Market preview
DeepSeek: DeepSeek Pro Latest+27%DeepSeek V4 Flash Latest+16%DeepSeek: DeepSeek V4 Flash 0731+16%@cf/ai4bharat/indictrans2-en-indic-1B$0.342 / 1MV100$0.02/hr
Anthropic · Tools · Structured output · Reasoning controls · Output limits · Released Jun 9, 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 |
|---|---|---|---|---|---|
 OpenRouteropenrouter.ai ↗ | $10/ 1M | $50/ 1M | $1 | Not published | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
 DeepInfradeepinfra.com ↗ | $10/ 1M | $50/ 1M | Not published | Not published | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
 Anthropicanthropic.com ↗ | $10/ 1M | $50/ 1M | $1 | $5 | Sourcehttps://docs.anthropic.com/en/docs/about-claude/pricing 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 | 82.10 | Public benchmark | SourceGPQA Diamond via OpenRouter See where this value came from and when it was checked.
|
| TAU-Bench | reasoning | 80.70 | Public benchmark | SourceTAU-Bench via OpenRouter See where this value came from and when it was checked.
|
| Artificial Analysis Intelligence | reasoning | 62.10 | Public benchmark | SourceArtificial Analysis Intelligence via OpenRouter See where this value came from and when it was checked.
|
| Artificial Analysis Coding | reasoning | 76.50 | Public benchmark | SourceArtificial Analysis Coding via OpenRouter See where this value came from and when it was checked.
|
| Artificial Analysis Agentic | reasoning | 56.60 | Public benchmark | SourceArtificial Analysis Agentic via OpenRouter See where this value came from and when it was checked.
|
| ARC-AGI | reasoning | 89.20 | Public benchmark | SourceARC-AGI via openlm.ai See where this value came from and when it was checked.
|
| Chatbot Arena Elo | reasoning | 1510.00 | Public benchmark | SourceChatbot Arena Elo via openlm.ai See where this value came from and when it was checked.
|
| Chatbot Arena Coding Elo | reasoning | 1566.00 | Public benchmark | SourceChatbot Arena Coding Elo via openlm.ai See where this value came from and when it was checked.
|
| MMLU-Pro | reasoning | 91.50 | Public benchmark | SourceMMLU-Pro via openlm.ai See where this value came from and when it was checked.
|
| Chatbot Arena Vision Elo | reasoning | 1312.00 | Public benchmark | SourceChatbot Arena Vision Elo via openlm.ai See where this value came from and when it was checked.
|
History
Recorded changes in pricing, availability and other tracked model data.