Just the tokens.
Nothing in the way.

Prepaid usage. No recurring plan.
Input and output are priced separately, so you know what a request costs.

−10%

Below OpenRouter reference prices.

Qwen3.8 Flash, MiMo V2.6 Flash, MiMo V2.6 Pro, DeepSeek V4.1 Flash and GLM 5.3 Flash are priced 10% below their eligible OpenRouter reference prices.

ModelProviderContext windowMax outputModality
Qwen3.8 FlashQwen1M131KText
MiMo V2.6 FlashXiaomi1M131.1KText
MiMo V2.6 ProXiaomi1M131.1KText
DeepSeek V4.1 FlashDeepSeek1M384KText
GLM 5.3 FlashZ.ai1M131.1KText
Claude Fable 5.1Anthropic1M128KText
Claude Fable 5Anthropic1M128KText
Claude Haiku 4.5Anthropic8,192 (platform limit)1,024Text
Claude Opus 4.5Anthropic8,192 (platform limit)1,024Text
Claude Opus 4.6Anthropic8,192 (platform limit)1,024Text
Claude Opus 4.7Anthropic1M128KText
Claude Opus 4.8Anthropic1M128KText
Claude Opus 5.5Anthropic1M128KText
Claude Opus 5Anthropic1M128KText
Claude Sonnet 4.5Anthropic8,192 (platform limit)1,024Text
Claude Sonnet 4.6Anthropic1M128KText
Claude Sonnet 5Anthropic1M128KText
DeepSeek-V4-Flash-Vision-ExpDeepSeek1M384KText
DeepSeek-V4-FlashDeepSeek1M384KText
DeepSeek V4 ProDeepSeek1M384KText
Gemini 3.5 Flash-LiteGoogle1M65.5KText
Gemini 3.5 FlashGoogle1M65.5KText
Gemini 3.6 FlashGoogle1M65.5KText
Gemini 3.8 FlashGoogle1M65.5KText
GLM-5.1Z.AI200K128KText
GLM-5.2Z.AI1M128KText
GLM-5.3-FlashXZ.AI1M131.1KText
GLM-5.3Z.AI8,192 (platform limit)1,024Text
GPT-5.6 LunaOpenAI1.1M128KText
GPT-5.6 SolOpenAI1.1M128KText
GPT-5.6 TerraOpenAI1.1M128KText
GPT-6 AstraOpenAI1.1M128KText
GPT-6 LunaOpenAI1.1M128KText
GPT-6 SolOpenAI1.1M128KText
Grok 4.5xAI500K (platform limit)1,024Text
Grok 4.6xAI500K (platform limit)1,024Text
Hy3Tencent256K128KText
Hy4 PreviewTencent1M64KText
Kimi K2.6Moonshot AI8,192 (platform limit)1,024Text
Kimi K2.8 PreviewMoonshot AI1M (platform limit)1,024Text
Kimi K3Moonshot AI1M1MText
MiMo-V2.5-ProXiaomi1M128KText
MiMo-V2.5Xiaomi1M128KText
MiniMax M2.7MiniMax204.8K131.1KText
MiniMax M3MiniMax1M (platform limit)1,024Text
Muse Spark 1.3Meta1M131KText
Qwen3.6-27BQwen128K32.8KText
Qwen3.7-MaxQwen1M65.5KText
Qwen3.8-27BQwen262.1K131.1KText
Qwen3.8-MaxQwen1M131.1KText
DeepSeek V3.2DeepSeek164K164KText
Gemini 3.1 ProGoogle1M (platform limit)64KText
Gemini 3 FlashGoogle8,192 (platform limit)1,024Text
GPT-5.4OpenAI272K128KText
GPT-5.5OpenAI1.1M128KText
GPT-5.5 InstantOpenAI1M128KText
GPT-5.4 ProOpenAI1.1M128KText
GPT-5.2OpenAI8,192 (platform limit)1,024Text
GPT-5.4 MiniOpenAI400K16KText
GPT-5 MiniOpenAI8,192 (platform limit)1,024Text
GPT-5.4 NanoOpenAI400K (platform limit)1,024Text
GPT-5 NanoOpenAI8,192 (platform limit)1,024Text
Kimi K2.5Moonshot AI256K256KText
JEV-1.13.0TypeSafe AI32KStructured resultStructured decisions
GPT-Image-2OpenAI1024×1024 imageOne PNGImage generation

Live per-token prices load from the catalogue API and refresh hourly. This table lists stable model facts only.

How pricing works

Cache write entries marked “Input rate” show the cost of uncached input tokens for automatic caching; no separate cache-write rate is quoted.

Standard prices include separate cache rates where supported. New DeepSeek models follow the official peak and off-peak schedule. Image generation is billed by tokens, not by image. JEV decisions charge input tokens only.

For the five existing discounted models, prices are checked against synchronous endpoints for the same model. Scheduled prices are applied at the time of verification. Input and output minima may come from different endpoints. Batch tariffs are excluded.

Reference endpoints can use different quantization and context limits. This is a price comparison, not a claim of identical performance. Expired prices cannot authorize a request.

Explore the reference catalogue

Stay in control

Each request reserves its maximum possible cost, then settles against the tokens actually reported. Uncertain requests keep their reservation until reviewed.

Credit purchases are in USD.

Create an account