BlendedA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.$/1M
In$/1M
Out$/1M
ObservationGap to the lowest price we track for this model.
CtxThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.
DeepSeek V4.1 Flash (deepseek/deepseek-v4.1-flash)Drop 50%Price drop observed · −50% vs previous price: The blended price is 50% lower than before this drop; possibly temporary. · Price drop observed since Oct 30, 2026+1UnstablePrice changes often · 9 changes in 7 days · in $0.15 – $0.301 · out $0.601 – $1.20: 9 price changes in 7 days. Over that period: input $0.15 – $0.301, output $0.601 – $1.20 per million tokens. An offer whose price changes this often is not selected as the cheapest.
MiniMax M3 (minimax/minimax-m3)Tieredtiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
Qwen3.5-122B-A10B (qwen/qwen3.5-122b-a10b)Tieredtiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
Qwen3.5-27B (qwen/qwen3.5-27b)Tieredtiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
Qwen3.5-35B-A3B (qwen/qwen3.5-35b-a3b)Tieredtiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
Qwen3.5 397B A17B (qwen/qwen3.5-397b-a17b)Tieredtiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
GLM 4.6V (z-ai/glm-4.6v)Tieredtiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
GLM 4.7 (z-ai/glm-4.7)Tieredtiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
GLM 5 (z-ai/glm-5)Tieredtiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
GLM 5.1 (z-ai/glm-5.1)Tieredtiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.