Simple, pay-as-you-go pricing
You pay the official list price of each model, per token. No subscription, no minimum spend, no hidden fees.
Official list prices
Per-model prices match the providers' published list prices, in USD.
Pay only for usage
Charged per request based on input, output and cached tokens actually used.
One balance for all models
Top up once and use it across every model in the catalog.
Transparent billing
Every request is itemized in the console with tokens and cost.
How a request is billed
cost = input tokens × input price + output tokens × output price + cached tokens × cache price
Prices are per 1M tokens. Cached prompt tokens are billed at the (much lower) cache read price. Some models use tiered pricing by input length; image and media models may be billed per request.
List prices
Official list prices in USD. Token prices are per 1M tokens.- gpt-5.6-lunaOpenAI·Chat·922KTieredInput$0.2Output$1.2Cache read$0.02
- gpt-5.6-terraOpenAI·Chat·922KTieredInput$2Output$12Cache read$0.2
- gpt-5.6-solOpenAI·Chat·922KTieredInput$4Output$20Cache read$0.4
- gpt-6-lunaOpenAI·Chat·922KTieredInput$0.1Output$0.5Cache read$0.01
- gpt-6-solOpenAI·Chat·922KTieredInput$2Output$10Cache read$0.2
- gpt-6-astraOpenAI·Chat·922KTieredInput$10Output$50Cache read$1
- gpt-4.1OpenAI·Chat·1.05MInput$2Output$8Cache read$0.5
- gpt-4.1-miniOpenAI·Chat·1.05MInput$0.4Output$1.6Cache read$0.1
- gpt-4.1-nanoOpenAI·Chat·1.05MInput$0.1Output$0.4Cache read$0.025
- gpt-4oOpenAI·Chat·128KInput$2.5Output$10Cache read$1.25
- gpt-4o-miniOpenAI·Chat·128KInput$0.15Output$0.6Cache read$0.075
- gpt-5OpenAI·Chat·272KInput$1.25Output$10Cache read$0.125
- gpt-5-miniOpenAI·Chat·272KInput$0.25Output$2Cache read$0.025
- gpt-5-nanoOpenAI·Chat·272KInput$0.05Output$0.4Cache read$0.005
- gpt-5-proOpenAI·Chat·400KInput$15Output$120
- gpt-5-search-apiOpenAI·Chat·272KInput$1.25Output$10Cache read$0.125
- gpt-5.1OpenAI·Chat·272KInput$1.25Output$10Cache read$0.125
- gpt-5.2OpenAI·Chat·272KInput$1.75Output$14Cache read$0.175
- gpt-5.2-proOpenAI·Chat·272KInput$21Output$168
- gpt-5.3-codexOpenAI·Chat·272KInput$1.75Output$14Cache read$0.175
- gpt-5.4OpenAI·Chat·1.05MTieredInput$2.5Output$15Cache read$0.25
- gpt-5.4-miniOpenAI·Chat·272KInput$0.75Output$4.5Cache read$0.075
- gpt-5.4-nanoOpenAI·Chat·272KInput$0.2Output$1.25Cache read$0.02
- gpt-5.4-proOpenAI·Chat·1.05MTieredInput$30Output$180
- gpt-5.5OpenAI·Chat·1.05MTieredInput$5Output$30Cache read$0.5
- gpt-5.5-proOpenAI·Chat·1.05MTieredInput$30Output$180
- gpt-5.6OpenAI·Chat·922KTieredInput$4Output$20Cache read$0.4
- gpt-6.1-solOpenAI·Chat·922KTieredInput$2Output$10Cache read$0.1
- gpt-audioOpenAI·Chat·128KInput$2.5Output$10
- gpt-audio-1.5OpenAI·Chat·128KInput$2.5Output$10
- gpt-audio-miniOpenAI·Chat·128KInput$0.6Output$2.4
- o1OpenAI·Chat·200KInput$15Output$60Cache read$7.5
- o1-proOpenAI·Chat·200KInput$150Output$600
- o3OpenAI·Chat·200KInput$2Output$8Cache read$0.5
- o3-miniOpenAI·Chat·200KInput$1.1Output$4.4Cache read$0.55
- o3-proOpenAI·Chat·200KInput$20Output$80
- o4-miniOpenAI·Chat·200KInput$1.1Output$4.4Cache read$0.275
- gpt-image-1OpenAI·ImageInput$5Output—Cache read$1.25
- gpt-image-1-miniOpenAI·ImageInput$2Output—Cache read$0.2
- gpt-image-1.5OpenAI·ImageInput$5Output$10Cache read$1.25
- gpt-image-2OpenAI·ImageInput$5Output—Cache read$1.25
- text-embedding-3-largeOpenAI·Embedding·8KInput$0.13Output—
- text-embedding-3-smallOpenAI·Embedding·8KInput$0.02Output—
- text-embedding-ada-002OpenAI·Embedding·8KInput$0.1Output—
- claude-fable-5Anthropic·Chat·1MInput$10Output$50Cache read$1
- claude-fable-5-1Anthropic·Chat·1MInput$10Output$50Cache read$0.25
- claude-haiku-4-5Anthropic·Chat·200KInput$1Output$5Cache read$0.1
- claude-mythos-5Anthropic·Chat·1MInput$10Output$50Cache read$1
- claude-mythos-5-1Anthropic·Chat·1MInput$10Output$50Cache read$0.25
- claude-opus-4-5Anthropic·Chat·200KInput$5Output$25Cache read$0.5
- claude-opus-4-6Anthropic·Chat·1MInput$5Output$25Cache read$0.5
- claude-opus-4-7Anthropic·Chat·1MInput$5Output$25Cache read$0.5
- claude-opus-4-8Anthropic·Chat·1MInput$5Output$25Cache read$0.5
- claude-opus-5Anthropic·Chat·1MInput$5Output$25Cache read$0.5
- claude-opus-5-5Anthropic·Chat·1MInput$4Output$20Cache read$0.2
- claude-sonnet-4-5Anthropic·Chat·1MTieredInput$3Output$15Cache read$0.3
- claude-sonnet-4-6Anthropic·Chat·1MInput$3Output$15Cache read$0.3
- claude-sonnet-5Anthropic·Chat·1MInput$2Output$10Cache read$0.2
- claude-sonnet-5-5Anthropic·Chat·1MInput$2Output$10Cache read$0.2
- gemini-2.5-flashGoogle·Chat·1.05MInput$0.3Output$2.5Cache read$0.03
- gemini-2.5-flash-liteGoogle·Chat·1.05MInput$0.1Output$0.4Cache read$0.01
- gemini-2.5-proGoogle·Chat·1.05MTieredInput$1.25Output$10Cache read$0.125
- gemini-3-flash-previewGoogle·Chat·1.05MInput$0.5Output$3Cache read$0.05
- gemini-3.1-flash-liteGoogle·Chat·1.05MInput$0.25Output$1.5Cache read$0.025
- gemini-3.1-pro-previewGoogle·Chat·1.05MTieredInput$2Output$12Cache read$0.2
- gemini-3.5-flashGoogle·Chat·1.05MInput$1.5Output$9Cache read$0.15
- gemini-3.5-flash-liteGoogle·Chat·1.05MInput$0.3Output$2.5Cache read$0.03
- gemini-3.6-flashGoogle·Chat·1.05MInput$0.75Output$3.75Cache read$0.075
- gemini-3.7-flashGoogle·Chat·1.05MInput$0.75Output$3.75Cache read$0.075
- gemini-3.8-flashGoogle·Chat·1.05MInput$0.75Output$3.75Cache read$0.075
- gemini-omni-1.1-flashGoogle·Chat·1.05MInput$1.5Output$9
- gemini-3-pro-imageGoogle·Image·66KInput$2Output$12
- gemini-3.1-flash-imageGoogle·Image·131KInput$0.5Output$3
- gemini-3.1-flash-lite-imageGoogle·Image·66KInput$0.25Output$1.5
- gemini-embedding-001Google·Embedding·2KInput$0.15Output—
- gemini-embedding-2Google·Embedding·8KInput$0.2Output—
- imagen-3.0-fast-generate-001Google·Image$0.02 / request
- imagen-3.0-generate-001Google·Image$0.04 / request
- nano-banana-pro-previewGoogle·Image·131KInput$2Output$12
- grok-4.20xAI·Chat·1MTieredInput$1.25Output$2.5Cache read$0.2
- grok-4.3xAI·Chat·1MTieredInput$1.25Output$2.5Cache read$0.2
- grok-4.5xAI·Chat·500KTieredInput$2Output$6Cache read$0.3
- grok-4.6xAI·Chat·500KTieredInput$2Output$6Cache read$0.5
- grok-4.7xAI·Chat·500KTieredInput$2Output$6Cache read$0.5
- grok-code-fastxAI·Chat·256KTieredInput$1Output$2Cache read$0.2
- deepseek-coderDeepSeek·Chat·128KInput$0.14Output$0.28Cache read$0.014
- deepseek-flashDeepSeek·Chat·1MInput$0.3Output$1.2Cache read$0.006
- deepseek-r1DeepSeek·Chat·66KInput$0.55Output$2.19Cache read$0.14
- deepseek-v3DeepSeek·Chat·66KInput$0.27Output$1.1Cache read$0.07
- deepseek-v3.2DeepSeek·Chat·164KInput$0.28Output$0.4Cache read$0.028
- deepseek-v4-flashDeepSeek·Chat·1MInput$0.3Output$1.2Cache read$0.006
- deepseek-v4-proDeepSeek·Chat·1MInput$1.32Output$3.96Cache read$0.044
- qwen-coderAlibaba·Chat·1MInput$0.3Output$1.5
- qwen-maxAlibaba·Chat·31KInput$1.6Output$6.4
- qwen-plusAlibaba·Chat·129KInput$0.4Output$1.2
- qwen-turboAlibaba·Chat·129KInput$0.05Output$0.2
- qwen3-next-80b-a3b-instructAlibaba·Chat·262KInput$0.15Output$1.2
- qwen3-next-80b-a3b-thinkingAlibaba·Chat·262KInput$0.15Output$1.2
- qwen3-vl-235b-a22b-instructAlibaba·Chat·131KInput$0.4Output$1.6
- qwen3-vl-235b-a22b-thinkingAlibaba·Chat·131KInput$0.4Output$4
- qwen3-vl-32b-instructAlibaba·Chat·131KInput$0.16Output$0.64
- qwen3-vl-32b-thinkingAlibaba·Chat·131KInput$0.16Output$2.87
- qwen3.7-maxAlibaba·Chat·992KInput$2.5Output$7.5Cache read$0.5
- qwen3.8-flashAlibaba·Chat·992KInput$0.15Output$0.47Cache read$0.016
- qwen3.8-maxAlibaba·Chat·992KInput$2Output$6Cache read$0.25
- qwen3.8-omni-flashAlibaba·Chat·992KInput$0.15Output$0.47Cache read$0.016
- qwq-plusAlibaba·Chat·98KInput$0.8Output$2.4
- glm-4-32b-0414-128kZhipu AI·Chat·128KInput$0.1Output$0.1
- glm-4.5Zhipu AI·Chat·128KInput$0.6Output$2.2
- glm-4.5-airZhipu AI·Chat·128KInput$0.2Output$1.1
- glm-4.5-airxZhipu AI·Chat·128KInput$1.1Output$4.5
- glm-4.5-xZhipu AI·Chat·128KInput$2.2Output$8.9
- glm-4.5vZhipu AI·Chat·128KInput$0.6Output$1.8
- glm-4.6Zhipu AI·Chat·200KInput$0.6Output$2.2Cache read$0.11
- glm-4.7Zhipu AI·Chat·200KInput$0.6Output$2.2Cache read$0.11
- glm-5Zhipu AI·Chat·200KInput$1Output$3.2Cache read$0.2
- glm-5-codeZhipu AI·Chat·200KInput$1.2Output$5Cache read$0.3
- glm-5.1Zhipu AI·Chat·200KInput$1.4Output$4.4Cache read$0.26
- glm-5.2Zhipu AI·Chat·1MInput$1.4Output$4.4Cache read$0.26
- glm-5.3Zhipu AI·Chat·1MInput$1.4Output$4.4Cache read$0.26
- glm-5.3-flashZhipu AI·Chat·1.05MInput$0.15Output$0.5Cache read$0.03
- kimi-k2.5Moonshot AI·Chat·262KInput$0.6Output$3Cache read$0.1
- kimi-k2.6Moonshot AI·Chat·262KInput$0.95Output$4Cache read$0.16
- kimi-k2.7-codeMoonshot AI·Chat·262KInput$0.95Output$4Cache read$0.19
- kimi-k3Moonshot AI·Chat·1.05MInput$3Output$15Cache read$0.3
- MiniMax-M2MiniMax·Chat·200KInput$0.3Output$1.2Cache read$0.03
- MiniMax-M2.1MiniMax·Chat·1MInput$0.3Output$1.2Cache read$0.03
- MiniMax-M2.1-lightningMiniMax·Chat·1MInput$0.3Output$2.4Cache read$0.03
- MiniMax-M2.5MiniMax·Chat·1MInput$0.3Output$1.2Cache read$0.03
- MiniMax-M2.5-lightningMiniMax·Chat·1MInput$0.3Output$2.4Cache read$0.03
- MiniMax-M3MiniMax·Chat·1MInput$0.3Output$1.2Cache read$0.06
- doubao-seed-2-1-pro-260628ByteDance·Chat·256KInput$0.863Output$4.31Cache read$0.172
- doubao-seed-2-1-turbo-260628ByteDance·Chat·256KInput$0.431Output$2.16Cache read$0.0862
- codestral-2508Mistral AI·Chat·128KInput$0.3Output$0.9Cache read$0.03
- ministral-14b-2512Mistral AI·Chat·262KInput$0.2Output$0.2Cache read$0.02
- ministral-3-14b-2512Mistral AI·Chat·262KInput$0.2Output$0.2Cache read$0.02
- ministral-3-3b-2512Mistral AI·Chat·131KInput$0.1Output$0.1Cache read$0.01
- ministral-3-8b-2512Mistral AI·Chat·262KInput$0.15Output$0.15Cache read$0.015
- ministral-3b-2512Mistral AI·Chat·131KInput$0.1Output$0.1Cache read$0.01
- ministral-8b-2512Mistral AI·Chat·262KInput$0.15Output$0.15Cache read$0.015
- mistral-large-2512Mistral AI·Chat·262KInput$0.5Output$1.5Cache read$0.05
- mistral-large-3Mistral AI·Chat·262KInput$0.5Output$1.5Cache read$0.05
- mistral-mediumMistral AI·Chat·262KInput$1.5Output$7.5Cache read$0.15
- mistral-medium-3Mistral AI·Chat·262KInput$1.5Output$7.5Cache read$0.15
- mistral-medium-3.5Mistral AI·Chat·262KInput$1.5Output$7.5Cache read$0.15
- mistral-smallMistral AI·Chat·32KInput$0.1Output$0.3Cache read$0.01
- mistral-tinyMistral AI·Chat·32KInput$0.25Output$0.25Cache read$0.025
- open-mistral-nemoMistral AI·Chat·128KInput$0.3Output$0.3Cache read$0.03
- voxtral-small-2507Mistral AI·Chat·33KInput$0.1Output$0.4Cache read$0.01
- codestral-embedMistral AI·Embedding·8KInput$0.15Output—Cache read$0.015
- mistral-embedMistral AI·Embedding·8KInput$0.1Output—
Billing FAQ
Do you charge anything on top of the list price?+
No. The prices shown here are what you are billed per token. There are no platform or subscription fees.
How do I pay?+
Top up your balance in the console. Requests are deducted from the balance in real time.
Are failed requests billed?+
No. Requests that fail with an error are not charged.
Do you offer volume pricing?+
For large or committed volumes, contact us through the console and we will work out a plan.