Model Pricing Reference
All supported models with current per-token pricing (USD, May 2026)
| Model | Provider | Input /1M | Output /1M | Batch /1M | Max tokens |
|---|---|---|---|---|---|
| Claude 3 Haiku | Anthropic | $0.80 | $4.00 | — | 200K |
| Claude 3 Opus | Anthropic | $15.00 | $75.00 | — | 200K |
| Claude 3 Sonnet | Anthropic | $3.00 | $15.00 | — | 200K |
| Claude 3.5 Haiku | Anthropic | $0.80 | $4.00 | $0.40 | 200K |
| Claude 3.5 Sonnet | Anthropic | $3.00 | $15.00 | $1.50 | 200K |
| Codestral | Mistral AI | $0.20 | $0.60 | — | 32K |
| DeepSeek Chat | DeepSeek | $0.14 | $0.28 | — | 64K |
| DeepSeek Coder | DeepSeek | $0.14 | $0.28 | — | 64K |
| DeepSeek V3 | DeepSeek | $0.27 | $1.10 | — | 64K |
| Gemini 1.5 Flash | $0.07 | $0.30 | $0.04 | 1000K | |
| Gemini 1.5 Pro | $1.25 | $5.00 | $0.31 | 2000K | |
| Gemini 2.0 Flash | $0.07 | $0.30 | $0.04 | 32K | |
| Gemini 2.5 Flash | $0.07 | $0.30 | $0.04 | 1000K | |
| Gemini 2.5 Pro | $1.25 | $5.00 | $0.31 | 1000K | |
| GPT-3.5 Turbo | OpenAI | $0.50 | $1.50 | $0.25 | 16K |
| GPT-4 | OpenAI | $30.00 | $60.00 | — | 8K |
| GPT-4 Turbo | OpenAI | $10.00 | $30.00 | $5.00 | 128K |
| GPT-4o | OpenAI | $2.50 | $10.00 | $1.25 | 128K |
| GPT-4o mini | OpenAI | $0.15 | $0.60 | $0.07 | 128K |
| Llama 3 70B Instruct | Meta | $0.65 | $2.75 | — | 8K |
| Llama 3 8B Instruct | Meta | $0.08 | $0.40 | — | 8K |
| Llama 4 405B Instruct | Meta | $3.50 | $14.00 | — | 128K |
| Llama 4 70B Instruct | Meta | $0.65 | $2.75 | — | 128K |
| Llama 4 8B Instruct | Meta | $0.08 | $0.40 | — | 128K |
| Mistral Large | Mistral AI | $2.00 | $6.00 | — | 128K |
| Mistral Small | Mistral AI | $0.20 | $0.60 | — | 128K |
| o1 | OpenAI | $15.00 | $60.00 | — | 66K |
| o1 mini | OpenAI | $1.10 | $4.40 | — | 66K |
| o1 Preview | OpenAI | $15.00 | $60.00 | — | 33K |
| o3 mini | OpenAI | $1.10 | $4.40 | — | 66K |
Prices are in USD. Batch pricing applies to input tokens only. Regional multipliers may add 0–30% depending on region. Data sourced from official provider pricing pages. May not reflect enterprise negotiated rates.