modelbenchmark.io
All hosts

cortecs

105 models listed here. Prices are this host's, not the vendor list price.

Apertus 70B66K$1.393$2.228
Claude 4.5 Sonnet200K$2.989$14.945
Claude Haiku 4.5200K$0.996$4.982
Claude Opus 4.5 (latest)200K$5.313$26.568
Claude Opus 4.61M$5.313$26.561
Claude Opus 4.71M$5.437$27.186
Claude Opus 4.81M$5.437$27.186
Claude Opus 51M$5.50$27.498
Claude Sonnet 4 (latest)200K$2.898$14.493
Claude Sonnet 4.61M$3.196$15.94
Claude Sonnet 51M$2.20$11.00
Codestral (latest)256K$0.334$1.003
cosmos3-super-reasoner256K$0.099$0.296
DeepSeek V3.2164K$0.296$0.495
DeepSeek V4 Flash1M$0.13$0.28
DeepSeek V4 Pro1M$2.00$3.999
DeepSeek-R1164K$0.652$2.57
Devstral 2256K$0.478$2.392
Gemini 2.5 Flash1M$0.299$2.491
Gemini 2.5 Pro1M$1.495$9.964
Gemini 3.1 Flash Lite1M$0.272$1.631
Gemini 3.5 Flash1M$1.649$9.899
Gemini 3.5 Flash Lite1M$0.33$2.749
Gemini 3.6 Flash1M$0.75$3.75
Gemini 3.7 Flash1M$0.75$3.75
Gemma 4 26B A4B IT262K$0.111$0.557
Gemma 4 31B IT262K$0.223$0.39
gemma-3-27b-it131K$0.099$0.299
GLM-4.7203K$0.78$2.785
GLM-4.7-Flash203K$0.08$0.478
GLM-5203K$0.988$3.164
GLM-5-Turbo203K$1.186$3.955
GLM-5.1203K$1.384$4.348
GLM-5.21M$1.20$4.20
GLM-5.31M$1.75$4.499
GLM-5.3-Flash1M$0.201$0.50
GLM-5V-Turbo203K$1.186$3.955
GPT-4.11M$2.192$8.769
GPT-4.1 mini1M$0.434$1.704
GPT-4.1 nano1M$0.111$0.434
GPT-4o128K$2.659$10.635
GPT-4o mini128K$0.159$0.638
GPT-5400K$1.375$10.96
GPT-5 Mini400K$0.279$2.192
GPT-5 Nano400K$0.06$0.439
GPT-5.1400K$1.375$10.96
GPT-5.41.1M$2.898$15.453
GPT-5.6 Luna1.1M$0.219$1.32
GPT-5.6 Sol1.1M$5.50$32.998
GPT-5.6 Terra1.1M$2.20$13.199
gpt-oss-120b131K$0.089$0.446
gpt-oss-20b131K$0.045$0.167
Hermes 4 70B128K$0.129$0.399
hermes-4-405b128K$0.996$2.989
Kimi K2.5262K$0.495$2.768
Kimi K2.6262K$0.773$3.38
Kimi K2.7 Code262K$0.75$3.50
Kimi K31M$3.00$14.999
Llama 3.1 405B Instruct128K$1.95$1.95
Llama 3.1 8B Instruct128K$0.167$0.167
Llama 3.3 70B Instruct131K$0.129$0.399
llama-3.1-nemotron-ultra-253b-v1128K$0.598$1.794
minicpm-v-4.532K$0.651$1.097
MiniMax-M2400K$0.349$1.405
MiniMax-M2.1196K$0.359$1.435
MiniMax-M2.5196K$0.296$1.186
MiniMax-M2.7197K$0.668$2.674
MiniMax-M31M$0.395$1.977
Ministral 3B (latest)256K$0.111$0.111
Ministral 8B (latest)256K$0.167$0.167
ministral-14b-2512256K$0.223$0.223
Mistral Large 2.1256K$0.557$1.671
Mistral Nemo Instruct 2407128K$0.145$0.145
Mistral Small (latest)262K$0.143$0.568
Mistral Small 3.2 24B Instruct131K$0.10$0.312
mistral-7b-instruct-v0.232K$0.159$0.219
mistral-7b-instruct-v0.3127K$0.111$0.111
mistral-medium-3.5256K$1.393$7.13
Mixtral 8x7B Instruct v0.132K$0.488$0.758
nemotron-nano-v2-12b128K$0.24$0.707
Nova 2 Lite1M$0.373$3.144
Nova Pro 1.0300K$0.918$3.671
nova-lite-v1300K$0.069$0.275
nova-micro-v1128K$0.04$0.159
nvidia-nemotron-3-nano-30b-a3b256K$0.06$0.24
nvidia-nemotron-3-nano-omni300K$0.059$0.237
Pixtral 12B128K$0.223$0.223
Pixtral Large (latest)128K$1.993$5.978
Qwen2.5-VL 72B Instruct32K$0.25$0.747
Qwen3 235b A22B Instruct 2507262K$0.069$0.455
Qwen3 30b A3b Instruct 2507262K$0.099$0.299
Qwen3 32B40K$0.099$0.299
Qwen3 Coder Next256K$0.167$0.891
Qwen3-Coder 30B-A3B Instruct262K$0.067$0.245
Qwen3-Next 80B-A3B (Thinking)128K$0.149$1.195
Qwen3-VL 235B-A22B256K$0.617$3.119
Qwen3.5 122B-A10B262K$0.495$3.46
Qwen3.5 397B-A17B262K$0.668$4.01
Qwen3.5 9B262K$0.111$0.167
Qwen3.6 27B262K$0.446$3.008
Qwen3.6 35B-A3B262K$0.167$0.557
Qwen3.8 2.4T A95B262K$2.50$6.00
Qwen3.8 27B262K$0.334$2.451
Qwen3.8 Flash Next262K$0.201$0.50
Voxtral Small (latest)32K$0.111$0.334