Providers/CheaperInference
CheaperInference logo

CheaperInference

Inference providercheaperinference.com
MODELS
57
ENDPOINTS
107
MIN INPUT
$0.04
MEDIAN BLENDED
$1.18
AVG UPTIME
CHEAPEST FOR
0 models
Models on CheaperInference · prices & measurements for models served by CheaperInference’s APIUSD / MTOK · VERIFIED 3 HOURS AGO
MODELINPUTOUTPUTCONTEXTQUANTTTFTTPSVS BEST ELSEWHERE
OpenAI logoGPT-5 NanoOpenAI$0.04$0.32400K$0.05 elsewhere
OpenAI logogpt-oss-120bOpenAI$0.04$0.20131K1.5s118 tok/s$0.03 elsewhere
DeepSeek logoDeepSeek V4 Flash 0731DeepSeek$0.05$0.091.31M7.6s82 tok/s$0.038 elsewhere
Qwen logoQwen3.6 35B A3BQwen$0.07$0.70262K2s192 tok/s$0.05 elsewhere
DeepSeek logoDeepSeek V4 Flash 0423DeepSeek$0.09$0.361.05M5.7s85 tok/s$0.082 elsewhere
OpenAI logoGPT-4.1 NanoOpenAI$0.09$0.341.05M2.1s72 tok/s$0.10 elsewhere
Z.ai logoGLM 4.5 AirZ.ai$0.11$0.60131K4.4s119 tok/s$0.13 elsewhere
DeepSeek logoDeepSeek V4.1 FlashDeepSeek$0.13$0.511.05M2s139 tok/s$0.10 elsewhere
Z.ai logoGLM 5.3 FlashZ.ai$0.13$0.421.31M48.3s6 tok/s$0.03 elsewhere
OpenAI logoGPT-5.4 NanoOpenAI$0.14$0.88400K3.3s146 tok/s$0.20 elsewhere
Qwen logoQwen3.8 27BQwen$0.15$1.781M6.4s55 tok/s$0.10 elsewhere
OpenAI logoGPT-5.6 LunaOpenAI$0.17$1.021.05M3.2s205 tok/s$0.20 elsewhere
Google logoGemini 3.1 Flash LiteGoogle$0.17$1.051.05M2.1s96 tok/s$0.25 elsewhere
OpenAI logoGPT-5 MiniOpenAI$0.17$1.40400K$0.25 elsewhere
MiniMax logoMiniMax M2.7MiniMax$0.21$0.84205K3.3s78 tok/s$0.21 elsewhere
Qwen logoQwen3.5-35B-A3BQwen$0.22$0.88262K1.9s147 tok/s$0.08 elsewhere
Google logoGemini 3.5 Flash LiteGoogle$0.26$2.131.05M2.3s119 tok/s$0.30 elsewhere
Google logoGemini 2.5 FlashGoogle$0.26$2.131.05M$0.30 elsewhere
Z.ai logoGLM 4.7Z.ai$0.33$1.21205K13s39 tok/s$0.40 elsewhere
Z.ai logoGLM 4.6Z.ai$0.33$1.21205K9.1s58 tok/s$0.43 elsewhere
Z.ai logoGLM 4.5Z.ai$0.33$1.21131K5.2s50 tok/s$0.60 elsewhere
Qwen logoQwen3.6 27BQwen$0.42$2.52262K3.2s69 tok/s$0.30 elsewhere
Google logoGemini 3 Flash PreviewGoogle$0.42$2.551.05M6.3s11 tok/s$0.50 elsewhere
DeepSeek logoDeepSeek V4 Pro 0813DeepSeek$0.46$1.391.05M$0.40 elsewhere
DeepSeek logoDeepSeek V4 Pro 0423DeepSeek$0.46$1.391.05M2.1s59 tok/s$0.95 elsewhere
Google logoGemini 3.7 FlashGoogle$0.53$2.631.05M$0.75 elsewhere
Google logoGemini 3.6 FlashGoogle$0.53$2.631.05M$0.75 elsewhere
OpenAI logoGPT-5.4 MiniOpenAI$0.53$3.15400K$0.75 elsewhere
Z.ai logoGLM 5Z.ai$0.55$1.76205K$0.60 elsewhere
AION Labs logoAion-2.0AION Labs$0.68$1.36131K$0.80 elsewhere
Anthropic logoClaude Haiku 4.5Anthropic$0.70$3.50200K$1.00 elsewhere
Z.ai logoGLM 5.3Z.ai$0.77$2.421.31M$0.561 elsewhere
Z.ai logoGLM 5.2Z.ai$0.77$2.421.05M$0.561 elsewhere
Z.ai logoGLM 5.1Z.ai$0.77$2.42205K$0.965 elsewhere
OpenAI logoGPT-5.6 TerraOpenAI$0.80$4.801.05M$2.00 elsewhere
Google logoGemini 3.5 FlashGoogle$1.05$6.301.05M$1.50 elsewhere
Meta logoMuse Spark 1.2Meta$1.06$3.611.05M$1.25 elsewhere
OpenAI logoGPT-5.2-CodexOpenAI$1.23$9.80400K$1.75 elsewhere
xAI logoGrok 4.5xAI$1.40$4.20500K$2.00 elsewhere
Anthropic logoClaude Sonnet 5Anthropic$1.40$7.001M3s77 tok/s$2.00 elsewhere
Google logoGemini 3.1 Pro PreviewGoogle$1.40$8.401.05M$2.00 elsewhere
OpenAI logoGPT-5.4OpenAI$1.75$10.501.05M$2.50 elsewhere
OpenAI logoGPT-5.6 SolOpenAI$2.00$10.001.05M$4.00 elsewhere
Moonshot AI logoKimi K3Moonshot AI$2.10$10.501.05M$1.50 elsewhere
Anthropic logoClaude Sonnet 4.6Anthropic$2.10$10.501M$3.00 elsewhere
Anthropic logoClaude Sonnet 4.5Anthropic$2.10$10.501M$3.00 elsewhere
Anthropic logoClaude Opus 5.5Anthropic$2.80$14.001M$4.00 elsewhere
Anthropic logoClaude Opus 4.8Anthropic$3.50$17.501M$5.00 elsewhere
OpenAI logoGPT-5.5OpenAI$3.50$21.001.05M$5.00 elsewhere
Anthropic logoClaude Opus 4.7Anthropic$3.50$17.501M$5.00 elsewhere
Anthropic logoClaude Opus 4.6Anthropic$3.50$17.501M$5.00 elsewhere
Anthropic logoClaude Opus 4.5Anthropic$3.50$17.50200K$5.00 elsewhere
Anthropic logoClaude Opus 5Anthropic$4.25$21.251M5.1s96 tok/s$5.00 elsewhere
OpenAI logoGPT-6 AstraOpenAI$7.00$35.001.05M$10.00 elsewhere
Anthropic logoClaude Fable 5.1Anthropic$7.00$35.001M$10.00 elsewhere
Anthropic logoClaude Fable 5Anthropic$7.00$35.001M$10.00 elsewhere
OpenAI logoGPT-5.5 ProOpenAI$21.00$126.001.05M$30.00 elsewhere
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for CheaperInference’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page