Model pricing catalog
73 modelsModel usage is billed at exactly what the model's provider charges for each call, with no markup.
| OpenAI: gpt-6.1-solLong context, a prompt above 272,000 tokens: $4 input, $0.20 cached input, $15 output per 1M tokens. | from $2 | from $10 | from $0.10 |
|---|---|---|---|
| OpenAI: gpt-6-astraLong context, a prompt above 272,000 tokens: $20 input, $2 cached input, $75 output per 1M tokens. | $10 | $50 | $1 |
| OpenAI: gpt-6-solLong context, a prompt above 272,000 tokens: $4 input, $0.40 cached input, $15 output per 1M tokens. | $2 | $10 | $0.20 |
| OpenAI: gpt-6-lunaLong context, a prompt above 272,000 tokens: $0.20 input, $0.02 cached input, $0.75 output per 1M tokens. | $0.10 | $0.50 | $0.01 |
| OpenAI: gpt-5.6-solLong context, a prompt above 272,000 tokens: $8 input, $0.80 cached input, $30 output per 1M tokens. | from $4 | from $20 | from $0.40 |
| OpenAI: gpt-5.6-terraLong context, a prompt above 272,000 tokens: $4 input, $0.40 cached input, $18 output per 1M tokens. | $2 | $12 | $0.20 |
| OpenAI: gpt-5.6-lunaLong context, a prompt above 272,000 tokens: $0.40 input, $0.04 cached input, $1.80 output per 1M tokens. | $0.20 | $1.20 | $0.02 |
| OpenAI: gpt-5.5Long context, a prompt above 272,000 tokens: $10 input, $1 cached input, $45 output per 1M tokens. | from $5 | from $30 | from $0.50 |
| OpenAI: gpt-5.4Long context, a prompt above 272,000 tokens: $5 input, $0.50 cached input, $22.50 output per 1M tokens. | $2.50 | $15 | $0.25 |
| OpenAI: gpt-5.4-mini | $0.75 | $4.50 | $0.075 |
| OpenAI: gpt-5.3-codex | $1.75 | $14 | $0.175 |
| OpenAI: gpt-5.2 | from $1.75 | from $14 | from $0.175 |
| Anthropic: claude-fable-5-1 | $10 | $50 | $0.25 |
| Anthropic: claude-fable-5 | $10 | $50 | $1 |
| Anthropic: claude-opus-5.5 | from $4 | from $20 | from $0.20 |
| Anthropic: claude-opus-5 | $5 | $25 | $0.50 |
| Anthropic: claude-sonnet-5.5 | $2 | $10 | $0.10 |
| Anthropic: claude-sonnet-5 | $2 | $10 | $0.20 |
| Anthropic: claude-opus-4.8 | $5 | $25 | $0.50 |
| Anthropic: claude-opus-4.7 | $5 | $25 | $0.50 |
| Anthropic: claude-sonnet-4.6 | $3 | $15 | $0.30 |
| Anthropic: claude-haiku-5.5Long context, a prompt above 100,000 tokens: $0.50 input, $0.05 cached input, $2.50 output per 1M tokens. | $0.10 | $0.50 | $0.01 |
| Anthropic: claude-haiku-4.5 | $1 | $5 | $0.10 |
| Google: gemini-4-argonThrough November 30, 2026; then $4 input, $0.20 cached input, $20 output per 1M tokens. | $2 | $10 | $0.10 |
| Google: gemini-3.8-flashThrough December 31, 2026; then $1.50 input, $0.15 cached input, $7.50 output per 1M tokens. | $0.75 | $3.75 | $0.075 |
| Google: gemini-3.7-flashThrough December 31, 2026; then $1.50 input, $0.15 cached input, $7.50 output per 1M tokens. | $0.75 | $3.75 | $0.075 |
| Google: gemini-3.6-flashThrough December 31, 2026; then $1.50 input, $0.15 cached input, $7.50 output per 1M tokens. | $0.75 | $3.75 | $0.075 |
| Google: gemini-3.5-flash | $1.50 | $9 | $0.15 |
| Google: gemini-3.5-flash-lite | $0.30 | $2.50 | $0.03 |
| Google: gemini-3.1-pro-previewLong context, a prompt above 200,000 tokens: $4 input, $0.40 cached input, $18 output per 1M tokens. | $2 | $12 | $0.20 |
| Google: gemini-3.1-flash-lite | $0.25 | $1.50 | $0.025 |
| Google: gemini-3-flash-preview | $0.50 | $3 | $0.05 |
| xAI: grok-4.6Long context, a prompt above 200,000 tokens: $4 input, $1 cached input, $12 output per 1M tokens. | $2 | $6 | $0.50 |
| xAI: grok-4.5Long context, a prompt above 200,000 tokens: $4 input, $0.60 cached input, $12 output per 1M tokens. | $2 | $6 | $0.30 |
| xAI: grok-4.3Long context, a prompt above 200,000 tokens: $2.50 input, $0.40 cached input, $5 output per 1M tokens. | $1.25 | $2.50 | $0.20 |
| xAI: grok-4.20Long context, a prompt above 200,000 tokens: $2.50 input, $0.40 cached input, $5 output per 1M tokens. | from $1.25 | from $2.50 | from $0.20 |
| xAI: grok-build-0.1Long context, a prompt above 200,000 tokens: $2 input, $0.40 cached input, $4 output per 1M tokens. | $1 | $2 | $0.20 |
| Meta: muse-wonder-1.0 | $4 | $20 | $0.20 |
| Meta: muse-spark-1.3 | $1.25 | $4.25 | $0.15 |
| Meta: muse-spark-1.2 | $1.25 | $4.25 | $0.15 |
| Meta: muse-spark-1.1 | $1.25 | $4.25 | $0.15 |
| Meta: muse-glimmer-30b | from $0.30 | from $1.20 | from $0.04 |
| Meta: llama-4-maverick | from $0.1875 | from $0.6525 | from $0.05 |
| Meta: llama-3.3-70b | from $0.59 | from $0.79 | from $0.295 |
| DeepSeek: deepseek-v4.1-flash | from $0.30 | from $1.20 | from $0.007 |
| DeepSeek: deepseek-v4-pro | from $0.66 | from $1.98 | from $0.022 |
| DeepSeek: deepseek-v4-flash | from $0.13 | from $0.26 | from $0.028 |
| Moonshot AI: kimi-k3 | from $3 | from $15 | from $0.30 |
| Moonshot AI: kimi-k2.7-code | $0.95 | $4 | $0.19 |
| Alibaba Qwen: qwen3.8-max | $2 | $6 | $0.25 |
| Alibaba Qwen: qwen3.8-flash | $0.15 | $0.47 | $0.016 |
| Alibaba Qwen: qwen3.8-27b | from $0.24 | from $2.20 | from $0.05 |
| Alibaba Qwen: qwen3.7-max | $2.50 | $7.50 | $0.50 |
| Alibaba Qwen: qwen3.7-plus | $0.40 | $1.60 | $0.08 |
| Alibaba Qwen: qwen3.7-flash | from $0.03 | from $0.13 | from $0.006 |
| Z.ai: glm-5.3 | from $1.40 | from $4.40 | from $0.14 |
| Z.ai: glm-5.3-flash | from $0.15 | from $0.50 | from $0.03 |
| Mistral: mistral-medium-3.5 | $1.50 | $7.50 | $0.15 |
| StepFun: step-3.7-flash | $0.20 | $1.15 | $0.04 |
| Tencent: hunyuan-4-preview | $0.834 | $2.501 | $0.042 |
| Tencent: hunyuan-3 | from $0.132 | from $0.528 | from $0.033 |
| MiniMax: minimax-m3 | from $0.30 | from $1.20 | from $0.06 |
| NVIDIA: nemotron-3.5-lightning | from $0.07 | from $0.20 | from $0.04 |
| NVIDIA: nemotron-3-ultra | from $0.60 | from $2.40 | from $0.12 |
| NVIDIA: nemotron-3-super | $0.15 | $0.65 | $0.08 |
| InclusionAI: ling-3.0-flash | from $0.021 | from $0.063 | from $0.0042 |
Images are billed per image at the provider's price.
- A price marked "from" is where the model starts: what a call costs depends on which provider serves it and, for some models, the time of day.
- Where a provider has announced a price change, the row says when it takes effect and what the new price is.
- On your own keys, your provider bills you directly at its own rates; nothing on this page applies.
- Prices updated October 15, 2026.