Token Barometer

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
Gemini 2.5 Flashgooglegoogle-vertex–0.30n/a2.50n/a0.85n/a0.0300n/a–n/a–n/a–n/a1048576gemini–aggregatorlitellm
Gemini 2.5 Flashgooglegoogle–0.30n/a2.50n/a0.85n/a0.0300n/a–n/a0.15n/a1.25n/a1048576gemini–officialofficial-google
MiniMax M1minimaxminimax–0.40n/a2.20n/a0.85n/a–n/a–n/a–n/a–n/a1000000––apiopenrouter
Gemini 2.5 Flashgooglegoogle-vertex–0.30n/a2.50n/a0.85n/a0.0300n/a0.0833n/a–n/a–n/a1048576gemini–apiopenrouter
Gemini 2.5 Flashgooglegoogle-vertex–0.30n/a2.50n/a0.85n/a0.0300n/a0.0833n/a–n/a–n/a1048576gemini–apiopenrouter
Gemini 2.5 Flashgooglegoogle–0.30n/a2.50n/a0.85n/a0.0300n/a0.0833n/a–n/a–n/a1048576gemini–apiopenrouter
Gemini 2.5 Flashgooglegoogle-vertex–0.30n/a2.50n/a0.85n/a0.0300n/a0.0833n/a–n/a–n/a1048576gemini–apiopenrouter
GLM 4.6zhipudeepinfrafp40.50n/a2.00n/a0.88n/a0.10n/a–n/a–n/a–n/a204800––apiopenrouter
Kimi K2 Instructmoonshotdeepinfra–0.50n/a2.00n/a0.88n/a–n/a–n/a–n/a–n/a262144––aggregatorlitellm
Kimi K2 Instructmoonshotdeepinfra–0.50n/a2.00n/a0.88n/a0.40n/a–n/a–n/a–n/a262144––aggregatorlitellm
GLM 4.6zhipudeepinfra–0.50n/a2.00n/a0.88n/a0.10n/a–n/a–n/a–n/a204800––aggregatorlitellm
DeepSeek: DeepSeek V3deepseektogether–0.600.201.700.560.880.29–n/a–n/a–n/a–n/a163840deepseek–aggregatorlitellm
Llama 4 Maverick 17B 128E Instruct FP8metasambanova–0.630.191.800.540.920.28–n/a–n/a–n/a–n/a524288llama3–aggregatorlitellm
Qwen3 235B A22B Instruct 2507alibabadeepinfra–0.300.09052.900.870.950.29–n/a–n/a–n/a–n/a131072qwen22025-10-04 ↑aggregatorlitellm
MiniMax M1minimaxopenrouter–0.55n/a2.20n/a0.96n/a–n/a–n/a–n/a–n/a1000000––apiopenrouter
GLM 4.6zhipunovita–0.55n/a2.20n/a0.96n/a0.11n/a–n/a–n/a–n/a204800––apiopenrouter
MiniMax M1minimaxnovita–0.55n/a2.20n/a0.96n/a–n/a–n/a–n/a–n/a1000000––apiopenrouter
GLM 4.6zhipunovita–0.55n/a2.20n/a0.96n/a0.11n/a–n/a–n/a–n/a204800–2026-01-13 ↓aggregatorlitellm
MiniMax M1minimaxnovita–0.55n/a2.20n/a0.96n/a–n/a–n/a–n/a–n/a1000000–2026-01-13 ↓aggregatorlitellm
Qwen3 235B A22B Instruct 2507alibabanovitafp80.300.09053.000.900.980.29–n/a–n/a–n/a–n/a131072qwen2–apiopenrouter
Qwen3 235B A22B Instruct 2507alibabanovita–0.300.09053.000.900.980.29–n/a–n/a–n/a–n/a131072qwen22026-01-13 ↓aggregatorlitellm
GLM 4.6zhipuzhipufp40.60n/a2.20n/a1.00n/a0.11n/a–n/a–n/a–n/a204800––apiopenrouter
GLM 4.6zhiputogether–0.60n/a2.20n/a1.00n/a–n/a–n/a–n/a–n/a204800––aggregatorlitellm
GLM 4.6zhipuzhipu–0.60n/a2.20n/a1.00n/a0.11n/afreen/a–n/a–n/a204800––aggregatorlitellm
GLM 4.6zhipuzhipu–0.60n/a2.20n/a1.00n/a0.11n/a–n/a–n/a–n/a204800––officialofficial-zhipu
Kimi K2 Instructmoonshotnovita–0.57n/a2.30n/a1.00n/a–n/a–n/a–n/a–n/a262144–2026-01-13 ↓aggregatorlitellm
Llama 3.3 70B Instructmetatogetherunknown1.040.311.040.311.040.31–n/a–n/a–n/a–n/a131072llama3–apiopenrouter
Llama 3.3 70B Instructmetatogether–1.040.311.040.311.040.31–n/a–n/a–n/a–n/a131072llama32026-08-25 ↑aggregatorlitellm
Llama 3.3 70B Instructmetatogether–1.040.311.040.311.040.31–n/a–n/a–n/a–n/a131072llama3–apiopenrouter
Kimi K2 Instructmoonshotopenrouter–0.60n/a2.50n/a1.08n/a–n/a–n/a–n/a–n/a262144––apiopenrouter
Kimi K2 Instructmoonshotopenrouter–0.60n/a2.50n/a1.08n/a–n/a–n/a–n/a–n/a262144––apiopenrouter
Kimi K2 Instructmoonshotgoogle-vertexunknown0.60n/a2.50n/a1.08n/a–n/a–n/a–n/a–n/a262144––apiopenrouter
Kimi K2 Instructmoonshotnovita–0.60n/a2.50n/a1.08n/a0.15n/a–n/a–n/a–n/a262144––apiopenrouter
Kimi K2 Instructmoonshotnovitafp80.60n/a2.50n/a1.08n/a–n/a–n/a–n/a–n/a262144––apiopenrouter
Kimi K2 Instructmoonshotfireworks–0.60n/a2.50n/a1.08n/a–n/a–n/a–n/a–n/a262144––aggregatorlitellm
Kimi K2 Instructmoonshotfireworks–0.60n/a2.50n/a1.08n/a–n/a–n/a–n/a–n/a262144––aggregatorlitellm
Kimi K2 Instructmoonshotfireworks–0.60n/a2.50n/a1.08n/a–n/a–n/a–n/a–n/a262144––aggregatorlitellm
Kimi K2 Instructmoonshotaws-bedrock–0.60n/a2.50n/a1.08n/a–n/a–n/a–n/a–n/a262144––aggregatorlitellm
Kimi K2 Instructmoonshotnovita–0.60n/a2.50n/a1.08n/a0.15n/a–n/a–n/a–n/a262144–2026-01-13 ↓aggregatorlitellm
Kimi K2 Instructmoonshotnovita–0.60n/a2.50n/a1.08n/a–n/a–n/a–n/a–n/a262144–2026-01-13 ↓aggregatorlitellm
Kimi K2 Instructmoonshotgoogle-vertex–0.60n/a2.50n/a1.08n/a–n/a–n/a–n/a–n/a262144––apiopenrouter
DeepSeek-R1deepseekdeepinfra–0.700.232.400.791.130.37–n/a–n/a–n/a–n/a163839deepseek2025-09-10 ↑aggregatorlitellm
DeepSeek-R1deepseekopenrouter–0.700.232.500.821.150.38–n/a–n/a–n/a–n/a163839deepseek–apiopenrouter
DeepSeek-R1deepseeknovitafp80.700.232.500.821.150.38–n/a–n/a–n/a–n/a163839deepseek–apiopenrouter
DeepSeek-R1deepseeknebius–0.800.262.400.791.200.39–n/a–n/a–n/a–n/a163839deepseek–aggregatorlitellm
Qwen2.5-72B-Instructalibabatogether–1.200.361.200.361.200.36–n/a–n/a–n/a–n/a131072qwen2–aggregatorlitellm
Qwen2.5-72B-Instructalibabatogether–1.200.361.200.361.200.36–n/a–n/a–n/a–n/a131072qwen2–aggregatorlitellm
Qwen3 235B A22B Instruct 2507alibabavenicefp80.450.143.501.061.210.37–n/a–n/a–n/a–n/a131072qwen2–apiopenrouter
Qwen3 235B A22B Instruct 2507alibabaalibaba–0.700.212.800.841.230.37–n/a–n/a–n/a–n/a131072qwen2–aggregatormodelsdev
Kimi K2 Instructmoonshotaws-bedrock–0.73n/a3.03n/a1.31n/a–n/a–n/a–n/a–n/a262144––aggregatorlitellm

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