LLM API price comparison
All 338 models in one live table. Prices are per 1M tokens and already include the flat 3% fee — the provider price behind every number is printed on each model page and on /pricing. Set your monthly workload to rank models by what they would actually cost you.
338 of 338 models · workload 10M in + 2M out · flat 3% fee included
Free Models RouterOpenRouterFreeFreeFree200K$0.00in Free · out Free · ctx 200K · run $0.00
Gemma 4 26B A4B (free)GoogleFreeFreeFree262K$0.00in Free · out Free · ctx 262K · run $0.00- Gemma 4 31B (free)GoogleFreeFreeFree262K$0.00in Free · out Free · ctx 262K · run $0.00
gpt-oss-120b (free)OpenAIFreeFreeFree131K$0.00in Free · out Free · ctx 131K · run $0.00- gpt-oss-20b (free)OpenAIFreeFreeFree131K$0.00in Free · out Free · ctx 131K · run $0.00
Hermes 3 405B Instruct (free)Nous ResearchFreeFreeFree131K$0.00in Free · out Free · ctx 131K · run $0.00
Laguna M.1 (free)poolsideFreeFreeFree262K$0.00in Free · out Free · ctx 262K · run $0.00- Laguna XS.2 (free)poolsideFreeFreeFree262K$0.00in Free · out Free · ctx 262K · run $0.00
LFM2.5-1.2B-Instruct (free)Liquid AIFreeFreeFree33K$0.00in Free · out Free · ctx 33K · run $0.00- LFM2.5-1.2B-Thinking (free)Liquid AIFreeFreeFree33K$0.00in Free · out Free · ctx 33K · run $0.00
Llama 3.2 3B Instruct (free)Meta AIFreeFreeFree131K$0.00in Free · out Free · ctx 131K · run $0.00- Llama 3.3 70B Instruct (free)Meta AIFreeFreeFree131K$0.00in Free · out Free · ctx 131K · run $0.00
- Lyria 3 Clip PreviewGoogleFreeFreeFree1.0M$0.00in Free · out Free · ctx 1.0M · run $0.00
- Lyria 3 Pro PreviewGoogleFreeFreeFree1.0M$0.00in Free · out Free · ctx 1.0M · run $0.00
Nemotron 3 Nano 30B A3B (free)NVIDIAFreeFreeFree256K$0.00in Free · out Free · ctx 256K · run $0.00- Nemotron 3 Nano Omni (free)NVIDIAFreeFreeFree256K$0.00in Free · out Free · ctx 256K · run $0.00
- Nemotron 3 Super (free)NVIDIAFreeFreeFree1M$0.00in Free · out Free · ctx 1M · run $0.00
- Nemotron 3 Ultra (free)NVIDIAFreeFreeFree1M$0.00in Free · out Free · ctx 1M · run $0.00
- Nemotron 3.5 Content Safety (free)NVIDIAFreeFreeFree128K$0.00in Free · out Free · ctx 128K · run $0.00
- Nemotron Nano 12B 2 VL (free)NVIDIAFreeFreeFree128K$0.00in Free · out Free · ctx 128K · run $0.00
- Nemotron Nano 9B V2 (free)NVIDIAFreeFreeFree128K$0.00in Free · out Free · ctx 128K · run $0.00
North Mini Code (free)CohereFreeFreeFree256K$0.00in Free · out Free · ctx 256K · run $0.00
Qwen3 Coder 480B A35B (free)QwenFreeFreeFree1.0M$0.00in Free · out Free · ctx 1.0M · run $0.00- Qwen3 Next 80B A3B Instruct (free)QwenFreeFreeFree262K$0.00in Free · out Free · ctx 262K · run $0.00
Uncensored (free)Cognitive ComputationsFreeFreeFree33K$0.00in Free · out Free · ctx 33K · run $0.00
Ling-2.6-flashInclusionAI$0.010$0.031262K$0.16in $0.010 · out $0.031 · ctx 262K · run $0.16- Llama 3.1 8B InstructMeta AI$0.021$0.031131K$0.27in $0.021 · out $0.031 · ctx 131K · run $0.27
Mistral NemoMistral AI$0.021$0.031131K$0.27in $0.021 · out $0.031 · ctx 131K · run $0.27
Granite 4.0 MicroIBM$0.018$0.115131K$0.41in $0.018 · out $0.115 · ctx 131K · run $0.41
Llama 3 8B LunarisSao10K$0.041$0.0528K$0.52in $0.041 · out $0.052 · ctx 8K · run $0.52- LFM2-24B-A2BLiquid AI$0.031$0.124128K$0.56in $0.031 · out $0.124 · ctx 128K · run $0.56
- gpt-oss-20bOpenAI$0.030$0.144131K$0.59in $0.030 · out $0.144 · ctx 131K · run $0.59
- gpt-oss-120bOpenAI$0.031$0.154131K$0.62in $0.031 · out $0.154 · ctx 131K · run $0.62
- Qwen2.5 7B InstructQwen$0.041$0.103131K$0.62in $0.041 · out $0.103 · ctx 131K · run $0.62
Nova Micro 1.0Amazon$0.036$0.144128K$0.65in $0.036 · out $0.144 · ctx 128K · run $0.65- Mistral Small 3Mistral AI$0.052$0.08233K$0.68in $0.052 · out $0.082 · ctx 33K · run $0.68
- Llama 3.2 1B InstructMeta AI$0.028$0.207131K$0.69in $0.028 · out $0.207 · ctx 131K · run $0.69
- Command R7B (12-2024)Cohere$0.039$0.154128K$0.70in $0.039 · out $0.154 · ctx 128K · run $0.70
- Gemma 3 4BGoogle$0.052$0.103131K$0.72in $0.052 · out $0.103 · ctx 131K · run $0.72
- Granite 4.1 8BIBM$0.052$0.103131K$0.72in $0.052 · out $0.103 · ctx 131K · run $0.72
MythoMax 13BGryphe$0.062$0.0624K$0.74in $0.062 · out $0.062 · ctx 4K · run $0.74
Trinity MiniArcee AI$0.046$0.154131K$0.77in $0.046 · out $0.154 · ctx 131K · run $0.77- Gemma 3 12BGoogle$0.052$0.154131K$0.82in $0.052 · out $0.154 · ctx 131K · run $0.82
- Gemma 3n 4BGoogle$0.062$0.12433K$0.87in $0.062 · out $0.124 · ctx 33K · run $0.87
- Qwen3 30B A3B Instruct 2507Qwen$0.050$0.199131K$0.89in $0.050 · out $0.199 · ctx 131K · run $0.89
- Nemotron 3 Nano 30B A3BNVIDIA$0.052$0.206262K$0.93in $0.052 · out $0.206 · ctx 262K · run $0.93
Phi 4Microsoft$0.072$0.14416K$1.01in $0.072 · out $0.144 · ctx 16K · run $1.01
Hy3 previewTencent$0.065$0.216262K$1.08in $0.065 · out $0.216 · ctx 262K · run $1.08- Nova Lite 1.0Amazon$0.062$0.247300K$1.11in $0.062 · out $0.247 · ctx 300K · run $1.11
- Qwen3 235B A22B Instruct 2507Qwen$0.093$0.103262K$1.13in $0.093 · out $0.103 · ctx 262K · run $1.13
- Gemma 3 27BGoogle$0.082$0.165131K$1.15in $0.082 · out $0.165 · ctx 131K · run $1.15
- Mistral Small 3.2 24BMistral AI$0.077$0.206128K$1.18in $0.077 · out $0.206 · ctx 128K · run $1.18
- Qwen3.5-FlashQwen$0.067$0.2681M$1.21in $0.067 · out $0.268 · ctx 1M · run $1.21
- Llama 3.2 3B InstructMeta AI$0.052$0.345131K$1.21in $0.052 · out $0.345 · ctx 131K · run $1.21
- Ministral 3 3B 2512Mistral AI$0.103$0.103131K$1.24in $0.103 · out $0.103 · ctx 131K · run $1.24
Reka EdgeReka$0.103$0.10316K$1.24in $0.103 · out $0.103 · ctx 16K · run $1.24- Qwen3 Coder 30B A3B InstructQwen$0.072$0.278160K$1.28in $0.072 · out $0.278 · ctx 160K · run $1.28
DeepSeek V4 FlashDeepSeek$0.093$0.1851.0M$1.30in $0.093 · out $0.185 · ctx 1.0M · run $1.30- Gemma 4 26B A4B Google$0.062$0.340262K$1.30in $0.062 · out $0.340 · ctx 262K · run $1.30
- GPT-5 NanoOpenAI$0.052$0.412400K$1.34in $0.052 · out $0.412 · ctx 400K · run $1.34
- Qwen3.5-9BQwen$0.103$0.154262K$1.34in $0.103 · out $0.154 · ctx 262K · run $1.34
- gpt-oss-safeguard-20bOpenAI$0.077$0.309131K$1.39in $0.077 · out $0.309 · ctx 131K · run $1.39
Seed 1.6 FlashByteDance Seed$0.077$0.309262K$1.39in $0.077 · out $0.309 · ctx 262K · run $1.39- Qwen3 32BQwen$0.082$0.288131K$1.40in $0.082 · out $0.288 · ctx 131K · run $1.40
GLM 4.7 FlashZ.ai$0.062$0.412203K$1.44in $0.062 · out $0.412 · ctx 203K · run $1.44- Laguna XS.2poolside$0.103$0.206262K$1.44in $0.103 · out $0.206 · ctx 262K · run $1.44
- Reka Flash 3Reka$0.103$0.20666K$1.44in $0.103 · out $0.206 · ctx 66K · run $1.44
UI-TARS 7B ByteDance$0.103$0.206128K$1.44in $0.103 · out $0.206 · ctx 128K · run $1.44- Qwen3 14BQwen$0.103$0.247132K$1.52in $0.103 · out $0.247 · ctx 132K · run $1.52
- Llama 4 ScoutMeta AI$0.103$0.30910M$1.65in $0.103 · out $0.309 · ctx 10M · run $1.65
Step 3.5 FlashStepFun$0.103$0.309262K$1.65in $0.103 · out $0.309 · ctx 262K · run $1.65- Voxtral Small 24B 2507Mistral AI$0.103$0.30932K$1.65in $0.103 · out $0.309 · ctx 32K · run $1.65
MiMo-V2.5Xiaomi$0.108$0.2881.0M$1.66in $0.108 · out $0.288 · ctx 1.0M · run $1.66- Llama 3.3 70B InstructMeta AI$0.103$0.330131K$1.69in $0.103 · out $0.330 · ctx 131K · run $1.69
- Nemotron 3 SuperNVIDIA$0.088$0.4121M$1.70in $0.088 · out $0.412 · ctx 1M · run $1.70
- Llama 3 8B InstructMeta AI$0.144$0.1448K$1.73in $0.144 · out $0.144 · ctx 8K · run $1.73
- Ministral 3 8B 2512Mistral AI$0.154$0.154262K$1.85in $0.154 · out $0.154 · ctx 262K · run $1.85
- Gemini 2.5 Flash LiteGoogle$0.103$0.4121.0M$1.85in $0.103 · out $0.412 · ctx 1.0M · run $1.85
- Gemini 2.5 Flash Lite Preview 09-2025Google$0.103$0.4121.0M$1.85in $0.103 · out $0.412 · ctx 1.0M · run $1.85
- GPT-4.1 NanoOpenAI$0.103$0.4121.0M$1.85in $0.103 · out $0.412 · ctx 1.0M · run $1.85
- Qwen3 VL 8B InstructQwen$0.082$0.515256K$1.85in $0.082 · out $0.515 · ctx 256K · run $1.85
- Seed-2.0-MiniByteDance Seed$0.103$0.412262K$1.85in $0.103 · out $0.412 · ctx 262K · run $1.85
- Qwen3 VL 32B InstructQwen$0.107$0.428262K$1.93in $0.107 · out $0.428 · ctx 262K · run $1.93
- Gemma 4 31BGoogle$0.124$0.360262K$1.96in $0.124 · out $0.360 · ctx 262K · run $1.96
- Ling-2.6-1TInclusionAI$0.077$0.644262K$2.06in $0.077 · out $0.644 · ctx 262K · run $2.06
- Ring-2.6-1TInclusionAI$0.077$0.644262K$2.06in $0.077 · out $0.644 · ctx 262K · run $2.06
- Qwen3 8BQwen$0.121$0.469131K$2.14in $0.121 · out $0.469 · ctx 131K · run $2.14
- Hermes 4 70BNous Research$0.134$0.412131K$2.16in $0.134 · out $0.412 · ctx 131K · run $2.16
- Llama Guard 4 12BMeta AI$0.185$0.185164K$2.22in $0.185 · out $0.185 · ctx 164K · run $2.22
MiniMax M2.5MiniMax$0.124$0.494205K$2.22in $0.124 · out $0.494 · ctx 205K · run $2.22- Qwen3 30B A3BQwen$0.124$0.515131K$2.27in $0.124 · out $0.515 · ctx 131K · run $2.27
- Qwen3 VL 30B A3B InstructQwen$0.134$0.536262K$2.41in $0.134 · out $0.536 · ctx 262K · run $2.41
- Ministral 3 14B 2512Mistral AI$0.206$0.206262K$2.47in $0.206 · out $0.206 · ctx 262K · run $2.47
Olmo 3 32B ThinkAi2$0.154$0.51566K$2.58in $0.154 · out $0.515 · ctx 66K · run $2.58- Qwen3 Next 80B A3B ThinkingQwen$0.100$0.803262K$2.61in $0.100 · out $0.803 · ctx 262K · run $2.61
- Hunyuan A13B InstructTencent$0.144$0.587131K$2.62in $0.144 · out $0.587 · ctx 131K · run $2.62
- Command R (08-2024)Cohere$0.154$0.618128K$2.78in $0.154 · out $0.618 · ctx 128K · run $2.78
- GPT-4o-miniOpenAI$0.154$0.618128K$2.78in $0.154 · out $0.618 · ctx 128K · run $2.78
- GPT-4o-mini (2024-07-18)OpenAI$0.154$0.618128K$2.78in $0.154 · out $0.618 · ctx 128K · run $2.78
- GPT-4o-mini Search PreviewOpenAI$0.154$0.618128K$2.78in $0.154 · out $0.618 · ctx 128K · run $2.78
- Llama 4 MaverickMeta AI$0.154$0.6181.0M$2.78in $0.154 · out $0.618 · ctx 1.0M · run $2.78
- Mistral Small 4Mistral AI$0.154$0.618262K$2.78in $0.154 · out $0.618 · ctx 262K · run $2.78
Solar Pro 3Upstage$0.154$0.618128K$2.78in $0.154 · out $0.618 · ctx 128K · run $2.78- Qwen3 Coder NextQwen$0.113$0.824262K$2.78in $0.113 · out $0.824 · ctx 262K · run $2.78
- Laguna M.1poolside$0.206$0.412262K$2.88in $0.206 · out $0.412 · ctx 262K · run $2.88
- DeepSeek V3.2DeepSeek$0.236$0.353131K$3.06in $0.236 · out $0.353 · ctx 131K · run $3.06
- GLM 4.5 AirZ.ai$0.134$0.875131K$3.09in $0.134 · out $0.875 · ctx 131K · run $3.09
- Qwen3 Next 80B A3B InstructQwen$0.093$1.13262K$3.19in $0.093 · out $1.13 · ctx 262K · run $3.19
- SabaMistral AI$0.206$0.61833K$3.30in $0.206 · out $0.618 · ctx 33K · run $3.30
- MiniMax M2.7MiniMax$0.185$0.742205K$3.34in $0.185 · out $0.742 · ctx 205K · run $3.34
- Qwen3.5-35B-A3BQwen$0.144$1.03262K$3.50in $0.144 · out $1.03 · ctx 262K · run $3.50
- Qwen3.6 35B A3BQwen$0.144$1.03262K$3.50in $0.144 · out $1.03 · ctx 262K · run $3.50
Rocinante 12BTheDrummer$0.258$0.51533K$3.61in $0.258 · out $0.515 · ctx 33K · run $3.61- DeepSeek V3.2 ExpDeepSeek$0.278$0.422164K$3.63in $0.278 · out $0.422 · ctx 164K · run $3.63
- DeepSeek V3DeepSeek$0.206$0.824131K$3.71in $0.206 · out $0.824 · ctx 131K · run $3.71
- DeepSeek V3.1DeepSeek$0.216$0.814164K$3.79in $0.216 · out $0.814 · ctx 164K · run $3.79
- Qwen3 VL 235B A22B InstructQwen$0.206$0.906262K$3.87in $0.206 · out $0.906 · ctx 262K · run $3.87
- Qwen3 Coder FlashQwen$0.201$1.001M$4.02in $0.201 · out $1.00 · ctx 1M · run $4.02
- Qwen3 VL 8B ThinkingQwen$0.121$1.41256K$4.02in $0.121 · out $1.41 · ctx 256K · run $4.02
- Cydonia 24B V4.1TheDrummer$0.309$0.515131K$4.12in $0.309 · out $0.515 · ctx 131K · run $4.12
Mercury 2Inception$0.258$0.772128K$4.12in $0.258 · out $0.772 · ctx 128K · run $4.12- Trinity Large ThinkingArcee AI$0.258$0.824262K$4.22in $0.258 · out $0.824 · ctx 262K · run $4.22
- Qwen3.6 FlashQwen$0.193$1.161M$4.25in $0.193 · out $1.16 · ctx 1M · run $4.25
- Llama 3.2 11B Vision InstructMeta AI$0.355$0.355131K$4.26in $0.355 · out $0.355 · ctx 131K · run $4.26
- Qwen Plus 0728Qwen$0.268$0.8031M$4.28in $0.268 · out $0.803 · ctx 1M · run $4.28
- Qwen Plus 0728 (thinking)Qwen$0.268$0.8031M$4.28in $0.268 · out $0.803 · ctx 1M · run $4.28
- Qwen-PlusQwen$0.268$0.8031M$4.28in $0.268 · out $0.803 · ctx 1M · run $4.28
- DeepSeek V3 0324DeepSeek$0.247$0.927164K$4.33in $0.247 · out $0.927 · ctx 164K · run $4.33
- MiniMax-01MiniMax$0.206$1.131.0M$4.33in $0.206 · out $1.13 · ctx 1.0M · run $4.33
- Step 3.7 FlashStepFun$0.206$1.18256K$4.43in $0.206 · out $1.18 · ctx 256K · run $4.43
- Qwen2.5 72B InstructQwen$0.371$0.412131K$4.53in $0.371 · out $0.412 · ctx 131K · run $4.53
- Qwen3 30B A3B Thinking 2507Qwen$0.134$1.61131K$4.55in $0.134 · out $1.61 · ctx 131K · run $4.55
- Qwen3 VL 30B A3B ThinkingQwen$0.134$1.61131K$4.55in $0.134 · out $1.61 · ctx 131K · run $4.55
- Qwen3 235B A22B Thinking 2507Qwen$0.154$1.54262K$4.62in $0.154 · out $1.54 · ctx 262K · run $4.62
- GPT-5.4 NanoOpenAI$0.206$1.29400K$4.63in $0.206 · out $1.29 · ctx 400K · run $4.63
Nex-N2-ProNex$0.258$1.03262K$4.63in $0.258 · out $1.03 · ctx 262K · run $4.63
Perceptron Mk1Perceptron AI$0.154$1.5433K$4.63in $0.154 · out $1.54 · ctx 33K · run $4.63- MiniMax M2MiniMax$0.263$1.05205K$4.73in $0.263 · out $1.05 · ctx 205K · run $4.73
- DeepSeek V3.1 TerminusDeepSeek$0.278$0.978164K$4.74in $0.278 · out $0.978 · ctx 164K · run $4.74
- Mistral Small 3.1 24BMistral AI$0.362$0.572128K$4.76in $0.362 · out $0.572 · ctx 128K · run $4.76
- Codestral 2508Mistral AI$0.309$0.927256K$4.94in $0.309 · out $0.927 · ctx 256K · run $4.94
- GLM 4.6VZ.ai$0.309$0.927131K$4.94in $0.309 · out $0.927 · ctx 131K · run $4.94
- Llama 3.1 70B InstructMeta AI$0.412$0.412131K$4.94in $0.412 · out $0.412 · ctx 131K · run $4.94
- Llama 3.3 Nemotron Super 49B V1.5NVIDIA$0.412$0.412131K$4.94in $0.412 · out $0.412 · ctx 131K · run $4.94
- UnslopNemo 12BTheDrummer$0.412$0.41233K$4.94in $0.412 · out $0.412 · ctx 33K · run $4.94
Claude 3 HaikuAnthropic$0.258$1.29200K$5.15in $0.258 · out $1.29 · ctx 200K · run $5.15- Qwen3.5-27BQwen$0.201$1.61262K$5.22in $0.201 · out $1.61 · ctx 262K · run $5.22
KAT-Coder-Pro V2Kwaipilot$0.309$1.24256K$5.56in $0.309 · out $1.24 · ctx 256K · run $5.56- MiniMax M2-herMiniMax$0.309$1.2466K$5.56in $0.309 · out $1.24 · ctx 66K · run $5.56
- MiniMax M2.1MiniMax$0.309$1.24205K$5.56in $0.309 · out $1.24 · ctx 205K · run $5.56
- MiniMax M3MiniMax$0.309$1.241.0M$5.56in $0.309 · out $1.24 · ctx 1.0M · run $5.56
- Gemini 3.1 Flash LiteGoogle$0.258$1.541.0M$5.67in $0.258 · out $1.54 · ctx 1.0M · run $5.67
- Gemini 3.1 Flash Lite PreviewGoogle$0.258$1.541.0M$5.67in $0.258 · out $1.54 · ctx 1.0M · run $5.67
- Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google$0.258$1.5466K$5.67in $0.258 · out $1.54 · ctx 66K · run $5.67
- Qwen3.5 Plus 2026-02-15Qwen$0.268$1.611M$5.89in $0.268 · out $1.61 · ctx 1M · run $5.89
- Qwen3.7 PlusQwen$0.330$1.321M$5.93in $0.330 · out $1.32 · ctx 1M · run $5.93
- Qwen3 Coder 480B A35BQwen$0.227$1.851.0M$5.97in $0.227 · out $1.85 · ctx 1.0M · run $5.97
ReMM SLERP 13BUndi95$0.464$0.6706K$5.97in $0.464 · out $0.670 · ctx 6K · run $5.97- DeepSeek V4 ProDeepSeek$0.448$0.8961.0M$6.27in $0.448 · out $0.896 · ctx 1.0M · run $6.27
- MiMo-V2.5-ProXiaomi$0.448$0.8961.0M$6.27in $0.448 · out $0.896 · ctx 1.0M · run $6.27
- GPT-5 MiniOpenAI$0.258$2.06400K$6.70in $0.258 · out $2.06 · ctx 400K · run $6.70
- GPT-5.1-Codex-MiniOpenAI$0.258$2.06400K$6.70in $0.258 · out $2.06 · ctx 400K · run $6.70
- Seed 1.6ByteDance Seed$0.258$2.06262K$6.70in $0.258 · out $2.06 · ctx 262K · run $6.70
- Seed-2.0-LiteByteDance Seed$0.258$2.06262K$6.70in $0.258 · out $2.06 · ctx 262K · run $6.70
- Coder LargeArcee AI$0.515$0.82433K$6.80in $0.515 · out $0.824 · ctx 33K · run $6.80
- Qwen3.5 Plus 2026-04-20Qwen$0.309$1.851M$6.80in $0.309 · out $1.85 · ctx 1M · run $6.80
ERNIE 4.5 VL 424B A47B Baidu$0.433$1.29131K$6.90in $0.433 · out $1.29 · ctx 131K · run $6.90- Qwen3.5-122B-A10BQwen$0.268$2.14262K$6.96in $0.268 · out $2.14 · ctx 262K · run $6.96
- Skyfall 36B V2TheDrummer$0.567$0.82433K$7.31in $0.567 · out $0.824 · ctx 33K · run $7.31
- Qwen3.6 PlusQwen$0.335$2.011M$7.36in $0.335 · out $2.01 · ctx 1M · run $7.36
- GPT-4.1 MiniOpenAI$0.412$1.651.0M$7.42in $0.412 · out $1.65 · ctx 1.0M · run $7.42
- WizardLM-2 8x22BMicrosoft$0.639$0.63966K$7.66in $0.639 · out $0.639 · ctx 66K · run $7.66
- GLM 4.7Z.ai$0.412$1.80203K$7.72in $0.412 · out $1.80 · ctx 203K · run $7.72
- Qwen3.6 27BQwen$0.294$2.47262K$7.88in $0.294 · out $2.47 · ctx 262K · run $7.88
- GLM 4.6Z.ai$0.443$1.79203K$8.01in $0.443 · out $1.79 · ctx 203K · run $8.01
Kimi K2.5Moonshot AI$0.386$2.09262K$8.03in $0.386 · out $2.09 · ctx 262K · run $8.03- Gemma 2 27BGoogle$0.670$0.6708K$8.03in $0.670 · out $0.670 · ctx 8K · run $8.03
- Qwen3 VL 235B A22B ThinkingQwen$0.268$2.68131K$8.03in $0.268 · out $2.68 · ctx 131K · run $8.03
- Devstral 2 2512Mistral AI$0.412$2.06262K$8.24in $0.412 · out $2.06 · ctx 262K · run $8.24
- Gemini 2.5 FlashGoogle$0.309$2.581.0M$8.24in $0.309 · out $2.58 · ctx 1.0M · run $8.24
- GPT-3.5 TurboOpenAI$0.515$1.5416K$8.24in $0.515 · out $1.54 · ctx 16K · run $8.24
- Mistral Large 3 2512Mistral AI$0.515$1.54262K$8.24in $0.515 · out $1.54 · ctx 262K · run $8.24
- Mistral Medium 3Mistral AI$0.412$2.06131K$8.24in $0.412 · out $2.06 · ctx 131K · run $8.24
- Mistral Medium 3.1Mistral AI$0.412$2.06131K$8.24in $0.412 · out $2.06 · ctx 131K · run $8.24
- Nano Banana (Gemini 2.5 Flash Image)Google$0.309$2.5833K$8.24in $0.309 · out $2.58 · ctx 33K · run $8.24
- Nova 2 LiteAmazon$0.309$2.581M$8.24in $0.309 · out $2.58 · ctx 1M · run $8.24
- Llama 3.3 Euryale 70BSao10K$0.670$0.772131K$8.24in $0.670 · out $0.772 · ctx 131K · run $8.24
- Qwen3 235B A22BQwen$0.469$1.87131K$8.44in $0.469 · out $1.87 · ctx 131K · run $8.44
- Hermes 3 70B InstructNous Research$0.721$0.721131K$8.65in $0.721 · out $0.721 · ctx 131K · run $8.65
- MiniMax M1MiniMax$0.412$2.271M$8.65in $0.412 · out $2.27 · ctx 1M · run $8.65
- Qwen2.5 Coder 32B InstructQwen$0.680$1.03128K$8.86in $0.680 · out $1.03 · ctx 128K · run $8.86
- Qwen3.5 397B A17BQwen$0.397$2.52256K$9.01in $0.397 · out $2.52 · ctx 256K · run $9.01
- R1 0528DeepSeek$0.515$2.21164K$9.58in $0.515 · out $2.21 · ctx 164K · run $9.58
- Nemotron 3 UltraNVIDIA$0.515$2.271M$9.68in $0.515 · out $2.27 · ctx 1M · run $9.68
Weaver (alpha)Mancer$0.772$1.038K$9.79in $0.772 · out $1.03 · ctx 8K · run $9.79- GLM 4.5VZ.ai$0.618$1.8566K$9.89in $0.618 · out $1.85 · ctx 66K · run $9.89
- R1 Distill Llama 70BDeepSeek$0.824$0.824128K$9.89in $0.824 · out $0.824 · ctx 128K · run $9.89
Aion-1.0-MiniAion Labs$0.721$1.44131K$10.09in $0.721 · out $1.44 · ctx 131K · run $10.09- GLM 5Z.ai$0.618$1.98203K$10.14in $0.618 · out $1.98 · ctx 203K · run $10.14
- Virtuoso LargeArcee AI$0.772$1.24131K$10.20in $0.772 · out $1.24 · ctx 131K · run $10.20
- Qwen2.5 VL 72B InstructQwen$0.824$1.03131K$10.30in $0.824 · out $1.03 · ctx 131K · run $10.30
- Llama 3.1 Euryale 70B v2.2Sao10K$0.875$0.875131K$10.51in $0.875 · out $0.875 · ctx 131K · run $10.51
- Kimi K2 0711Moonshot AI$0.587$2.37131K$10.61in $0.587 · out $2.37 · ctx 131K · run $10.61
- GLM 4.5Z.ai$0.618$2.27131K$10.71in $0.618 · out $2.27 · ctx 131K · run $10.71
Morph V3 FastMorph$0.824$1.2482K$10.71in $0.824 · out $1.24 · ctx 82K · run $10.71- GPT Audio MiniOpenAI$0.618$2.47128K$11.12in $0.618 · out $2.47 · ctx 128K · run $11.12
Relace Apply 3Relace$0.875$1.29256K$11.33in $0.875 · out $1.29 · ctx 256K · run $11.33- Gemini 3 Flash PreviewGoogle$0.515$3.091.0M$11.33in $0.515 · out $3.09 · ctx 1.0M · run $11.33
- Kimi K2 0905Moonshot AI$0.618$2.58262K$11.33in $0.618 · out $2.58 · ctx 262K · run $11.33
- Kimi K2 ThinkingMoonshot AI$0.618$2.58262K$11.33in $0.618 · out $2.58 · ctx 262K · run $11.33
- Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google$0.515$3.09131K$11.33in $0.515 · out $3.09 · ctx 131K · run $11.33
- Nano Banana 2 (Gemini 3.1 Flash Image)Google$0.515$3.09131K$11.33in $0.515 · out $3.09 · ctx 131K · run $11.33
- Aion-2.0Aion Labs$0.824$1.65131K$11.54in $0.824 · out $1.65 · ctx 131K · run $11.54
- Aion-RP 1.0 (8B)Aion Labs$0.824$1.6533K$11.54in $0.824 · out $1.65 · ctx 33K · run $11.54
- Kimi K2.6Moonshot AI$0.567$3.30262K$12.26in $0.567 · out $3.30 · ctx 262K · run $12.26
- MoonshotAI Kimi LatestMoonshot AI$0.567$3.30262K$12.26in $0.567 · out $3.30 · ctx 262K · run $12.26
- R1DeepSeek$0.721$2.58164K$12.36in $0.721 · out $2.58 · ctx 164K · run $12.36
- Hermes 3 405B InstructNous Research$1.03$1.03131K$12.36in $1.03 · out $1.03 · ctx 131K · run $12.36
SonarPerplexity$1.03$1.03127K$12.36in $1.03 · out $1.03 · ctx 127K · run $12.36- Morph V3 LargeMorph$0.927$1.96262K$13.18in $0.927 · out $1.96 · ctx 262K · run $13.18
- Qwen3 Coder PlusQwen$0.670$3.351M$13.39in $0.670 · out $3.35 · ctx 1M · run $13.39
- GPT-3.5 Turbo (older v0613)OpenAI$1.03$2.064K$14.42in $1.03 · out $2.06 · ctx 4K · run $14.42
Grok Build 0.1xAI$1.03$2.06256K$14.42in $1.03 · out $2.06 · ctx 256K · run $14.42- Kimi K2.7 CodeMoonshot AI$0.762$3.60262K$14.83in $0.762 · out $3.60 · ctx 262K · run $14.83
- Nova Pro 1.0Amazon$0.824$3.30300K$14.83in $0.824 · out $3.30 · ctx 300K · run $14.83
Cogito v2.1 671BDeep Cogito$1.29$1.29128K$15.45in $1.29 · out $1.29 · ctx 128K · run $15.45
Switchpoint RouterSwitchpoint AI$0.875$3.50131K$15.76in $0.875 · out $3.50 · ctx 131K · run $15.76- GLM 5.2Z.ai$0.958$3.091.0M$15.76in $0.958 · out $3.09 · ctx 1.0M · run $15.76
- Qwen3 MaxQwen$0.803$4.02262K$16.07in $0.803 · out $4.02 · ctx 262K · run $16.07
- Qwen3 Max ThinkingQwen$0.803$4.02262K$16.07in $0.803 · out $4.02 · ctx 262K · run $16.07
- Hermes 4 405BNous Research$1.03$3.09131K$16.48in $1.03 · out $3.09 · ctx 131K · run $16.48
- Relace SearchRelace$1.03$3.09256K$16.48in $1.03 · out $3.09 · ctx 256K · run $16.48
- GPT-5.4 MiniOpenAI$0.772$4.63400K$16.99in $0.772 · out $4.63 · ctx 400K · run $16.99
- OpenAI GPT Mini LatestOpenAI$0.772$4.63400K$16.99in $0.772 · out $4.63 · ctx 400K · run $16.99
- Grok 4.20xAI$1.29$2.582M$18.02in $1.29 · out $2.58 · ctx 2M · run $18.02
- Grok 4.20 Multi-AgentxAI$1.29$2.582M$18.02in $1.29 · out $2.58 · ctx 2M · run $18.02
- Grok 4.3xAI$1.29$2.581M$18.02in $1.29 · out $2.58 · ctx 1M · run $18.02
Palmyra X5Writer$0.618$6.181.0M$18.54in $0.618 · out $6.18 · ctx 1.0M · run $18.54- GLM 5.1Z.ai$1.00$4.43203K$18.90in $1.00 · out $4.43 · ctx 203K · run $18.90
- GPT-3.5 Turbo InstructOpenAI$1.54$2.064K$19.57in $1.54 · out $2.06 · ctx 4K · run $19.57
- o3 MiniOpenAI$1.13$4.53200K$20.39in $1.13 · out $4.53 · ctx 200K · run $20.39
- o3 Mini HighOpenAI$1.13$4.53200K$20.39in $1.13 · out $4.53 · ctx 200K · run $20.39
- o4 MiniOpenAI$1.13$4.53200K$20.39in $1.13 · out $4.53 · ctx 200K · run $20.39
- o4 Mini HighOpenAI$1.13$4.53200K$20.39in $1.13 · out $4.53 · ctx 200K · run $20.39
- Anthropic Claude Haiku LatestAnthropic$1.03$5.15200K$20.60in $1.03 · out $5.15 · ctx 200K · run $20.60
- Claude Haiku 4.5Anthropic$1.03$5.15200K$20.60in $1.03 · out $5.15 · ctx 200K · run $20.60
- GLM 5 TurboZ.ai$1.24$4.12262K$20.60in $1.24 · out $4.12 · ctx 262K · run $20.60
- GLM 5V TurboZ.ai$1.24$4.12203K$20.60in $1.24 · out $4.12 · ctx 203K · run $20.60
- Qwen3.7 MaxQwen$1.29$3.861M$20.60in $1.29 · out $3.86 · ctx 1M · run $20.60
- Qwen3.6 Max PreviewQwen$1.07$6.43262K$23.57in $1.07 · out $6.43 · ctx 262K · run $23.57
- GPT-5 Image MiniOpenAI$2.58$2.06400K$29.87in $2.58 · out $2.06 · ctx 400K · run $29.87
- Mistral Medium 3.5Mistral AI$1.54$7.73262K$30.90in $1.54 · out $7.73 · ctx 262K · run $30.90
- Mistral LargeMistral AI$2.06$6.18128K$32.96in $2.06 · out $6.18 · ctx 128K · run $32.96
- Mistral Large 2407Mistral AI$2.06$6.18131K$32.96in $2.06 · out $6.18 · ctx 131K · run $32.96
- Mixtral 8x22B InstructMistral AI$2.06$6.1866K$32.96in $2.06 · out $6.18 · ctx 66K · run $32.96
- Gemini 2.5 ProGoogle$1.29$10.301.0M$33.48in $1.29 · out $10.30 · ctx 1.0M · run $33.48
- Gemini 2.5 Pro Preview 05-06Google$1.29$10.301.0M$33.48in $1.29 · out $10.30 · ctx 1.0M · run $33.48
- Gemini 2.5 Pro Preview 06-05Google$1.29$10.301.0M$33.48in $1.29 · out $10.30 · ctx 1.0M · run $33.48
- GPT-5OpenAI$1.29$10.30400K$33.48in $1.29 · out $10.30 · ctx 400K · run $33.48
- GPT-5 ChatOpenAI$1.29$10.30128K$33.48in $1.29 · out $10.30 · ctx 128K · run $33.48
- GPT-5 CodexOpenAI$1.29$10.30400K$33.48in $1.29 · out $10.30 · ctx 400K · run $33.48
- GPT-5.1OpenAI$1.29$10.30400K$33.48in $1.29 · out $10.30 · ctx 400K · run $33.48
- GPT-5.1 ChatOpenAI$1.29$10.30128K$33.48in $1.29 · out $10.30 · ctx 128K · run $33.48
- GPT-5.1-CodexOpenAI$1.29$10.30400K$33.48in $1.29 · out $10.30 · ctx 400K · run $33.48
- GPT-5.1-Codex-MaxOpenAI$1.29$10.30400K$33.48in $1.29 · out $10.30 · ctx 400K · run $33.48
- Gemini 3.5 FlashGoogle$1.54$9.271.0M$33.99in $1.54 · out $9.27 · ctx 1.0M · run $33.99
- Google Gemini Flash LatestGoogle$1.54$9.271.0M$33.99in $1.54 · out $9.27 · ctx 1.0M · run $33.99
- GPT-4.1OpenAI$2.06$8.241.0M$37.08in $2.06 · out $8.24 · ctx 1.0M · run $37.08
Jamba Large 1.7AI21 Labs$2.06$8.24256K$37.08in $2.06 · out $8.24 · ctx 256K · run $37.08- Llama 3.1 70B Hanami x1Sao10K$3.09$3.0916K$37.08in $3.09 · out $3.09 · ctx 16K · run $37.08
- o3OpenAI$2.06$8.24200K$37.08in $2.06 · out $8.24 · ctx 200K · run $37.08
- o4 Mini Deep ResearchOpenAI$2.06$8.24200K$37.08in $2.06 · out $8.24 · ctx 200K · run $37.08
- Sonar Deep ResearchPerplexity$2.06$8.24128K$37.08in $2.06 · out $8.24 · ctx 128K · run $37.08
- Sonar Reasoning ProPerplexity$2.06$8.24128K$37.08in $2.06 · out $8.24 · ctx 128K · run $37.08
- GPT-3.5 Turbo 16kOpenAI$3.09$4.1216K$39.14in $3.09 · out $4.12 · ctx 16K · run $39.14
- Anthropic Claude Sonnet LatestAnthropic$2.06$10.301M$41.20in $2.06 · out $10.30 · ctx 1M · run $41.20
- Claude Sonnet 5Anthropic$2.06$10.301M$41.20in $2.06 · out $10.30 · ctx 1M · run $41.20
Magnum v4 72BAnthracite$3.09$5.1533K$41.20in $3.09 · out $5.15 · ctx 33K · run $41.20- Gemini 3.1 Pro PreviewGoogle$2.06$12.361.0M$45.32in $2.06 · out $12.36 · ctx 1.0M · run $45.32
- Gemini 3.1 Pro Preview Custom ToolsGoogle$2.06$12.361.0M$45.32in $2.06 · out $12.36 · ctx 1.0M · run $45.32
- Google Gemini Pro LatestGoogle$2.06$12.361.0M$45.32in $2.06 · out $12.36 · ctx 1.0M · run $45.32
- Nano Banana Pro (Gemini 3 Pro Image Preview)Google$2.06$12.3666K$45.32in $2.06 · out $12.36 · ctx 66K · run $45.32
- Nano Banana Pro (Gemini 3 Pro Image)Google$2.06$12.3666K$45.32in $2.06 · out $12.36 · ctx 66K · run $45.32
- Command ACohere$2.58$10.30256K$46.35in $2.58 · out $10.30 · ctx 256K · run $46.35
- Command R+ (08-2024)Cohere$2.58$10.30128K$46.35in $2.58 · out $10.30 · ctx 128K · run $46.35
- GPT AudioOpenAI$2.58$10.30128K$46.35in $2.58 · out $10.30 · ctx 128K · run $46.35
- GPT-4oOpenAI$2.58$10.30128K$46.35in $2.58 · out $10.30 · ctx 128K · run $46.35
- GPT-4o (2024-08-06)OpenAI$2.58$10.30128K$46.35in $2.58 · out $10.30 · ctx 128K · run $46.35
- GPT-4o (2024-11-20)OpenAI$2.58$10.30128K$46.35in $2.58 · out $10.30 · ctx 128K · run $46.35
- GPT-4o Search PreviewOpenAI$2.58$10.30128K$46.35in $2.58 · out $10.30 · ctx 128K · run $46.35
Inflection 3 PiInflection AI$2.58$10.308K$46.35in $2.58 · out $10.30 · ctx 8K · run $46.35- Inflection 3 ProductivityInflection AI$2.58$10.308K$46.35in $2.58 · out $10.30 · ctx 8K · run $46.35
- GPT-5.2OpenAI$1.80$14.42400K$46.86in $1.80 · out $14.42 · ctx 400K · run $46.86
- GPT-5.2 ChatOpenAI$1.80$14.42128K$46.86in $1.80 · out $14.42 · ctx 128K · run $46.86
- GPT-5.2-CodexOpenAI$1.80$14.42400K$46.86in $1.80 · out $14.42 · ctx 400K · run $46.86
- GPT-5.3 ChatOpenAI$1.80$14.42128K$46.86in $1.80 · out $14.42 · ctx 128K · run $46.86
- GPT-5.3-CodexOpenAI$1.80$14.42400K$46.86in $1.80 · out $14.42 · ctx 400K · run $46.86
- Nova Premier 1.0Amazon$2.58$12.881M$51.50in $2.58 · out $12.88 · ctx 1M · run $51.50
- GPT-5.4OpenAI$2.58$15.451.1M$56.65in $2.58 · out $15.45 · ctx 1.1M · run $56.65
- Aion-1.0Aion Labs$4.12$8.24131K$57.68in $4.12 · out $8.24 · ctx 131K · run $57.68
- Claude Sonnet 4Anthropic$3.09$15.451M$61.80in $3.09 · out $15.45 · ctx 1M · run $61.80
- Claude Sonnet 4.5Anthropic$3.09$15.451M$61.80in $3.09 · out $15.45 · ctx 1M · run $61.80
- Claude Sonnet 4.6Anthropic$3.09$15.451M$61.80in $3.09 · out $15.45 · ctx 1M · run $61.80
- Sonar ProPerplexity$3.09$15.45200K$61.80in $3.09 · out $15.45 · ctx 200K · run $61.80
- Sonar Pro SearchPerplexity$3.09$15.45200K$61.80in $3.09 · out $15.45 · ctx 200K · run $61.80
- GPT-4o (2024-05-13)OpenAI$5.15$15.45128K$82.40in $5.15 · out $15.45 · ctx 128K · run $82.40
- Claude Opus 4.5Anthropic$5.15$25.75200K$103.00in $5.15 · out $25.75 · ctx 200K · run $103.00
- Claude Opus 4.6Anthropic$5.15$25.751M$103.00in $5.15 · out $25.75 · ctx 1M · run $103.00
- Claude Opus 4.7Anthropic$5.15$25.751M$103.00in $5.15 · out $25.75 · ctx 1M · run $103.00
- Claude Opus 4.8Anthropic$5.15$25.751M$103.00in $5.15 · out $25.75 · ctx 1M · run $103.00
- Claude Opus LatestAnthropic$5.15$25.751M$103.00in $5.15 · out $25.75 · ctx 1M · run $103.00
Fugu UltraSakana AI$5.15$30.901M$113.30in $5.15 · out $30.90 · ctx 1M · run $113.30- GPT Chat LatestOpenAI$5.15$30.90400K$113.30in $5.15 · out $30.90 · ctx 400K · run $113.30
- GPT-5.4 Image 2OpenAI$8.24$15.45272K$113.30in $8.24 · out $15.45 · ctx 272K · run $113.30
- GPT-5.5OpenAI$5.15$30.901.1M$113.30in $5.15 · out $30.90 · ctx 1.1M · run $113.30
- OpenAI GPT LatestOpenAI$5.15$30.901.1M$113.30in $5.15 · out $30.90 · ctx 1.1M · run $113.30
- GPT-5 ImageOpenAI$10.30$10.30400K$123.60in $10.30 · out $10.30 · ctx 400K · run $123.60
- GPT-4 TurboOpenAI$10.30$30.90128K$164.80in $10.30 · out $30.90 · ctx 128K · run $164.80
- GPT-4 Turbo PreviewOpenAI$10.30$30.90128K$164.80in $10.30 · out $30.90 · ctx 128K · run $164.80
- o3 Deep ResearchOpenAI$10.30$41.20200K$185.40in $10.30 · out $41.20 · ctx 200K · run $185.40
- Claude Fable 5Anthropic$10.30$51.501M$206.00in $10.30 · out $51.50 · ctx 1M · run $206.00
- Claude Fable LatestAnthropic$10.30$51.501M$206.00in $10.30 · out $51.50 · ctx 1M · run $206.00
- Claude Opus 4.8 (Fast)Anthropic$10.30$51.501M$206.00in $10.30 · out $51.50 · ctx 1M · run $206.00
- o1OpenAI$15.45$61.80200K$278.10in $15.45 · out $61.80 · ctx 200K · run $278.10
- Claude Opus 4Anthropic$15.45$77.25200K$309.00in $15.45 · out $77.25 · ctx 200K · run $309.00
- Claude Opus 4.1Anthropic$15.45$77.25200K$309.00in $15.45 · out $77.25 · ctx 200K · run $309.00
- o3 ProOpenAI$20.60$82.40200K$370.80in $20.60 · out $82.40 · ctx 200K · run $370.80
- GPT-5 ProOpenAI$15.45$123.60400K$401.70in $15.45 · out $123.60 · ctx 400K · run $401.70
- GPT-4OpenAI$30.90$61.808K$432.60in $30.90 · out $61.80 · ctx 8K · run $432.60
- GPT-5.2 ProOpenAI$21.63$173.04400K$562.38in $21.63 · out $173.04 · ctx 400K · run $562.38
- Claude Opus 4.7 (Fast)Anthropic$30.90$154.501M$618.00in $30.90 · out $154.50 · ctx 1M · run $618.00
- GPT-5.4 ProOpenAI$30.90$185.401.1M$679.80in $30.90 · out $185.40 · ctx 1.1M · run $679.80
- GPT-5.5 ProOpenAI$30.90$185.401.1M$679.80in $30.90 · out $185.40 · ctx 1.1M · run $679.80
- o1-proOpenAI$154.50$618.00200K$2,781in $154.50 · out $618.00 · ctx 200K · run $2,781
- Auto RouterOpenRouterVariableVariable2MVariablein Variable · out Variable · ctx 2M · run Variable
- Body Builder (beta)OpenRouterVariableVariable128KVariablein Variable · out Variable · ctx 128K · run Variable
- FusionOpenRouterVariableVariable1MVariablein Variable · out Variable · ctx 1M · run Variable
- Pareto Code RouterOpenRouterVariableVariable2MVariablein Variable · out Variable · ctx 2M · run Variable
Workload cost = input price × input millions + output price × output millions. Provider prices sourced live from the catalog; variable-priced routers are excluded from cost ranking because their price depends on the routed model.
Keep comparing
Every price here is one key away.
Switch between any of these 338 models by changing one string in an OpenAI-compatible request.