1M | $0.017 | Not published | Sourcehttps://docs.digitalocean.com/products/inference/details/pricing/index.html.md See where this value came from and when it was checked.
|
Performance
Benchmark results collected from published sources. Scores from different benchmark versions or test setups may not be directly comparable.
| Benchmark | Category | Score | Origin | Evidence |
|---|---|---|---|---|
| GPQA Diamond | reasoning | 89.80 | Public benchmark | SourceGPQA Diamond via OpenRouter See where this value came from and when it was checked.
|
| TAU-Bench | reasoning | 77.60 | Public benchmark | SourceTAU-Bench via OpenRouter See where this value came from and when it was checked.
|
| Artificial Analysis Intelligence | reasoning | 42.10 | Public benchmark | SourceArtificial Analysis Intelligence via OpenRouter See where this value came from and when it was checked.
|
| Artificial Analysis Coding | reasoning | 56.20 | Public benchmark | SourceArtificial Analysis Coding via OpenRouter See where this value came from and when it was checked.
|
| Artificial Analysis Agentic | reasoning | 33.70 | Public benchmark | SourceArtificial Analysis Agentic via OpenRouter See where this value came from and when it was checked.
|
History
Recorded changes in pricing, availability and other tracked model data.