modelbenchmark.io
All hosts

deepinfra

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

Anthropic: Claude Opus 4200K$16.50$82.50
Anthropic: Claude Sonnet 4200K$3.30$16.50
ByteDance Seed 2.0 Code256K$0.50$3.00
Claude 3.7 Sonnet200K$3.30$16.50
Claude Fable 51M$10.00$50.00
Claude Haiku 4.5200K$1.00$5.00
Claude Opus 4.71M$5.00$25.00
Claude Opus 4.81M$5.00$25.00
Claude Opus 51M$5.00$25.00
Claude Sonnet 4.61M$3.00$15.00
Claude Sonnet 51M$2.00$10.00
DeepSeek R1 (Turbo) 41K$1.00$3.00
Deepseek R1 Distill Qwen 32B131K$0.27$0.27
DeepSeek V3.2164K$0.26$0.38
DeepSeek V4 Flash1M$0.08$0.18
DeepSeek V4 Pro1M$1.30$2.60
DeepSeek-R1164K$0.50$2.15
deepseek-r1-0528-turbo33K$1.00$3.00
DeepSeek-V3-0324164K$0.24$0.90
DeepSeek-V3.1164K$0.25$0.95
DeepSeek/DeepSeek-V3.1-Terminus164K$0.27$1.00
DeepSeek/DeepSeek-V3.2-Exp164K$0.32$0.89
Gemini 2.5 Flash1M$0.30$2.50
Gemini 2.5 Pro1M$1.25$10.00
Gemini 3.1 Flash Lite1M$0.25$1.50
Gemini 3.1 Pro Preview1M$2.00$12.00
Gemini 3.5 Flash1M$1.50$9.00
Gemini 3.7 Flash1M$0.75$3.75
gemini-2-0-flash-0011M$0.10$0.40
Gemma 3 12B IT131K$0.05$0.15
Gemma 3 4B IT131K$0.05$0.10
Gemma 4 26B A4B IT262K$0.07$0.34
Gemma 4 31B IT262K$0.13$0.38
Gemma 4 E4B Instruct131K$0.02$0.10
gemma-3-27b-it131K$0.08$0.16
gemma-4-31b-it-turbo262K$0.09$0.34
gemma-4-31b-it-ultra131K$0.27$0.76
GLM-4.5131K$0.40$1.60
GLM-4.6203K$0.50$2.00
GLM-4.7203K$0.40$1.75
GLM-4.7-Flash203K$0.06$0.40
GLM-5203K$0.60$2.08
GLM-5.1203K$1.05$3.50
GLM-5.21M$0.75$2.40
GLM-5.31M$1.20$4.00
GLM-5.3-Flash1M$0.15$0.50
gpt-oss-120b131K$0.037$0.17
gpt-oss-120b-turbo131K$0.15$0.60
gpt-oss-120b-ultra131K$0.20$0.95
gpt-oss-20b131K$0.03$0.14
Hermes 3 405B Instruct131K$1.00$1.00
Hermes 3 70B131K$0.70$0.70
Hy3262K$0.14$0.58
Inkling524K$0.95$4.05
Inkling Small Thinking524K$0.45$1.20
Kimi K2 0905131K$0.50$2.00
Kimi K2.5262K$0.45$2.25
Kimi K2.6262K$0.75$3.50
Kimi K2.7 Code262K$0.68$3.40
Kimi K31M$2.85$14.25
l3-1-70b-euryale131K$0.85$0.85
l3-3-70b-euryale131K$0.65$0.75
l3-8b-lunaris-v1-turbo8K$0.04$0.05
Ling 3.0 Flash131K$0.06$0.18
Llama 3.1 8B Instruct131K$0.03$0.05
Llama 3.1 Nemotron 70B Instruct131K$0.60$0.60
Llama 3.2 11B Vision Instruct131K$0.049$0.049
Llama 3.2 3B Instruct131K$0.02$0.02
Llama 3.3 70B Instruct131K$0.23$0.40
Llama 3.3 70B Turbo131K$0.10$0.32
Llama 3.3 Nemotron Super 49B v1131K$0.40$0.40
Llama 4 Maverick 17B FP81M$0.20$0.80
Llama 4 Scout 17B 16E Instruct328K$0.10$0.30
meta-llama-3-1-70b-instruct131K$0.40$0.40
meta-llama-3-1-70b-instruct-turbo131K$0.40$0.40
meta-llama-3-1-8b-instruct-turbo131K$0.02$0.04
meta-llama-3-8b-instruct8K$0.03$0.06
MiMo V2.5 (DeepInfra)262K$0.40$2.00
MiMo V2.5 Pro1M$1.00$3.00
MiMo V2.5 Thinking262K$0.40$2.00
MiniMax M2.7 Turbo197K$0.38$1.70
MiniMax-M2.5197K$0.15$1.15
MiniMax-M2.7197K$0.25$1.00
MiniMax-M3524K$0.28$1.10
Mistral Nemo Instruct 2407131K$0.019$0.03
Mistral Small 333K$0.05$0.08
Mistral Small 3.2 24B Instruct128K$0.075$0.20
Mistral: Mixtral 8x7B Instruct33K$0.40$0.40
Muse Glimmer 30B131K$0.30$1.20
MythoMax 13B4K$0.40$0.40
Nemotron 3 Nano Omni262K$0.20$0.80
Nemotron Ultra262K$0.50$2.20
nemotron-3-nano-30b-a3b262K$0.05$0.20
nemotron-content-safety-3-5131K$0.20$0.20
nvidia-nemotron-3-5-lightning262K$0.08$0.20
nvidia-nemotron-3-super-120b-a12b262K$0.085$0.40
nvidia-nemotron-nano-9b-v2131K$0.04$0.16
olmocr-7b-0725-fp816K$0.27$1.50
Phi 416K$0.07$0.14
Qwen2.5 72B Instruct33K$0.36$0.40
Qwen2.5 7B Instruct33K$0.04$0.10
Qwen2.5 VL 32B Instruct128K$0.20$0.60
Qwen3 14B41K$0.12$0.24
Qwen3 235b A22B Instruct 2507262K$0.09$0.55
Qwen3 235B A22B Thinking 2507262K$0.30$2.90
Qwen3 235B-A22B41K$0.18$0.54
Qwen3 30B A3B41K$0.12$0.50
Qwen3 32B41K$0.08$0.28
Qwen3 Coder 480B A35B Instruct Turbo262K$0.30$1.00
Qwen3 Max256K$1.20$6.00
Qwen3 Max Thinking256K$1.20$6.00
Qwen3 VL 235B A22B Instruct262K$0.20$0.88
Qwen3 VL 30B A3B Instruct262K$0.15$0.60
Qwen3-Coder 480B-A35B Instruct262K$0.40$1.60
Qwen3-Next 80B-A3B (Thinking)262K$0.14$1.40
Qwen3-Next 80B-A3B Instruct262K$0.09$1.10
Qwen3.5 122B-A10B262K$0.29$2.40
Qwen3.5 27B262K$0.26$2.60
Qwen3.5 35B-A3B262K$0.14$1.00
Qwen3.5 397B-A17B262K$0.45$3.00
Qwen3.5 9B262K$0.10$0.15
Qwen3.6 27B262K$0.32$3.20
Qwen3.6 35B-A3B262K$0.10$0.95
Qwen3.7 Max256K$2.50$7.50
Qwen3.8 2.4T A95B262K$2.00$6.00
Qwen3.8 27B262K$0.40$3.00
Qwen3.8 Max256K$1.65$4.951
QwQ 32B131K$0.15$0.40
R1 Distill Llama 70B131K$0.20$0.60
Seed 2.0 Mini256K$0.10$0.40
Seed 2.0 Pro256K$0.50$3.00
seed-1.8256K$0.25$2.00
Step 3.7 Flash262K$0.20$1.15
WizardLM-2 8x22B66K$0.48$0.48