Competitive pricing
Our industry-leading scale lets us consistently offer the best prices on both frontier and open-weight models.
Access every model on the planet in a single interface through the world's largest inference provider. Serving 600 trillion tokens a month.
Our industry-leading scale lets us consistently offer the best prices on both frontier and open-weight models.
Plug every model into any SDK, agent or product with an API key. Or go keyless with OIDC, with no long-lived credentials. Setup instructions.
Choose which regions your requests run in and whether any model can train on your data. Zero retention by default, with some exceptions.
The latest model in each family OpenCode Models serves, with its list prices in US dollars per million tokens. View more reveals every row. Search and the provider filter apply to the complete list.
Model prices per 1M tokens and features
| Model | Features | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| Claude Fable 5.1 | $10.00 | $50.00 | $0.25 | $12.50 | |
| Claude Haiku 5.5 | $0.10 | $0.50 | $0.01 | $0.125 | |
| Claude Opus 5.5 | $4.00 | $20.00 | $0.20 | $5.00 | |
| Claude Sonnet 5.5 | $2.00 | $10.00 | $0.20 | $2.50 | |
| DeepSeek V4 Pro | $1.74 | $3.48 | $0.145 | Not listed | |
| DeepSeek V4.1 Flash | $0.30 | $1.20 | $0.006 | Not listed | |
| Gemini 3.5 Flash Lite | $0.30 | $2.50 | $0.03 | Not listed | |
| Gemini 3.8 Flash | $1.50 | $7.50 | $0.15 | Not listed | |
| Gemini 4 Argon | $2.00 | $10.00 | $0.10 | Not listed | |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | Not listed | |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | Not listed | |
| GPT-5.3 Codex | $1.75 | $14.00 | $0.175 | Not listed | |
| GPT-5.3 Codex Spark | $1.75 | $14.00 | $0.175 | Not listed | |
| GPT-5.4 Mini | $0.75 | $4.50 | $0.075 | Not listed | |
| GPT-5.4 Nano | $0.20 | $1.25 | $0.02 | Not listed | |
| GPT-5.5 | $5.00 | $30.00 | $0.50 | Not listed | |
| GPT-5.5 Pro | $30.00 | $180.00 | $30.00 | Not listed | |
| GPT-5.6 Terra | $2.00 | $12.00 | $0.20 | $2.50 | |
| GPT-6 Astra | $10.00 | $50.00 | $1.00 | $12.50 | |
| GPT-6 Luna | $0.10 | $0.50 | $0.01 | $0.125 | |
| GPT-6.1 Sol | $2.00 | $10.00 | $0.10 | $2.50 | |
| Grok 4.7 | $2.00 | $6.00 | $0.50 | Not listed | |
| Grok Build 0.1 | $1.00 | $2.00 | $0.20 | Not listed | |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | Not listed | |
| Kimi K3 | $3.00 | $15.00 | $0.30 | $3.00 | |
| MiniMax-M3 | $0.30 | $1.20 | $0.06 | Not listed | |
| Mistral Large 4 | $0.68 | $2.09 | $0.07 | Not listed | |
| Muse Wonder | $4.00 | $20.00 | $0.20 | Not listed | |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 |
Use frontier models for the hardest work and open-weight models for everything else, all from one account.
Usage and spend are tracked for every model, so you can see exactly where your tokens go.
The models above are priced per token. For a low-cost fixed monthly subscription, try OpenCode Go.