Model pricing catalog
33 modelsRun any model at its listed catalog price. We add no markup on top of the upstream listing price; own-key models are billed to you directly by your provider.
| Anthropic: claude-opus-5 | $5 | $25 | $0.50 |
|---|---|---|---|
| Anthropic: claude-fable-5 | $10 | $50 | $1 |
| Anthropic: claude-opus-4.8 | $5 | $25 | $0.50 |
| Anthropic: claude-sonnet-5 | $2 | $10 | $0.20 |
| Anthropic: claude-opus-4.7 | $5 | $25 | $0.50 |
| Anthropic: claude-sonnet-4.6 | $3 | $15 | $0.30 |
| Anthropic: claude-haiku-4.5 | $1 | $5 | $0.10 |
| OpenAI: gpt-5.6-solShort context. Long context bills at 2x input and cache read, 1.5x output. | $5 | $30 | $0.50 |
| OpenAI: gpt-5.6-terraShort context. Long context bills at 2x input and cache read, 1.5x output. | $2 | $12 | $0.20 |
| OpenAI: gpt-5.6-lunaShort context. Long context bills at 2x input and cache read, 1.5x output. | $0.20 | $1.20 | $0.02 |
| OpenAI: gpt-5.5Above 272K input tokens, the session bills at 2x input, 1.5x output. | $5 | $30 | $0.50 |
| OpenAI: gpt-5.4Above 272K input tokens, the session bills at 2x input, 1.5x output. | $2.50 | $15 | $0.25 |
| OpenAI: gpt-5.4-mini | $0.75 | $4.50 | $0.075 |
| OpenAI: gpt-5.2 | $1.75 | $14 | $0.175 |
| OpenAI: gpt-5.3-codex | $1.75 | $14 | $0.175 |
| Google: gemini-3.6-flash | $1.50 | $7.50 | $0.15 |
| Z.ai: glm-5.3 | $1.40 | $4.40 | $0.26 |
| Z.ai: glm-5.3-flash | $0.15 | $0.50 | $0.03 |
| DeepSeek: deepseek-v4-pro | $1.32 | $3.96 | $0.044 |
| DeepSeek: deepseek-v4-flash | $0.44 | $1.32 | $0.014 |
| Alibaba Qwen: qwen3.7-max | $2.50 | $7.50 | —Not listed |
| Alibaba Qwen: qwen3.8-max | $2 | $6 | $0.25 |
| Mistral: mistral-medium-3.5 | $1.50 | $7.50 | $0.15 |
| Moonshot AI: kimi-k3 | $3 | $15 | $0.30 |
| Moonshot AI: kimi-k2.7-code | $0.95 | $4 | $0.19 |
| StepFun: step-3.7-flash | $0.20 | $1.15 | $0.032 |
| MiniMax: minimax-m3Own keyUp to 512K context; above that all rates double. | $0.30 | $1.20 | $0.06 |
| NVIDIA: nemotron-3-ultraOwn key | $0.50 | $2.20 | $0.10 |
| Tencent: hunyuan-3Own keyTime-of-day rate; off-hours listing is lower. | $0.132 | $0.528 | $0.033 |
| InclusionAI: ling-3.0-flashOwn key | $0.021 | $0.063 | $0.0042 |
| Alibaba Qwen: qwen3.7-flashOwn key | $0.03 | $0.13 | —Not listed |
| OpenAI: gpt-image-1Image-token rates. Per-image cost varies with quality and size; text input is priced separately by the provider. | $10 | $40 | $2.50 |
| OpenAI: gpt-image-1-miniImage-token rates. Per-image cost varies with quality and size; text input is priced separately by the provider. | $2.50 | $8 | $0.25 |
Own key: currently served on your own aggregator key, not on platform keys. The aggregator or provider bills you directly; prices shown are the current listings for reference.
- Anthropic, OpenAI, Google, DeepSeek, Z.ai, Mistral: each provider's published API pricing.
- Alibaba Qwen: Alibaba Cloud Model Studio published pricing, Singapore (International).
- Moonshot AI, StepFun, and all own-key models: aggregator listing; the provider publishes no USD token price.
- Prices are the listed catalog prices, verified against each provider's published pricing on 2026-09-03. Where a provider publishes no USD token price, the aggregator listing is the catalog source.
- When an upstream listing changes, this catalog is updated to match. Your usage is billed at the listed catalog price.
- On your own keys, your provider bills you directly at its own rates; nothing on this page applies.