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.
Claude Haiku 5.5 (anthropic/claude-haiku-5.5)≤ 100Kprompt up to 100K (99,999) tokens: up to 100K (99,999): $0.10 / $0.50; above that: $0.50 / $2.50 (Input / Output, per million tokens)
Claude Sonnet 4.5 (anthropic/claude-sonnet-4.5)≤ 200Kprompt up to 200K (199,999) tokens: up to 200K (199,999): $3.00 / $15.00; above that: $6.00 / $22.50 (Input / Output, per million tokens)
Gemini 2.5 Pro (google/gemini-2.5-pro)≤ 200Kprompt up to 200K tokens: up to 200K: $1.25 / $10.00; above that: $2.50 / $15.00 (Input / Output, per million tokens)
Gemini 3.8 Flash (google/gemini-3.8-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 Sep 21, 20262 routes
GPT-5.4 (openai/gpt-5.4)≤ 272Kprompt up to 272K (271,999) tokens: up to 272K (271,999): $2.50 / $15.00; above that: $5.00 / $22.50 (Input / Output, per million tokens)
GPT-5.4 Pro (openai/gpt-5.4-pro)≤ 272Kprompt up to 272K (271,999) tokens: up to 272K (271,999): $30.00 / $180.00; above that: $60.00 / $270.00 (Input / Output, per million tokens)
GPT-5.5 (openai/gpt-5.5)≤ 272Kprompt up to 272K (271,999) tokens: up to 272K (271,999): $5.00 / $30.00; above that: $10.00 / $45.00 (Input / Output, per million tokens)
GPT-5.5 Pro (openai/gpt-5.5-pro)≤ 272Kprompt up to 272K (271,999) tokens: up to 272K (271,999): $30.00 / $180.00; above that: $60.00 / $270.00 (Input / Output, per million tokens)
GPT-5.6 Luna (openai/gpt-5.6-luna)≤ 272Kprompt up to 272K tokens: up to 272K: $0.20 / $1.20; above that: $0.40 / $1.80 (Input / Output, per million tokens)
GPT-5.6 Terra (openai/gpt-5.6-terra)≤ 272Kprompt up to 272K tokens: up to 272K: $2.00 / $12.00; above that: $4.00 / $18.00 (Input / Output, per million tokens)
GPT-6 Astra (openai/gpt-6-astra)≤ 272Kprompt up to 272K tokens: up to 272K: $10.00 / $50.00; above that: $20.00 / $75.00 (Input / Output, per million tokens)
GPT-6 Luna (openai/gpt-6-luna)≤ 272Kprompt up to 272K tokens: up to 272K: $0.10 / $0.50; above that: $0.20 / $0.75 (Input / Output, per million tokens)
GPT-6 Sol (openai/gpt-6-sol)≤ 272Kprompt up to 272K tokens: up to 272K: $2.00 / $10.00; above that: $4.00 / $15.00 (Input / Output, per million tokens)
GPT-6.1 Sol (openai/gpt-6.1-sol)≤ 272Kprompt up to 272K tokens: up to 272K: $2.00 / $10.00; above that: $4.00 / $15.00 (Input / Output, per million tokens)
GPT-6.1 Terra (openai/gpt-6.1-terra)≤ 272Kprompt up to 272K (271,999) tokens: up to 272K (271,999): $1.00 / $5.00; above that: $2.00 / $7.50 (Input / Output, per million tokens)
Fugu Ultra v2 (sakana/fugu-ultra-v2)≤ 272Kprompt up to 272K (271,999) tokens: up to 272K (271,999): $5.00 / $30.00; above that: $10.00 / $45.00 (Input / Output, per million tokens)
Grok 4.3 (x-ai/grok-4.3)≤ 200Kprompt up to 200K (199,999) tokens: up to 200K (199,999): $1.25 / $2.50; above that: $2.50 / $5.00 (Input / Output, per million tokens)
Grok 4.7 (x-ai/grok-4.7)≤ 200Kprompt up to 200K (199,999) tokens: up to 200K (199,999): $2.00 / $6.00; above that: $4.00 / $12.00 (Input / Output, per million tokens)
GLM 4.6V (z-ai/glm-4.6v)≤ 32Kprompt up to 32K (31,999) tokens: up to 32K (31,999): $0.146 / $0.437; above that: $0.291 / $0.873 (Input / Output, per million tokens)
$0.218
$0.146
$0.437
CheapestCheapest. The lowest price on InferIndex for this model.
GLM 5 Turbo (z-ai/glm-5-turbo)≤ 32Kprompt up to 32K (31,999) tokens: up to 32K (31,999): $0.73 / $3.19; above that: $1.02 / $3.77 (Input / Output, per million tokens)
$1.35
$0.73
$3.19
CheapestCheapest. The lowest price on InferIndex for this model.
GLM 5V Turbo (z-ai/glm-5v-turbo)≤ 32Kprompt up to 32K (31,999) tokens: up to 32K (31,999): $0.726 / $3.19; above that: $1.02 / $3.78 (Input / Output, per million tokens)
$1.34
$0.726
$3.19
CheapestCheapest. The lowest price on InferIndex for this model.
One row per offer, at its cheapest route at this provider; the other routes (hosted API, aggregators) open on the row. Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.
ZenMux