LLM API pricing comparison
Input and output price per 1M tokens for 340 models, using the cheapest provider serving each one. Rebuilt from the OpenRouter API on every deploy.
Last rebuild: August 3, 2026
Cost calculator
Enter your monthly token volume to see the 15 cheapest paid models for that workload. The 18 zero-cost models are excluded here — they have their own ranking.
Full pricing table
| Model | Lab | Input / 1M | Output / 1M | Cached input | Context | Providers |
|---|---|---|---|---|---|---|
| Nemotron 3 Ultra (free) | nvidia | Free | Free | — | 1M | 1 |
| Gemma 4 31B (free) | Free | Free | — | 262K | 1 | |
| Gemma 4 26B A4B (free) | Free | Free | — | 262K | 2 | |
| Nemotron 3 Super (free) | nvidia | Free | Free | — | 262K | 1 |
| North Mini Code (free) | cohere | Free | Free | — | 256K | 1 |
| gpt-oss-20b (free) | openai | Free | Free | — | 131K | 1 |
| Nemotron 3 Nano 30B A3B (free) | nvidia | Free | Free | — | 256K | 1 |
| Free Models Router | openrouter | Free | Free | — | 200K | 0 |
| Lyria 3 Clip Preview | Free | Free | — | 1.0M | 1 | |
| Lyria 3 Pro Preview | Free | Free | — | 1.0M | 1 | |
| Ling-3.0-flash (free) | inclusionai | Free | Free | — | 262K | 1 |
| Nemotron 3 Nano Omni (free) | nvidia | Free | Free | — | 256K | 1 |
| Nemotron 3.5 Content Safety (free) | nvidia | Free | Free | — | 128K | 1 |
| Nemotron Nano 12B 2 VL (free) | nvidia | Free | Free | — | 128K | 1 |
| Nemotron Nano 9B V2 (free) | nvidia | Free | Free | — | 128K | 1 |
| Laguna M.1 (free) | poolside | Free | Free | — | 262K | 1 |
| Laguna S 2.1 (free) | poolside | Free | Free | — | 262K | 1 |
| Laguna XS 2.1 (free) | poolside | Free | Free | — | 262K | 1 |
| Ling-2.6-flash | inclusionai | $0.010 | $0.030 | $0.0020 | 262K | 1 |
| Mistral Nemo | mistralai | $0.019 | $0.030 | — | 131K | 3 |
| Llama 3.1 8B Instruct | meta-llama | $0.020 | $0.040 | $0.025 | 131K | 5 |
| Llama 3 8B Lunaris | sao10k | $0.040 | $0.050 | — | 8K | 2 |
| MythoMax 13B | gryphe | $0.060 | $0.060 | — | 8K | 3 |
| Mistral Small 3 | mistralai | $0.050 | $0.080 | — | 33K | 1 |
| Ministral 3 3B 2512 | mistralai | $0.100 | $0.100 | $0.010 | 131K | 1 |
| Gemma 3 4B | $0.050 | $0.100 | — | 131K | 1 | |
| Granite 4.1 8B | ibm-granite | $0.050 | $0.100 | $0.050 | 131K | 1 |
| Nex-N2-Mini | nex-agi | $0.025 | $0.100 | $0.0025 | 262K | 1 |
| Qwen2.5 7B Instruct | qwen | $0.040 | $0.100 | — | 33K | 2 |
| Reka Edge | rekaai | $0.100 | $0.100 | — | 16K | 1 |
| Granite 4.0 Micro | ibm-granite | $0.017 | $0.112 | — | 131K | 1 |
| Gemma 3n 4B | $0.060 | $0.120 | — | 33K | 1 | |
| Laguna XS 2.1 | poolside | $0.060 | $0.120 | $0.030 | 262K | 1 |
| gpt-oss-20b | openai | $0.030 | $0.130 | — | 131K | 11 |
| Nova Micro 1.0 | amazon | $0.035 | $0.140 | — | 128K | 1 |
| Phi 4 | microsoft | $0.070 | $0.140 | — | 16K | 1 |
| Qwen3.5-9B | qwen | $0.100 | $0.150 | — | 262K | 5 |
| Ministral 3 8B 2512 | mistralai | $0.150 | $0.150 | $0.015 | 262K | 2 |
| Gemma 3 12B | $0.050 | $0.150 | — | 131K | 1 | |
| Command R7B (12-2024) | cohere | $0.037 | $0.150 | — | 128K | 1 |
| Gemma 3 27B | $0.080 | $0.160 | $0.040 | 262K | 5 | |
| gpt-oss-120b | openai | $0.030 | $0.170 | — | 131K | 17 |
| DeepSeek V4 Flash | deepseek | $0.090 | $0.179 | $0.028 | 1.0M | 21 |
| Llama Guard 4 12B | meta-llama | $0.180 | $0.180 | — | 1.0M | 2 |
| Qwen3 30B A3B Instruct 2507 | qwen | $0.048 | $0.193 | — | 262K | 6 |
| Nemotron 3 Nano 30B A3B | nvidia | $0.050 | $0.200 | — | 262K | 3 |
| Ministral 3 14B 2512 | mistralai | $0.200 | $0.200 | $0.020 | 262K | 1 |
| UI-TARS 7B | bytedance | $0.100 | $0.200 | $0.100 | 128K | 1 |
| Mistral Small 3.2 24B | mistralai | $0.075 | $0.200 | $0.010 | 256K | 3 |
| GPT-5 Nano | openai | $0.025 | $0.200 | $0.0050 | 400K | 2 |
| Laguna S 2.1 | poolside | $0.100 | $0.200 | $0.010 | 1.0M | 1 |
| Reka Flash 3 | rekaai | $0.100 | $0.200 | — | 66K | 1 |
| Llama 3.2 1B Instruct | meta-llama | $0.027 | $0.201 | — | 60K | 1 |
| Hy3 preview | tencent | $0.063 | $0.210 | $0.021 | 262K | 1 |
| MiMo-V2.5 | xiaomi | $0.112 | $0.224 | $0.0028 | 1.1M | 7 |
| Qwen3 14B | qwen | $0.100 | $0.240 | — | 131K | 3 |
| Nova Lite 1.0 | amazon | $0.060 | $0.240 | — | 300K | 1 |
| Qwen3.5-Flash | qwen | $0.065 | $0.260 | — | 1M | 1 |
| Qwen3 Coder 30B A3B Instruct | qwen | $0.070 | $0.270 | — | 262K | 5 |
| Qwen3 32B | qwen | $0.080 | $0.280 | — | 131K | 5 |
| Gemma 4 26B A4B | $0.070 | $0.300 | $0.050 | 262K | 9 | |
| Llama 4 Scout | meta-llama | $0.100 | $0.300 | — | 1.3M | 4 |
| Seed 1.6 Flash | bytedance-seed | $0.075 | $0.300 | — | 262K | 1 |
| Voxtral Small 24B 2507 | mistralai | $0.100 | $0.300 | $0.010 | 32K | 1 |
| gpt-oss-safeguard-20b | openai | $0.075 | $0.300 | $0.037 | 131K | 1 |
| Step 3.5 Flash | stepfun | $0.100 | $0.300 | — | 262K | 1 |
| DeepSeek V3.2 | deepseek | $0.207 | $0.311 | $0.135 | 164K | 14 |
| Llama 3.3 70B Instruct | meta-llama | $0.100 | $0.320 | — | 131K | 12 |
| Llama 3.2 3B Instruct | meta-llama | $0.050 | $0.330 | — | 131K | 2 |
| Gemma 4 31B | $0.090 | $0.340 | — | 262K | 16 | |
| Nemotron 3 Super | nvidia | $0.085 | $0.400 | — | 1M | 3 |
| GPT-4.1 Nano | openai | $0.100 | $0.400 | $0.025 | 1.0M | 2 |
| Seed-2.0-Mini | bytedance-seed | $0.100 | $0.400 | — | 262K | 1 |
| Gemini 2.5 Flash Lite | $0.100 | $0.400 | $0.010 | 1.0M | 2 | |
| Llama 3.1 70B Instruct | meta-llama | $0.400 | $0.400 | — | 131K | 3 |
| Hermes 4 70B | nousresearch | $0.130 | $0.400 | — | 131K | 1 |
| Laguna M.1 | poolside | $0.200 | $0.400 | $0.100 | 262K | 1 |
| Qwen2.5 72B Instruct | qwen | $0.360 | $0.400 | — | 33K | 2 |
| UnslopNemo 12B | thedrummer | $0.400 | $0.400 | — | 33K | 1 |
| GLM 4.7 Flash | z-ai | $0.060 | $0.400 | $0.010 | 203K | 4 |
| DeepSeek V3.2 Exp | deepseek | $0.270 | $0.410 | — | 164K | 3 |
| Qwen3 VL 32B Instruct | qwen | $0.104 | $0.416 | — | 131K | 1 |
| Qwen3 8B | qwen | $0.117 | $0.455 | — | 131K | 1 |
| Qwen3 VL 8B Instruct | qwen | $0.117 | $0.455 | — | 262K | 2 |
| Olmo 3 32B Think | allenai | $0.150 | $0.500 | — | 66K | 0 |
| Qwen3 30B A3B | qwen | $0.120 | $0.500 | — | 131K | 3 |
| Cydonia 24B V4.1 | thedrummer | $0.300 | $0.500 | $0.150 | 131K | 1 |
| Rocinante 12B | thedrummer | $0.250 | $0.500 | — | 66K | 1 |
| Qwen3 VL 30B A3B Instruct | qwen | $0.130 | $0.520 | — | 262K | 5 |
| Hy3 | tencent | $0.129 | $0.528 | $0.033 | 262K | 5 |
| Qwen3 235B A22B Instruct 2507 | qwen | $0.090 | $0.550 | — | 262K | 11 |
| Mistral Small 3.1 24B | mistralai | $0.351 | $0.555 | — | 128K | 1 |
| Hunyuan A13B Instruct | tencent | $0.140 | $0.570 | — | 131K | 1 |
| Mistral Small 4 | mistralai | $0.150 | $0.600 | $0.015 | 262K | 2 |
| Solar Pro 3 | upstage | $0.150 | $0.600 | $0.015 | 128K | 1 |
| Command R (08-2024) | cohere | $0.150 | $0.600 | — | 128K | 1 |
| KAT-Coder-Air V2.5 | kwaipilot | $0.150 | $0.600 | $0.030 | 256K | 1 |
| Saba | mistralai | $0.200 | $0.600 | $0.020 | 33K | 1 |
| GPT-4o-mini | openai | $0.150 | $0.600 | $0.075 | 128K | 2 |
| GPT-4o-mini (2024-07-18) | openai | $0.150 | $0.600 | $0.075 | 128K | 1 |
| WizardLM-2 8x22B | microsoft | $0.620 | $0.620 | — | 66K | 1 |
| GPT-5.4 Nano | openai | $0.100 | $0.625 | $0.020 | 400K | 2 |
| Ring-2.6-1T | inclusionai | $0.075 | $0.625 | $0.015 | 262K | 1 |
| Ling-2.6-1T | inclusionai | $0.075 | $0.625 | $0.015 | 262K | 1 |
| Gemma 2 27B | $0.650 | $0.650 | — | 8K | 1 | |
| ReMM SLERP 13B | undi95 | $0.450 | $0.650 | — | 6K | 2 |
| MiMo-V2.5-Pro | xiaomi | $0.348 | $0.696 | $0.0036 | 1.1M | 6 |
| Hermes 3 70B Instruct | nousresearch | $0.700 | $0.700 | — | 131K | 1 |
| Mercury 2 | inception | $0.250 | $0.750 | $0.025 | 128K | 1 |
| Weaver (alpha) | mancer | $0.500 | $0.750 | — | 8K | 1 |
| Qwen2.5 VL 72B Instruct | qwen | $0.250 | $0.750 | $0.400 | 128K | 2 |
| Llama 3.3 Euryale 70B | sao10k | $0.650 | $0.750 | — | 131K | 1 |
| Qwen3 Next 80B A3B Thinking | qwen | $0.098 | $0.780 | — | 262K | 3 |
| Qwen Plus 0728 | qwen | $0.260 | $0.780 | — | 1M | 1 |
| Qwen Plus 0728 (thinking) | qwen | $0.260 | $0.780 | — | 1M | 1 |
| Qwen-Plus | qwen | $0.260 | $0.780 | $0.052 | 1M | 1 |
| Qwen3 Next 80B A3B Instruct | qwen | $0.090 | $0.780 | $0.070 | 262K | 5 |
| Qwen3 Coder Next | qwen | $0.110 | $0.800 | $0.070 | 262K | 5 |
| Trinity Large Thinking | arcee-ai | $0.220 | $0.800 | $0.060 | 262K | 2 |
| Llama 4 Maverick | meta-llama | $0.200 | $0.800 | — | 1.0M | 5 |
| R1 Distill Llama 70B | deepseek | $0.800 | $0.800 | — | 8K | 1 |
| Skyfall 36B V2 | thedrummer | $0.550 | $0.800 | $0.250 | 33K | 1 |
| DeepSeek V3 | deepseek | $0.200 | $0.800 | — | 164K | 3 |
| Llama 3.1 Euryale 70B v2.2 | sao10k | $0.850 | $0.850 | — | 131K | 2 |
| GLM 4.5 Air | z-ai | $0.130 | $0.850 | $0.025 | 131K | 3 |
| DeepSeek V4 Pro | deepseek | $0.435 | $0.870 | $0.0036 | 1.0M | 18 |
| Qwen3 VL 235B A22B Instruct | qwen | $0.200 | $0.880 | $0.100 | 262K | 5 |
| DeepSeek V3 0324 | deepseek | $0.240 | $0.900 | $0.135 | 164K | 4 |
| MiniMax M2.5 | minimax | $0.150 | $0.900 | $0.050 | 205K | 14 |
| Codestral 2508 | mistralai | $0.300 | $0.900 | $0.030 | 256K | 1 |
| Uncensored | cognitivecomputations | $0.200 | $0.900 | — | 128K | 1 |
| GLM 4.6V | z-ai | $0.300 | $0.900 | $0.055 | 131K | 2 |
| DeepSeek V3.1 Terminus | deepseek | $0.270 | $0.950 | $0.135 | 164K | 5 |
| DeepSeek V3.1 | deepseek | $0.250 | $0.950 | $0.130 | 164K | 8 |
| MiniMax M3 | minimax | $0.240 | $0.960 | $0.060 | 1.0M | 8 |
| MiniMax M2.7 | minimax | $0.240 | $0.960 | $0.050 | 205K | 10 |
| Qwen3 Coder Flash | qwen | $0.195 | $0.975 | $0.039 | 1M | 1 |
| Nex-N2-Pro | nex-agi | $0.250 | $1.00 | $0.025 | 262K | 2 |
| Qwen3.6 35B A3B | qwen | $0.100 | $1.00 | — | 262K | 8 |
| GPT-5 Mini | openai | $0.125 | $1.00 | $0.025 | 400K | 2 |
| Qwen3.5-35B-A3B | qwen | $0.140 | $1.00 | — | 262K | 9 |
| Hermes 3 405B Instruct | nousresearch | $1.00 | $1.00 | — | 131K | 1 |
| Sonar | perplexity | $1.00 | $1.00 | — | 127K | 1 |
| Qwen2.5 Coder 32B Instruct | qwen | $0.660 | $1.00 | — | 33K | 1 |
| Qwen3 Coder 480B A35B | qwen | $0.220 | $1.00 | $0.100 | 262K | 6 |
| Qwen3 VL 30B A3B Thinking | qwen | $0.130 | $1.00 | — | 262K | 2 |
| MiniMax M2 | minimax | $0.255 | $1.02 | — | 205K | 3 |
| MiniMax-01 | minimax | $0.200 | $1.10 | — | 1.0M | 1 |
| Qwen3.6 Flash | qwen | $0.188 | $1.13 | — | 1M | 1 |
| Step 3.7 Flash | stepfun | $0.200 | $1.15 | $0.040 | 262K | 3 |
| KAT-Coder-Pro V2 | kwaipilot | $0.300 | $1.20 | $0.060 | 262K | 2 |
| Virtuoso Large | arcee-ai | $0.750 | $1.20 | — | 131K | 1 |
| LongCat 2.0 | meituan | $0.300 | $1.20 | $0.0060 | 1.0M | 1 |
| MiniMax M2-her | minimax | $0.300 | $1.20 | $0.030 | 66K | 1 |
| MiniMax M2.1 | minimax | $0.300 | $1.20 | $0.030 | 205K | 2 |
| Morph V3 Fast | morph | $0.800 | $1.20 | — | 82K | 1 |
| Claude 3 Haiku | anthropic | $0.250 | $1.25 | $0.030 | 200K | 1 |
| ERNIE 4.5 VL 424B A47B | baidu | $0.420 | $1.25 | — | 123K | 1 |
| Cogito v2.1 671B | deepcogito | $1.25 | $1.25 | — | 128K | 1 |
| Nano Banana (Gemini 2.5 Flash Image) | $0.150 | $1.25 | $0.030 | 33K | 2 | |
| Relace Apply 3 | relace | $0.850 | $1.25 | — | 256K | 1 |
| Qwen3.7 Plus | qwen | $0.320 | $1.28 | $0.064 | 1M | 1 |
| Qwen3 VL 8B Thinking | qwen | $0.117 | $1.36 | — | 131K | 1 |
| Aion-3.0-Mini | aion-labs | $0.700 | $1.40 | $0.180 | 131K | 1 |
| Qwen3 235B A22B Thinking 2507 | qwen | $0.149 | $1.50 | — | 262K | 4 |
| Gemini 3.1 Flash Lite Preview | $0.250 | $1.50 | $0.025 | 1.0M | 1 | |
| Mistral Large 3 2512 | mistralai | $0.500 | $1.50 | $0.050 | 262K | 1 |
| Gemini 3.1 Flash Lite | $0.250 | $1.50 | $0.025 | 1.0M | 2 | |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | $0.250 | $1.50 | — | 66K | 2 | |
| GPT-3.5 Turbo | openai | $0.500 | $1.50 | — | 16K | 1 |
| Perceptron Mk1 | perceptron | $0.150 | $1.50 | — | 33K | 1 |
| Qwen3 30B A3B Thinking 2507 | qwen | $0.130 | $1.56 | — | 82K | 1 |
| Qwen3.5 Plus 2026-02-15 | qwen | $0.260 | $1.56 | — | 1M | 1 |
| Qwen3.5-27B | qwen | $0.195 | $1.56 | — | 262K | 6 |
| GPT-4.1 Mini | openai | $0.400 | $1.60 | $0.100 | 1.0M | 2 |
| Aion-2.0 | aion-labs | $0.800 | $1.60 | $0.200 | 131K | 1 |
| Aion-RP 1.0 (8B) | aion-labs | $0.800 | $1.60 | — | 33K | 1 |
| GLM 4.7 | z-ai | $0.400 | $1.75 | $0.080 | 205K | 9 |
| GLM 4.6 | z-ai | $0.430 | $1.75 | $0.100 | 205K | 5 |
| Qwen3.5 Plus 2026-04-20 | qwen | $0.300 | $1.80 | — | 1M | 1 |
| GLM 4.5V | z-ai | $0.600 | $1.80 | $0.110 | 66K | 2 |
| Qwen3 235B A22B | qwen | $0.455 | $1.82 | — | 131K | 1 |
| Morph V3 Large | morph | $0.900 | $1.90 | — | 262K | 1 |
| GLM 5 | z-ai | $0.600 | $1.92 | $0.200 | 205K | 14 |
| Qwen3.6 Plus | qwen | $0.325 | $1.95 | — | 1M | 1 |
| Qwen3.6 27B | qwen | $0.280 | $1.99 | $0.150 | 262K | 9 |
| Grok Build 0.1 | x-ai | $1.00 | $2.00 | $0.200 | 256K | 1 |
| Kimi K2.5 | moonshotai | $0.375 | $2.00 | $0.095 | 262K | 10 |
| Devstral 2 2512 | mistralai | $0.400 | $2.00 | $0.040 | 262K | 1 |
| Mistral Medium 3.1 | mistralai | $0.400 | $2.00 | $0.040 | 131K | 1 |
| Seed 1.6 | bytedance-seed | $0.250 | $2.00 | — | 262K | 1 |
| Seed-2.0-Lite | bytedance-seed | $0.250 | $2.00 | — | 262K | 1 |
| Mistral Medium 3 | mistralai | $0.400 | $2.00 | $0.040 | 131K | 1 |
| GPT-3.5 Turbo (older v0613) | openai | $1.00 | $2.00 | — | 4K | 1 |
| GPT-3.5 Turbo Instruct | openai | $1.50 | $2.00 | — | 4K | 1 |
| GPT-5 Image Mini | openai | $2.50 | $2.00 | $0.250 | 400K | 1 |
| GPT-5.1-Codex-Mini | openai | $0.250 | $2.00 | $0.030 | 400K | 2 |
| Qwen3.5-122B-A10B | qwen | $0.260 | $2.08 | — | 262K | 5 |
| R1 0528 | deepseek | $0.500 | $2.15 | $0.350 | 164K | 4 |
| Nemotron 3 Ultra | nvidia | $0.500 | $2.20 | $0.100 | 512K | 4 |
| MiniMax M1 | minimax | $0.400 | $2.20 | — | 1M | 2 |
| GLM 4.5 | z-ai | $0.600 | $2.20 | $0.110 | 131K | 1 |
| Kimi K2 0711 | moonshotai | $0.570 | $2.30 | — | 131K | 1 |
| GLM 5.2 | z-ai | $0.741 | $2.33 | $0.138 | 1.0M | 29 |
| Qwen3.5 397B A17B | qwen | $0.385 | $2.34 | — | 262K | 11 |
| GPT Audio Mini | openai | $0.600 | $2.40 | — | 128K | 1 |
| Grok 4.3 | x-ai | $1.25 | $2.50 | $0.200 | 1M | 1 |
| Gemini 3.5 Flash Lite | $0.300 | $2.50 | $0.030 | 1.0M | 2 | |
| R1 | deepseek | $0.700 | $2.50 | — | 164K | 2 |
| Nova 2 Lite | amazon | $0.300 | $2.50 | — | 1M | 1 |
| Kimi K2 Thinking | moonshotai | $0.600 | $2.50 | $0.150 | 262K | 2 |
| Gemini 2.5 Flash | $0.300 | $2.50 | $0.030 | 1.0M | 2 | |
| Kimi K2 0905 | moonshotai | $0.600 | $2.50 | — | 262K | 2 |
| Grok 4.20 | x-ai | $1.25 | $2.50 | $0.200 | 2M | 1 |
| Grok 4.20 Multi-Agent | x-ai | $1.25 | $2.50 | $0.200 | 2M | 1 |
| Qwen3 VL 235B A22B Thinking | qwen | $0.260 | $2.60 | — | 131K | 2 |
| Kimi K2.6 | moonshotai | $0.600 | $2.72 | $0.109 | 262K | 21 |
| KAT-Coder-Pro V2.5 | kwaipilot | $0.740 | $2.96 | $0.150 | 256K | 1 |
| GLM 5.1 | z-ai | $0.952 | $2.99 | $0.179 | 205K | 19 |
| GPT-5.6 Luna | openai | $0.500 | $3.00 | $0.050 | 1.1M | 2 |
| Gemini 3 Flash Preview | $0.500 | $3.00 | $0.050 | 1.0M | 2 | |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) | $0.500 | $3.00 | — | 66K | 1 | |
| Nano Banana 2 (Gemini 3.1 Flash Image) | $0.500 | $3.00 | — | 131K | 2 | |
| Hermes 4 405B | nousresearch | $1.00 | $3.00 | — | 131K | 1 |
| GPT-5.6 Luna Pro | openai | $0.500 | $3.00 | $0.050 | 1.1M | 2 |
| Relace Search | relace | $1.00 | $3.00 | — | 256K | 1 |
| Nova Pro 1.0 | amazon | $0.800 | $3.20 | — | 300K | 1 |
| Qwen3 Coder Plus | qwen | $0.650 | $3.25 | $0.130 | 1M | 1 |
| Kimi K2.7 Code | moonshotai | $0.710 | $3.50 | $0.150 | 262K | 13 |
| Qwen3 Max | qwen | $0.780 | $3.90 | $0.156 | 262K | 1 |
| Qwen3 Max Thinking | qwen | $0.780 | $3.90 | — | 262K | 1 |
| GPT-3.5 Turbo 16k | openai | $3.00 | $4.00 | — | 16K | 2 |
| GLM 5 Turbo | z-ai | $1.20 | $4.00 | $0.240 | 203K | 1 |
| GLM 5V Turbo | z-ai | $1.20 | $4.00 | $0.240 | 203K | 1 |
| Inkling | thinkingmachines | $1.00 | $4.05 | $0.170 | 1.0M | 3 |
| Muse Spark 1.1 | meta | $1.25 | $4.25 | $0.150 | 1.0M | 1 |
| o3 Mini High | openai | $1.10 | $4.40 | $0.550 | 200K | 1 |
| o3 Mini | openai | $1.10 | $4.40 | $0.550 | 200K | 1 |
| o4 Mini | openai | $1.10 | $4.40 | $0.275 | 200K | 1 |
| o4 Mini High | openai | $1.10 | $4.40 | $0.275 | 200K | 1 |
| Qwen3.7 Max | qwen | $1.48 | $4.42 | $0.295 | 1M | 1 |
| GPT-5.4 Mini | openai | $0.750 | $4.50 | $0.075 | 400K | 2 |
| OpenAI GPT Mini Latest | openai | $0.750 | $4.50 | $0.075 | 400K | 0 |
| Claude Haiku 4.5 | anthropic | $1.00 | $5.00 | $0.100 | 200K | 4 |
| Anthropic Claude Haiku Latest | anthropic | $1.00 | $5.00 | $0.100 | 200K | 0 |
| Magnum v4 72B | anthracite-org | $3.00 | $5.00 | — | 16K | 1 |
| Grok 4.5 | x-ai | $2.00 | $6.00 | $0.300 | 500K | 1 |
| Aion-3.0 | aion-labs | $3.00 | $6.00 | $0.750 | 131K | 1 |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | $1.00 | $6.00 | $0.200 | 66K | 1 | |
| Mistral Large | mistralai | $2.00 | $6.00 | $0.200 | 128K | 1 |
| Mistral Large 2407 | mistralai | $2.00 | $6.00 | $0.200 | 131K | 1 |
| Mixtral 8x22B Instruct | mistralai | $2.00 | $6.00 | $0.200 | 66K | 1 |
| Palmyra X5 | writer | $0.600 | $6.00 | — | 1.0M | 1 |
| Grok Latest | x-ai | $2.00 | $6.00 | $0.300 | 500K | 0 |
| Qwen3.6 Max Preview | qwen | $1.04 | $6.24 | — | 262K | 1 |
| GPT-5.6 Terra | openai | $1.25 | $7.50 | $0.125 | 1.1M | 2 |
| Gemini 3.6 Flash | $1.50 | $7.50 | $0.150 | 1.0M | 2 | |
| Mistral Medium 3.5 | mistralai | $1.50 | $7.50 | — | 262K | 1 |
| Google Gemini Flash Latest | $1.50 | $7.50 | $0.150 | 1.0M | 0 | |
| GPT-5.6 Terra Pro | openai | $1.25 | $7.50 | $0.125 | 1.1M | 2 |
| Jamba Large 1.7 | ai21 | $2.00 | $8.00 | — | 256K | 1 |
| GPT-4.1 | openai | $2.00 | $8.00 | $0.500 | 1.0M | 2 |
| o3 | openai | $2.00 | $8.00 | $0.500 | 200K | 1 |
| o4 Mini Deep Research | openai | $2.00 | $8.00 | $0.500 | 200K | 1 |
| Sonar Deep Research | perplexity | $2.00 | $8.00 | — | 128K | 1 |
| Sonar Reasoning Pro | perplexity | $2.00 | $8.00 | — | 128K | 1 |
| Gemini 3.5 Flash | $1.50 | $9.00 | $0.150 | 1.0M | 2 | |
| Claude Sonnet 5 | anthropic | $2.00 | $10.00 | $0.200 | 1M | 4 |
| GPT-5.1 | openai | $1.25 | $10.00 | $0.125 | 400K | 2 |
| GPT-5 | openai | $1.25 | $10.00 | $0.125 | 400K | 2 |
| Gemini 2.5 Pro | $1.25 | $10.00 | $0.125 | 1.0M | 2 | |
| Command A | cohere | $2.50 | $10.00 | — | 256K | 1 |
| Anthropic Claude Sonnet Latest | anthropic | $2.00 | $10.00 | $0.200 | 1M | 0 |
| Command R+ (08-2024) | cohere | $2.50 | $10.00 | — | 128K | 1 |
| Gemini 2.5 Pro Preview 05-06 | $1.25 | $10.00 | $0.125 | 1.0M | 2 | |
| Gemini 2.5 Pro Preview 06-05 | $1.25 | $10.00 | $0.125 | 1.0M | 2 | |
| GPT Audio | openai | $2.50 | $10.00 | — | 128K | 1 |
| GPT-4o | openai | $2.50 | $10.00 | $1.25 | 128K | 2 |
| GPT-4o (2024-08-06) | openai | $2.50 | $10.00 | $1.25 | 128K | 2 |
| GPT-4o (2024-11-20) | openai | $2.50 | $10.00 | $1.25 | 128K | 1 |
| GPT-5 Codex | openai | $1.25 | $10.00 | $0.125 | 400K | 1 |
| GPT-5 Image | openai | $10.00 | $10.00 | $1.25 | 400K | 1 |
| GPT-5.1 Chat | openai | $1.25 | $10.00 | $0.130 | 128K | 1 |
| GPT-5.1-Codex | openai | $1.25 | $10.00 | $0.130 | 400K | 2 |
| GPT-5.1-Codex-Max | openai | $1.25 | $10.00 | $0.125 | 400K | 2 |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | $0.200 | 1.0M | 2 | |
| Google Gemini Pro Latest | $2.00 | $12.00 | $0.200 | 1.0M | 0 | |
| Gemini 3.1 Pro Preview Custom Tools | $2.00 | $12.00 | $0.200 | 1.0M | 1 | |
| Nano Banana Pro (Gemini 3 Pro Image) | $2.00 | $12.00 | $0.200 | 131K | 2 | |
| Nova Premier 1.0 | amazon | $2.50 | $12.50 | $0.625 | 1M | 1 |
| GPT-5.2 | openai | $1.75 | $14.00 | $0.175 | 400K | 2 |
| GPT-5.2 Chat | openai | $1.75 | $14.00 | $0.175 | 128K | 2 |
| GPT-5.2-Codex | openai | $1.75 | $14.00 | $0.175 | 400K | 2 |
| GPT-5.3 Chat | openai | $1.75 | $14.00 | $0.175 | 128K | 2 |
| GPT-5.3-Codex | openai | $1.75 | $14.00 | $0.175 | 400K | 2 |
| Kimi K3 | moonshotai | $3.00 | $15.00 | $0.300 | 1.0M | 6 |
| GPT-5.4 | openai | $2.50 | $15.00 | $0.250 | 1.1M | 2 |
| Claude Sonnet 4.6 | anthropic | $3.00 | $15.00 | $0.300 | 1M | 4 |
| Claude Sonnet 4.5 | anthropic | $3.00 | $15.00 | $0.300 | 1M | 4 |
| Claude Sonnet 4 | anthropic | $3.00 | $15.00 | $0.300 | 1M | 2 |
| MoonshotAI Kimi Latest | moonshotai | $3.00 | $15.00 | $0.300 | 1.0M | 0 |
| GPT-4o (2024-05-13) | openai | $5.00 | $15.00 | — | 128K | 2 |
| GPT-5.4 Image 2 | openai | $8.00 | $15.00 | $2.00 | 272K | 1 |
| Sonar Pro | perplexity | $3.00 | $15.00 | — | 200K | 1 |
| Sonar Pro Search | perplexity | $3.00 | $15.00 | — | 200K | 1 |
| Claude Opus 5 | anthropic | $5.00 | $25.00 | $0.500 | 1M | 5 |
| Claude Opus 4.8 | anthropic | $5.00 | $25.00 | $0.500 | 1M | 4 |
| Claude Opus 4.7 | anthropic | $5.00 | $25.00 | $0.500 | 1M | 4 |
| Claude Opus 4.5 | anthropic | $5.00 | $25.00 | $0.500 | 200K | 4 |
| Claude Opus 4.6 | anthropic | $5.00 | $25.00 | $0.500 | 1M | 4 |
| Claude Opus Latest | anthropic | $5.00 | $25.00 | $0.500 | 1M | 0 |
| GPT-5.6 Sol | openai | $5.00 | $30.00 | $0.500 | 1.1M | 2 |
| GPT-5.5 | openai | $5.00 | $30.00 | $0.500 | 1.1M | 2 |
| OpenAI GPT Latest | openai | $5.00 | $30.00 | $0.500 | 1.1M | 0 |
| GPT Chat Latest | openai | $5.00 | $30.00 | $0.500 | 400K | 1 |
| GPT-4 Turbo | openai | $10.00 | $30.00 | — | 128K | 1 |
| GPT-4 Turbo Preview | openai | $10.00 | $30.00 | — | 128K | 1 |
| GPT-5.6 Sol Pro | openai | $5.00 | $30.00 | $0.500 | 1.1M | 2 |
| Fugu Ultra | sakana | $5.00 | $30.00 | $0.500 | 1M | 1 |
| o3 Deep Research | openai | $10.00 | $40.00 | $2.50 | 200K | 1 |
| Claude Fable 5 | anthropic | $10.00 | $50.00 | $1.00 | 1M | 4 |
| Claude Fable Latest | anthropic | $10.00 | $50.00 | $1.00 | 1M | 0 |
| Claude Opus 4.8 (Fast) | anthropic | $10.00 | $50.00 | $1.00 | 1M | 1 |
| Claude Opus 5 (Fast) | anthropic | $10.00 | $50.00 | $1.00 | 1M | 1 |
| GPT-4 | openai | $30.00 | $60.00 | — | 8K | 2 |
| o1 | openai | $15.00 | $60.00 | $7.50 | 200K | 1 |
| Claude Opus 4 | anthropic | $15.00 | $75.00 | $1.50 | 200K | 1 |
| Claude Opus 4.1 | anthropic | $15.00 | $75.00 | $1.50 | 200K | 4 |
| o3 Pro | openai | $20.00 | $80.00 | — | 200K | 1 |
| GPT-5.4 Pro | openai | $15.00 | $90.00 | — | 1.1M | 2 |
| GPT-5.5 Pro | openai | $15.00 | $90.00 | — | 1.1M | 1 |
| GPT-5 Pro | openai | $15.00 | $120.00 | — | 400K | 1 |
| Claude Opus 4.7 (Fast) | anthropic | $30.00 | $150.00 | $3.00 | 1M | 1 |
| GPT-5.2 Pro | openai | $21.00 | $168.00 | — | 400K | 1 |
| o1-pro | openai | $150.00 | $600.00 | — | 200K | 1 |
How to read these prices
- Per 1M tokens. A token is roughly ¾ of a word; 1M tokens is about 750,000 words in or out.
- Output costs more. Most providers charge 3–5× more for generated tokens than for prompt tokens, so a chatty system prompt is cheap and a verbose model is not.
- Cached input is the biggest lever. Where a cached-input price exists, repeated context (a system prompt, a document) bills at a fraction of the normal input rate.
- Same model, different price. Open-weight models are served by many providers at different rates and quantizations — the model page lists every provider with its own price, uptime and throughput.