Offerings

Every active offering: a model as served by one host, with its current canonical price. Sort by clicking a column header; filter with the row below. Prices are USD per 1M tokens unless the unit toggle is set to per 1M characters (an approximation using a measured, blended tokens-per-character ratio).

Showing tier-tagged and vendor-direct models. Show all offerings, including the long tail

ModelVendorHostVariantInputOutputBlended ↑?Cache readCache writeBatch inBatch outContextTokenizerLast changeConfidence?Source
Claude Haiku 4.5anthropicgoogle-vertexunknown1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a–n/a–n/a200000claude–apiopenrouter
Claude Haiku 4.5anthropicaws-bedrockunknown1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a–n/a–n/a200000claude–apiopenrouter
Claude Haiku 4.5anthropicgoogle-vertexunknown1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a–n/a–n/a200000claude–apiopenrouter
Claude Haiku 4.5anthropicaws-bedrock–1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a0.55n/a2.75n/a200000claude–aggregatorlitellm
Claude Haiku 4.5anthropicaws-bedrock–1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a0.55n/a2.75n/a200000claude–aggregatorlitellm
Claude Haiku 4.5anthropicaws-bedrock–1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a0.55n/a2.75n/a200000claude–aggregatorlitellm
Claude Haiku 4.5anthropicaws-bedrock–1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a0.55n/a2.75n/a200000claude–aggregatorlitellm
Claude Haiku 4.5anthropicaws-bedrock–1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a0.55n/a2.75n/a200000claude–aggregatorlitellm
Claude Haiku 4.5anthropicaws-bedrock–1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a–n/a–n/a200000claude–apiopenrouter
Claude Haiku 4.5anthropicgoogle-vertex–1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a–n/a–n/a200000claude–apiopenrouter
Claude Haiku 4.5anthropicaws-bedrock–1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a–n/a–n/a200000claude–apiopenrouter
Claude Haiku 4.5anthropicgoogle-vertex–1.10n/a5.50n/a2.20n/a0.11n/a1.38n/a–n/a–n/a200000claude–apiopenrouter
Qwen3-Maxalibabadeepinfra–1.200.366.001.812.400.720.240.0724–n/a–n/a–n/a262144qwen2–aggregatorlitellm
Mistral Medium 3.1mistralmistral–1.500.537.502.673.001.070.150.0533–n/a–n/a–n/a131072mistral2026-06-26 ↑aggregatorlitellm
Mistral Large 2 (24.11)mistralgoogle-vertex–2.000.716.002.133.001.07–n/a–n/a–n/a–n/a131072mistral–aggregatorlitellm
Mistral Large 2 (24.11)mistralmistral–2.000.716.002.133.001.07–n/a–n/a–n/a–n/a131072mistral–aggregatormodelsdev
GPT-5.1openaiopenrouter–1.250.3510.002.823.440.970.130.0352–n/a0.630.185.001.41400000o200k–apiopenrouter
GPT-5openaiopenrouter–1.250.3510.002.823.440.970.130.0352–n/a0.630.185.001.41400000o200k–apiopenrouter
Gemini 2.5 Progoogleopenrouter–1.25n/a10.00n/a3.44n/a0.13n/a0.38n/a0.63n/a5.00n/a1048576gemini–apiopenrouter
GPT-5.1openaiazureunknown1.250.3510.002.823.440.970.130.0366–n/a–n/a–n/a400000o200k–apiopenrouter
GPT-5.1openaiopenaiunknown1.250.3510.002.823.440.970.130.0352–n/a–n/a–n/a400000o200k–apiopenrouter
GPT-5openaiazureunknown1.250.3510.002.823.440.970.130.0352–n/a–n/a–n/a400000o200k–apiopenrouter
GPT-5openaiopenaiunknown1.250.3510.002.823.440.970.130.0352–n/a–n/a–n/a400000o200k–apiopenrouter
Gemini 2.5 Progooglegoogle-vertexunknown1.25n/a10.00n/a3.44n/a0.13n/a0.38n/a–n/a–n/a1048576gemini–apiopenrouter
Gemini 2.5 Progooglegoogle-vertexunknown1.25n/a10.00n/a3.44n/a0.13n/a0.38n/a–n/a–n/a1048576gemini–apiopenrouter
Gemini 2.5 Progooglegoogleunknown1.25n/a10.00n/a3.44n/a0.13n/a0.38n/a–n/a–n/a1048576gemini–apiopenrouter
Gemini 2.5 Progooglegoogle-vertexunknown1.25n/a10.00n/a3.44n/a0.13n/a0.38n/a–n/a–n/a1048576gemini–apiopenrouter
GPT-5.1openaiazure–1.250.3510.002.823.440.970.130.0352–n/a0.630.185.001.41400000o200k–aggregatorlitellm
GPT-5openaiazure–1.250.3510.002.823.440.970.130.0352–n/a0.630.185.001.41400000o200k–aggregatorlitellm
GPT-5openaiazure–1.250.3510.002.823.440.970.130.0352–n/a0.630.185.001.41400000o200k–aggregatorlitellm
GPT-5.1openaiazure–1.250.3510.002.823.440.970.130.0352–n/a0.630.185.001.41400000o200k–aggregatorlitellm
Gemini 2.5 Progoogledeepinfra–1.25n/a10.00n/a3.44n/a–n/a–n/a–n/a–n/a1048576gemini2025-10-04 ↑aggregatorlitellm
Gemini 2.5 Progooglegoogle-vertex–1.25n/a10.00n/a3.44n/a0.13n/a–n/a0.63n/a5.00n/a1048576gemini–aggregatorlitellm
Gemini 2.5 Progooglegoogle–1.25n/a10.00n/a3.44n/a0.13n/a–n/a0.63n/a5.00n/a1048576gemini–officialofficial-google
GPT-5openaiopenai–1.250.3510.002.823.440.970.130.0352–n/a0.630.185.001.41400000o200k–aggregatorlitellm
GPT-5.1openaiopenai–1.250.3510.002.823.440.970.130.0352–n/a0.630.185.001.41400000o200k–aggregatorlitellm
GPT-5.1openaiopenai–1.250.3510.002.823.440.970.130.0352–n/a0.630.185.001.41400000o200k–aggregatorlitellm
GPT-5openaiopenai–1.250.3510.002.823.440.970.130.0352–n/a0.630.185.001.41400000o200k–aggregatorlitellm
GPT-5.1openaiperplexity–1.250.3510.002.823.440.970.130.0352–n/a–n/a–n/a400000o200k–aggregatorlitellm
GPT-5openaiperplexity–1.250.3510.002.823.440.970.130.0352–n/a–n/a–n/a400000o200k–aggregatorlitellm
GPT-5.1openaiazure–1.250.3510.002.823.440.970.130.0366–n/a–n/a–n/a400000o200k–apiopenrouter
GPT-5.1openaiopenai–1.250.3510.002.823.440.970.130.0352–n/a–n/a–n/a400000o200k–apiopenrouter
GPT-5openaiazure–1.250.3510.002.823.440.970.130.0352–n/a–n/a–n/a400000o200k–apiopenrouter
GPT-5openaiopenai–1.250.3510.002.823.440.970.130.0352–n/a–n/a–n/a400000o200k–apiopenrouter
Gemini 2.5 Progooglegoogle-vertex–1.25n/a10.00n/a3.44n/a0.13n/a0.38n/a–n/a–n/a1048576gemini–apiopenrouter
Gemini 2.5 Progooglegoogle-vertex–1.25n/a10.00n/a3.44n/a0.13n/a0.38n/a–n/a–n/a1048576gemini–apiopenrouter
Gemini 2.5 Progooglegoogle–1.25n/a10.00n/a3.44n/a0.13n/a0.38n/a–n/a–n/a1048576gemini–apiopenrouter
Gemini 2.5 Progooglegoogle-vertex–1.25n/a10.00n/a3.44n/a0.13n/a0.38n/a–n/a–n/a1048576gemini–apiopenrouter
o3openaiopenrouter–2.000.568.002.253.500.990.500.14–n/a1.000.284.001.13200000o200k–apiopenrouter
o3openaiopenaiunknown2.000.568.002.253.500.990.500.14–n/a–n/a–n/a200000o200k–apiopenrouter

Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence