Updated daily
LLM prices today
Input, output and blended cost per 1 million tokens for 338 models across every major provider — sorted cheapest first. Rebuilt daily from official provider pricing. Prices verified 18 September 2026. Last price change 18 September 2026.
Newest models
Llama 3.2 1B Instruct
$0.010
Llama 3.2 3b Instruct
$0.020
Llama 3.1 8b Instruct
$0.025
GPT OSS 20B
$0.040
Ministral 3B
$0.040
Qwen3.7 Flash
$0.049
gemma-3-4b-it
$0.050
Gemma 3 4B IT (Bedrock)
$0.050
Gemma 4 E2B IT (Bedrock)
$0.050
DeepSeek R1 Distill Llama 70B
$0.055
Capability:
Provider:
338 models
Click a column to sort. Click again to flip between cheapest and most expensive.
| Llama 3.2 1B Instruct | $0.010 | $0.010 | — | $0.010 | Meta | 16,000 |
| Llama 3.2 3b Instruct | $0.020 | $0.020 | — | $0.020 | Meta | 16,000 |
| Llama 3.1 8b Instruct | $0.020 | $0.040 | — | $0.025 | Meta | 131,072 |
| GPT OSS 20B | $0.020 | $0.100 | — | $0.040 | OpenAI | 131,072 |
| Ministral 3B | $0.040 | $0.040 | — | $0.040 | Mistral AI | 128,000 |
| Qwen3.7 Flash | $0.028 | $0.113 | $0.006 | $0.049 | Alibaba | 991,000 |
| gemma-3-4b-it | $0.040 | $0.080 | — | $0.050 | 128,000 | |
| Gemma 3 4B IT (Bedrock) | $0.040 | $0.080 | — | $0.050 | AWS Bedrock | 128,000 |
| Gemma 4 E2B IT (Bedrock) | $0.040 | $0.080 | — | $0.050 | AWS Bedrock | 131,072 |
| DeepSeek R1 Distill Llama 70B | $0.030 | $0.130 | — | $0.055 | DeepSeek | 128,000 |
| Llama 3.2 11B Vision Instruct | $0.055 | $0.055 | — | $0.055 | Meta | 16,000 |
| GPT OSS 120B | $0.032 | $0.140 | $0.032 | $0.059 | OpenAI | 131,072 |
| Amazon Nova Micro | $0.035 | $0.140 | $0.009 | $0.061 | AWS Bedrock | 128,000 |
| nova-micro-v1 (Bedrock) | $0.035 | $0.140 | — | $0.061 | AWS Bedrock | 128,000 |
| Gemma 3 12B IT | $0.050 | $0.100 | — | $0.063 | 131,072 | |
| Command R7B | $0.037 | $0.150 | — | $0.066 | Cohere | 128,000 |
| Qwen3.5 9B | $0.040 | $0.150 | $0.008 | $0.068 | Alibaba | 262,144 |
| gemma-4-26b-a4b-it | $0.042 | $0.220 | — | $0.086 | 262,144 | |
| Nemotron 3 Nano 30B A3B | $0.050 | $0.200 | — | $0.088 | Nvidia | 262,144 |
| Phi 4 | $0.070 | $0.140 | — | $0.088 | Microsoft | 16,384 |
| Qwen Turbo | $0.050 | $0.200 | — | $0.088 | Alibaba | 1,000,000 |
| Nemotron 3.5 Lightning 30B | $0.050 | $0.200 | $0.010 | $0.088 | Nvidia | 1,000,000 |
| nvidia-nemotron-3-nano-30b-a3b | $0.050 | $0.200 | $0.030 | $0.088 | Nvidia | 262,144 |
| Qwen3.5 Flash | $0.029 | $0.287 | $0.006 | $0.093 | Alibaba | 1,000,000 |
| Qwen2.5-Coder 32B Instruct | $0.060 | $0.200 | — | $0.095 | Alibaba | 131,072 |
| Gemma 3 27B IT | $0.080 | $0.160 | — | $0.100 | 131,072 | |
| Ministral 3 3B (Bedrock) | $0.100 | $0.100 | — | $0.100 | AWS Bedrock | 256,000 |
| NVIDIA Nemotron Nano 9B v2 (Bedrock) | $0.060 | $0.230 | — | $0.103 | AWS Bedrock | 128,000 |
| nova-lite-v1 (Bedrock) | $0.059 | $0.238 | $0.030 | $0.104 | AWS Bedrock | 300,000 |
| Amazon Nova Lite | $0.060 | $0.240 | $0.015 | $0.105 | AWS Bedrock | 300,000 |
| NVIDIA Nemotron Nano 3 30B (Bedrock) | $0.060 | $0.240 | — | $0.105 | AWS Bedrock | 128,000 |
| Mistral 7B Instruct v0.3 | $0.110 | $0.110 | — | $0.110 | Mistral AI | 65,536 |
| GLM-5.3-Flash | $0.075 | $0.250 | $0.015 | $0.119 | Z.ai (Zhipu AI) | 1,000,000 |
| Qwen-Omni Turbo | $0.070 | $0.270 | — | $0.120 | Alibaba | 32,768 |
| Qwen3 30B A3b fp8 | $0.051 | $0.335 | — | $0.122 | Alibaba | 32,768 |
| Muse Spark 1.2 Contributor | $0.100 | $0.200 | $0.002 | $0.125 | Meta | 1,048,576 |
| Muse Spark 1.3 Contributor | $0.100 | $0.200 | $0.002 | $0.125 | Meta | 1,048,576 |
| gpt-oss-20b (Bedrock) | $0.070 | $0.300 | — | $0.128 | AWS Bedrock | 128,000 |
| Hy-MT2 Plusnew | $0.074 | $0.295 | — | $0.129 | Tencent | 8,192 |
| Gemini 2.0 Flash-Lite | $0.075 | $0.300 | — | $0.131 | 1,048,576 | |
| Qwen3 30B A3B | $0.080 | $0.290 | — | $0.133 | Alibaba | 41,000 |
| Mistral Small 3.2 24B Instruct | $0.094 | $0.250 | — | $0.133 | Mistral AI | 256,000 |
| GPT-5 Nano | $0.050 | $0.400 | $0.005 | $0.138 | OpenAI | 400,000 |
| Qwen Flash | $0.050 | $0.400 | — | $0.138 | Alibaba | 1,000,000 |
| gemma-4-31b-it | $0.100 | $0.250 | $0.010 | $0.138 | 262,144 | |
| Google Gemma 3 12B (Bedrock) | $0.090 | $0.290 | — | $0.140 | AWS Bedrock | 131,072 |
| GLM-4.7-Flash | $0.060 | $0.400 | $0.010 | $0.145 | Z.ai (Zhipu AI) | 200,000 |
| Qwen3.8 27B | $0.080 | $0.350 | $0.050 | $0.147 | Alibaba | 32,768 |
| Ministral 3 8B (Bedrock) | $0.150 | $0.150 | — | $0.150 | AWS Bedrock | 128,000 |
| Mistral Nemo | $0.150 | $0.150 | — | $0.150 | Mistral AI | 128,000 |
| Open Mistral Nemo | $0.150 | $0.150 | — | $0.150 | Mistral AI | 128,000 |
| Pixtral 12B | $0.150 | $0.150 | — | $0.150 | Mistral AI | 128,000 |
| Step 3.5 Flash | $0.100 | $0.300 | $0.020 | $0.150 | StepFun | 256,000 |
| Llama 4 Scout 17B 16E Instruct | $0.100 | $0.300 | — | $0.150 | Meta | 327,680 |
| Mistral Small 3.1 24B Instruct | $0.100 | $0.300 | $0.050 | $0.150 | Mistral AI | 128,000 |
| GLM-4.7-Flash (Bedrock) | $0.070 | $0.400 | — | $0.153 | AWS Bedrock | 200,000 |
| GLM-4.7-FlashX | $0.070 | $0.400 | $0.010 | $0.153 | Z.ai (Zhipu AI) | 200,000 |
| Llama-3.3-70B-Instruct | $0.100 | $0.320 | — | $0.155 | Meta | 128,000 |
| Llama 4 Scout | $0.110 | $0.340 | — | $0.168 | Meta | 10,000,000 |
| GPT-4.1 Nano | $0.100 | $0.400 | $0.025 | $0.175 | OpenAI | 1,000,000 |
| Gemini 2.5 Flash-Lite | $0.100 | $0.400 | $0.010 | $0.175 | 1,000,000 | |
| MiMo-V2.5 | $0.140 | $0.280 | $0.003 | $0.175 | Xiaomi | 1,048,576 |
| DeepSeek Chat | $0.140 | $0.280 | $0.003 | $0.175 | DeepSeek | 1,000,000 |
| DeepSeek Reasoner | $0.140 | $0.280 | $0.003 | $0.175 | DeepSeek | 1,000,000 |
| Gemini 2.0 Flash | $0.100 | $0.400 | $0.025 | $0.175 | 1,048,576 | |
| MiMo-V2-Flash | $0.140 | $0.280 | $0.003 | $0.175 | Xiaomi | 262,144 |
| MiMo-V2-Omni | $0.140 | $0.280 | $0.003 | $0.175 | Xiaomi | 262,144 |
| Qwen2.5-Omni 7B | $0.100 | $0.400 | — | $0.175 | Alibaba | 32,768 |
| deepseek-v4-1-flash | $0.100 | $0.400 | $0.003 | $0.175 | DeepSeek | 1,000,000 |
| Qwen3 VL 32B Instruct | $0.104 | $0.416 | — | $0.182 | Alibaba | 131,072 |
| Qwen3 VL 8B Instruct | $0.080 | $0.500 | — | $0.185 | Alibaba | 131,072 |
| Gemma 4 26B A4B IT (Bedrock)new | $0.130 | $0.400 | — | $0.198 | AWS Bedrock | 262,144 |
| Ministral 14B 3.0 (Bedrock) | $0.200 | $0.200 | — | $0.200 | AWS Bedrock | 128,000 |
| Gemma 4 31B IT (Bedrock) | $0.140 | $0.400 | — | $0.205 | AWS Bedrock | 262,144 |
| MiniMax M2.1 Lightning | $0.120 | $0.480 | — | $0.210 | MiniMax | 196,608 |
| Qwen3 Coder | $0.130 | $0.500 | $0.065 | $0.223 | Alibaba | 262,000 |
| Qwen3 VL 30B A3B Instruct | $0.130 | $0.520 | — | $0.228 | Alibaba | 131,072 |
| Qwen3.8 Flash | $0.150 | $0.470 | $0.016 | $0.230 | Alibaba | 1,000,000 |
| Qwen3.8 Omni Flashnew | $0.150 | $0.470 | $0.016 | $0.230 | Alibaba | 991,808 |
| Qwen-MT Turbo | $0.160 | $0.490 | — | $0.242 | Alibaba | 16,384 |
| Hunyuan A13B Instruct | $0.140 | $0.570 | — | $0.247 | Tencent | 131,072 |
| qwen3-coder-next | $0.108 | $0.675 | $0.060 | $0.250 | Alibaba | 262,144 |
| Mistral 7B | $0.250 | $0.250 | — | $0.250 | Mistral AI | 8,000 |
| GPT-4o mini | $0.150 | $0.600 | $0.075 | $0.262 | OpenAI | 128,000 |
| Mistral Small 4 | $0.150 | $0.600 | — | $0.262 | Mistral AI | 131,000 |
| DeepSeek V4 Flash | $0.150 | $0.600 | $0.003 | $0.262 | DeepSeek | 1,000,000 |
| Command R | $0.150 | $0.600 | — | $0.262 | Cohere | 128,000 |
| gpt-oss-120b (Bedrock) | $0.150 | $0.600 | — | $0.262 | AWS Bedrock | 128,000 |
| DeepSeek V4.1 Flashnew | $0.150 | $0.600 | $0.003 | $0.262 | DeepSeek | 1,000,000 |
| Google Gemma 3 27B Instruct (Bedrock) | $0.230 | $0.380 | — | $0.268 | AWS Bedrock | 202,752 |
| Nemotron 3 Super 120B A12B | $0.210 | $0.455 | — | $0.271 | Nvidia | 262,144 |
| NVIDIA Nemotron 3 Super 120B A12B (Bedrock) | $0.150 | $0.650 | — | $0.275 | AWS Bedrock | 262,144 |
| Mistral Saba | $0.199 | $0.595 | $0.099 | $0.298 | Mistral AI | 32,768 |
| DeepSeek R1 Distill Qwen 32B | $0.300 | $0.300 | — | $0.300 | DeepSeek | 64,000 |
| NVIDIA Nemotron Nano 12B v2 VL BF16 (Bedrock) | $0.200 | $0.600 | — | $0.300 | AWS Bedrock | 128,000 |
| Qwen2.5 7B Instruct | $0.175 | $0.700 | — | $0.306 | Alibaba | 131,072 |
| Qwen3 8B | $0.180 | $0.700 | — | $0.310 | Alibaba | 131,072 |
| DeepSeek V3.2 | $0.280 | $0.420 | $0.030 | $0.315 | DeepSeek | 164,000 |
| Qwen-VL Plus | $0.210 | $0.630 | — | $0.315 | Alibaba | 131,072 |
| DeepSeek V3.1 | $0.190 | $0.710 | $0.060 | $0.320 | DeepSeek | 131,072 |
| Hunyuan Hy3 | $0.200 | $0.800 | — | $0.350 | Tencent | 262,144 |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | $0.200 | $0.800 | — | $0.350 | Meta | 128,000 |
| Qwen3-VL 30B-A3B | $0.200 | $0.800 | — | $0.350 | Alibaba | 131,072 |
| DeepSeek Chat V3.1 | $0.200 | $0.800 | $0.050 | $0.350 | DeepSeek | 164,000 |
| Muse Glimmer 30B | $0.200 | $0.800 | $0.050 | $0.350 | Meta | 131,072 |
| Qwen3 235B A22B FP8 | $0.200 | $0.800 | — | $0.350 | Alibaba | 40,960 |
| DeepSeek V3.1 Terminus | $0.250 | $0.700 | $0.125 | $0.362 | DeepSeek | 128,000 |
| Qwen 2.5 72B Instruct | $0.357 | $0.408 | $0.178 | $0.370 | Alibaba | 131,072 |
| Qwen3 VL 235B A22B Instruct | $0.200 | $0.880 | $0.110 | $0.370 | Alibaba | 262,144 |
| Llama 4 Maverick | $0.220 | $0.850 | — | $0.378 | Meta | 1,000,000 |
| MiniMax 01 | $0.139 | $1.12 | $0.070 | $0.385 | MiniMax | 1,000,192 |
| Llama 3.1 70B Instruct | $0.400 | $0.400 | — | $0.400 | Meta | 131,072 |
| Qwen3 VL 30B A3B Thinking | $0.200 | $1.00 | — | $0.400 | Alibaba | 131,072 |
| QwQ 32B | $0.400 | $0.400 | — | $0.400 | Alibaba | 32,768 |
| Qwen/Qwen3-Next-80B-A3B-Instruct (Bedrock) | $0.150 | $1.20 | — | $0.412 | AWS Bedrock | 262,000 |
| MiniMax M1 | $0.132 | $1.25 | — | $0.412 | MiniMax | 1,000,000 |
| Step 3.7 Flash | $0.185 | $1.11 | $0.037 | $0.416 | StepFun | 256,000 |
| Qwen3.6 Flash | $0.188 | $1.13 | — | $0.422 | Alibaba | 1,000,000 |
| GLM-4.5-Air | $0.200 | $1.10 | $0.030 | $0.425 | Z.ai (Zhipu AI) | 131,072 |
| DeepSeek V3 | $0.250 | $1.00 | — | $0.438 | DeepSeek | 164,000 |
| GLM-4.6V | $0.300 | $0.900 | — | $0.450 | Z.ai (Zhipu AI) | 128,000 |
| GPT-5.6 Luna | $0.200 | $1.20 | $0.020 | $0.450 | OpenAI | 1,050,000 |
| GPT 5.6 Luna Pro | $0.200 | $1.20 | $0.020 | $0.450 | OpenAI | 1,050,000 |
| GPT-5.4 nano | $0.200 | $1.25 | $0.020 | $0.463 | OpenAI | 400,000 |
| Grok Code Fast 1 | $0.180 | $1.35 | — | $0.473 | xAI | 256,000 |
| WizardLM-2 8x22B | $0.493 | $0.493 | $0.246 | $0.493 | Microsoft | 65,536 |
| GPT-5.6 Luna (India) (Bedrock) | $0.220 | $1.32 | $0.022 | $0.495 | AWS Bedrock | 1,050,000 |
| Claude Haiku 3 | $0.250 | $1.25 | $0.030 | $0.500 | Anthropic | 200,000 |
| MiniMax-M3 | $0.300 | $1.20 | $0.060 | $0.525 | MiniMax | 1,000,000 |
| MiniMax-M2.7 | $0.300 | $1.20 | $0.060 | $0.525 | MiniMax | 204,800 |
| MiniMax-M2 | $0.300 | $1.20 | — | $0.525 | MiniMax | 196,608 |
| MiniMax M2 (Bedrock) | $0.300 | $1.20 | — | $0.525 | AWS Bedrock | 204,608 |
| MiniMax-M2.1 | $0.300 | $1.20 | $0.030 | $0.525 | MiniMax | 204,800 |
| MiniMax M2.1 (Bedrock) | $0.300 | $1.20 | — | $0.525 | AWS Bedrock | 204,800 |
| MiniMax-M2.5 | $0.300 | $1.20 | $0.030 | $0.525 | MiniMax | 204,800 |
| MiniMax M2.5 (Bedrock) | $0.300 | $1.20 | — | $0.525 | AWS Bedrock | 196,608 |
| Qwen2.5-VL 7B Instruct | $0.350 | $1.05 | — | $0.525 | Alibaba | 131,072 |
| MiniMax M2-her | $0.300 | $1.20 | $0.030 | $0.525 | MiniMax | 65,536 |
| Devstral 2 | $0.400 | $0.900 | — | $0.525 | Mistral AI | 262,000 |
| DeepSeek V4 Pro | $0.435 | $0.870 | $0.004 | $0.544 | DeepSeek | 1,000,000 |
| MiMo-V2.5-Pro | $0.435 | $0.870 | $0.004 | $0.544 | Xiaomi | 1,048,576 |
| MiMo-V2-Pro | $0.435 | $0.870 | $0.004 | $0.544 | Xiaomi | 1,048,576 |
| Qwen3-VL Plus | $0.200 | $1.60 | — | $0.550 | Alibaba | 262,144 |
| Qwen3.6 35B-A3B | $0.248 | $1.49 | — | $0.557 | Alibaba | 262,144 |
| Gemini 3.1 Flash Lite | $0.250 | $1.50 | $0.025 | $0.563 | 1,048,576 | |
| Llama 3 70B Instruct | $0.510 | $0.740 | — | $0.568 | Meta | 8,192 |
| Llama 3.3 70B | $0.600 | $0.600 | — | $0.600 | Meta | 128,000 |
| Qwen3 Coder Flash | $0.300 | $1.50 | — | $0.600 | Alibaba | 1,000,000 |
| Qwen Plus | $0.400 | $1.20 | — | $0.600 | Alibaba | 1,000,000 |
| Qwen2.5 14B Instruct | $0.350 | $1.40 | — | $0.612 | Alibaba | 131,072 |
| Qwen3 14B | $0.350 | $1.40 | — | $0.612 | Alibaba | 131,072 |
| meta-llama-3-3-70b-instructnew | $0.590 | $0.790 | — | $0.640 | Meta | 131,072 |
| Qwen3 Coder Next (Bedrock) | $0.500 | $1.20 | — | $0.675 | AWS Bedrock | 131,072 |
| GPT-5 Mini | $0.250 | $2.00 | $0.025 | $0.688 | OpenAI | 128,000 |
| GPT-5.1 Codex mini | $0.250 | $2.00 | $0.025 | $0.688 | OpenAI | 400,000 |
| Qwen3.5 35B-A3B | $0.250 | $2.00 | — | $0.688 | Alibaba | 262,144 |
| Mixtral 8x7B | $0.700 | $0.700 | — | $0.700 | Mistral AI | 32,000 |
| GPT-4.1 Mini | $0.400 | $1.60 | $0.100 | $0.700 | OpenAI | 1,000,000 |
| Qwen Plus Character (Japanese) | $0.500 | $1.40 | — | $0.725 | Alibaba | 8,192 |
| DeepSeek R1 | $0.400 | $1.70 | $0.200 | $0.725 | DeepSeek | 128,000 |
| Qwen3-Omni Flash | $0.430 | $1.66 | — | $0.738 | Alibaba | 65,536 |
| Mistral Large 3 | $0.500 | $1.50 | — | $0.750 | Mistral AI | 262,000 |
| Mistral Large 3 (Bedrock) | $0.500 | $1.50 | — | $0.750 | AWS Bedrock | 256,000 |
| GPT-3.5-turbo | $0.500 | $1.50 | $0 | $0.750 | OpenAI | 16,385 |
| Magistral Small | $0.500 | $1.50 | — | $0.750 | Mistral AI | 128,000 |
| Kimi K2 Instruct | $0.400 | $1.80 | $0.200 | $0.750 | Moonshot AI | 256,000 |
| Mistral Medium 3.1 | $0.400 | $2.00 | — | $0.800 | Mistral AI | 131,000 |
| Devstral 2 123B (Bedrock) | $0.400 | $2.00 | — | $0.800 | AWS Bedrock | 256,000 |
| Mistral Medium 3 | $0.400 | $2.00 | $0.200 | $0.800 | Mistral AI | 131,072 |
| Qwen3.5 27B | $0.300 | $2.40 | — | $0.825 | Alibaba | 262,144 |
| Gemini 2.5 Flash | $0.300 | $2.50 | $0.030 | $0.850 | 1,000,000 | |
| Gemini 3.5 Flash Lite | $0.300 | $2.50 | $0.030 | $0.850 | 1,048,576 | |
| Nova 2 Lite (Bedrock) | $0.300 | $2.50 | — | $0.850 | AWS Bedrock | 1,000,000 |
| Qwen3-Next 80B-A3B Instruct | $0.500 | $2.00 | — | $0.875 | Alibaba | 131,072 |
| GLM-4.5V | $0.600 | $1.80 | — | $0.900 | Z.ai (Zhipu AI) | 64,000 |
| Qwen3.5 Plus | $0.400 | $2.40 | — | $0.900 | Alibaba | 1,000,000 |
| Qwen3-Coder 30B-A3B Instruct | $0.450 | $2.25 | — | $0.900 | Alibaba | 262,144 |
| Gemini 3 Flash | $0.400 | $2.40 | $0.040 | $0.900 | 1,048,576 | |
| NVIDIA Nemotron 3 Ultra | $0.500 | $2.15 | $0.100 | $0.912 | Nvidia | 262,144 |
| Kimi K2 | $0.400 | $2.50 | $0.400 | $0.925 | Moonshot AI | 262,144 |
| Qwen3 VL 235B A22B Thinking | $0.287 | $2.87 | $0.057 | $0.932 | Alibaba | 131,072 |
| MiniMax M1 80K | $0.550 | $2.20 | — | $0.963 | MiniMax | 1,000,000 |
| Sonar | $1.00 | $1.00 | — | $1.00 | Perplexity | 128,000 |
| GLM-4.5 | $0.600 | $2.20 | $0.110 | $1.00 | Z.ai (Zhipu AI) | 131,072 |
| GLM-4.6 | $0.600 | $2.20 | $0.110 | $1.00 | Z.ai (Zhipu AI) | 204,800 |
| GLM-4.7 | $0.600 | $2.20 | $0.110 | $1.00 | Z.ai (Zhipu AI) | 204,800 |
| GLM-4.7 (Bedrock) | $0.600 | $2.20 | — | $1.00 | AWS Bedrock | 204,800 |
| MiniMax-M2.5-highspeed | $0.600 | $2.40 | $0.060 | $1.05 | MiniMax | 204,800 |
| MiniMax-M2.7-highspeed | $0.600 | $2.40 | $0.060 | $1.05 | MiniMax | 204,800 |
| Qwen/Qwen3-VL-235B-A22B-Instruct (Bedrock) | $0.530 | $2.66 | — | $1.06 | AWS Bedrock | 262,000 |
| Kimi K2 Thinking | $0.600 | $2.50 | $0.150 | $1.08 | Moonshot AI | 262,144 |
| Kimi K2 Thinking (Bedrock) | $0.600 | $2.50 | — | $1.08 | AWS Bedrock | 262,143 |
| Qwen3.5 122B-A10B | $0.400 | $3.20 | — | $1.10 | Alibaba | 262,144 |
| Qwen3.6 Plus | $0.500 | $3.00 | $0.050 | $1.13 | Alibaba | 1,000,000 |
| Qwen3.7 Plus | $0.500 | $3.00 | $0.050 | $1.13 | Alibaba | 1,000,000 |
| Kimi K2.5 | $0.600 | $3.00 | $0.100 | $1.20 | Moonshot AI | 262,144 |
| Kimi K2.5 (Bedrock) | $0.600 | $3.00 | — | $1.20 | AWS Bedrock | 262,143 |
| QwQ Plus | $0.800 | $2.40 | — | $1.20 | Alibaba | 131,072 |
| Qwen3-VL 235B-A22B | $0.700 | $2.80 | — | $1.22 | Alibaba | 131,072 |
| Qwen2.5 32B Instruct | $0.700 | $2.80 | — | $1.22 | Alibaba | 131,072 |
| Qwen3 235B-A22B | $0.700 | $2.80 | — | $1.22 | Alibaba | 131,072 |
| Qwen3 32B | $0.700 | $2.80 | — | $1.22 | Alibaba | 131,072 |
| Nemotron 3 Ultra 550B A55B | $0.600 | $3.60 | — | $1.35 | Nvidia | 1,000,000 |
| Qwen3.5 397B-A17B | $0.600 | $3.60 | — | $1.35 | Alibaba | 262,144 |
| Qwen3.6 27B | $0.600 | $3.60 | — | $1.35 | Alibaba | 262,144 |
| Nova Pro 1.0 (Bedrock) | $0.799 | $3.20 | $0.400 | $1.40 | AWS Bedrock | 300,000 |
| Amazon Nova Pro | $0.800 | $3.20 | $0.200 | $1.40 | AWS Bedrock | 300,000 |
| Qwen-VL Max | $0.800 | $3.20 | — | $1.40 | Alibaba | 131,072 |
| glm-5-2-fp8 | $0.850 | $3.10 | — | $1.41 | Z.ai (Zhipu AI) | 393,216 |
| GPT-3.5 Turbo Instruct | $1.40 | $1.80 | — | $1.50 | OpenAI | 3,500 |
| Gemini 3.6 Flash | $0.750 | $3.75 | $0.075 | $1.50 | 1,048,576 | |
| Gemini 3.7 Flash | $0.750 | $3.75 | $0.075 | $1.50 | 1,048,576 | |
| Gemini 3.8 Flash | $0.750 | $3.75 | $0.075 | $1.50 | 1,048,576 | |
| GLM-5.1 FP8 | $0.980 | $3.08 | $0.182 | $1.51 | Z.ai (Zhipu AI) | 202,752 |
| GLM-5 | $1.00 | $3.20 | $0.200 | $1.55 | Z.ai (Zhipu AI) | 204,800 |
| GLM-5 (Bedrock) | $1.00 | $3.20 | — | $1.55 | AWS Bedrock | 202,752 |
| Qwen3 Max Thinking | $0.780 | $3.90 | — | $1.56 | Alibaba | 262,144 |
| Grok 4.3 | $1.25 | $2.50 | $0.200 | $1.56 | xAI | 1,000,000 |
| Grok 4.3 (Bedrock) | $1.25 | $2.50 | $0.200 | $1.56 | AWS Bedrock | 1,000,000 |
| Grok 4.20 | $1.25 | $2.50 | $0.200 | $1.56 | xAI | 2,000,000 |
| Claude 3.5 Haiku | $0.800 | $4.00 | $0.080 | $1.60 | Anthropic | 200,000 |
| MiMo-V2.5-Pro-UltraSpeed | $1.31 | $2.61 | $0.011 | $1.63 | Xiaomi | 1,048,576 |
| MAI-Code-1-Flash | $0.750 | $4.50 | — | $1.69 | Microsoft | 256,000 |
| GPT-5.4 mini | $0.750 | $4.50 | $0.075 | $1.69 | OpenAI | 400,000 |
| Kimi K2.7 Code | $0.950 | $4.00 | $0.190 | $1.71 | Moonshot AI | 262,144 |
| Kimi K2.6 | $0.950 | $4.00 | $0.160 | $1.71 | Moonshot AI | 262,144 |
| o3 Mini High | $0.990 | $4.00 | — | $1.74 | OpenAI | 200,000 |
| Qwen3-Next 80B-A3B (Thinking) | $0.500 | $6.00 | — | $1.88 | Alibaba | 131,072 |
| GLM-5-Turbo | $1.20 | $4.00 | $0.240 | $1.90 | Z.ai (Zhipu AI) | 200,000 |
| GLM-5V-Turbo | $1.20 | $4.00 | $0.240 | $1.90 | Z.ai (Zhipu AI) | 200,000 |
| o4-mini | $1.10 | $4.40 | $0.275 | $1.93 | OpenAI | 200,000 |
| o3-mini | $1.10 | $4.40 | $0.550 | $1.93 | OpenAI | 200,000 |
| o4 Mini High | $1.10 | $4.40 | $0.550 | $1.93 | OpenAI | 200,000 |
| Claude Haiku 4.5 | $1.00 | $5.00 | $0.100 | $2.00 | Anthropic | 200,000 |
| Muse Spark 1.1 | $1.25 | $4.25 | $0.150 | $2.00 | Meta | 1,000,000 |
| Qwen3 Coder Plus | $1.00 | $5.00 | — | $2.00 | Alibaba | 1,048,576 |
| Muse Spark 1.2 | $1.25 | $4.25 | $0.150 | $2.00 | Meta | 1,048,576 |
| Muse Spark 1.3 | $1.25 | $4.25 | $0.150 | $2.00 | Meta | 1,048,576 |
| QVQ Max | $1.20 | $4.80 | — | $2.10 | Alibaba | 131,072 |
| GLM-5.2 | $1.40 | $4.40 | $0.260 | $2.15 | Z.ai (Zhipu AI) | 1,000,000 |
| GLM-5.1 | $1.40 | $4.40 | $0.260 | $2.15 | Z.ai (Zhipu AI) | 200,000 |
| GLM-5.3 | $1.40 | $4.40 | $0.260 | $2.15 | Z.ai (Zhipu AI) | 1,000,000 |
| GLM-5.2 | $1.40 | $4.40 | $0.140 | $2.15 | Mistral AI | 1,000,000 |
| GLM-5.3new | $1.40 | $4.40 | $0.140 | $2.15 | Mistral AI | 1,000,000 |
| GLM 5.2 Fast | $1.45 | $4.50 | $0.145 | $2.21 | Z.ai (Zhipu AI) | 1,048,560 |
| GPT-5.6 Luna (Bedrock) | $1.00 | $6.00 | $0.100 | $2.25 | AWS Bedrock | 272,000 |
| Qwen3 Max | $1.20 | $6.00 | — | $2.40 | Alibaba | 262,144 |
| Qwen2.5 72B Instruct | $1.40 | $5.60 | — | $2.45 | Alibaba | 131,072 |
| Qwen Max | $1.60 | $6.40 | — | $2.80 | Alibaba | 32,768 |
| Kimi K2 Thinking Turbo | $1.15 | $8.00 | $0.150 | $2.86 | Moonshot AI | 262,144 |
| Qwen3.8 2.4T A95B | $1.95 | $5.95 | $0.200 | $2.95 | Alibaba | 970,000 |
| Grok 4.5 | $2.00 | $6.00 | $0.300 | $3.00 | xAI | 500,000 |
| Mixtral 8x22B | $2.00 | $6.00 | — | $3.00 | Mistral AI | 64,000 |
| Qwen3-Coder 480B-A35B Instruct | $1.50 | $7.50 | — | $3.00 | Alibaba | 262,144 |
| Grok 4.6 | $2.00 | $6.00 | $0.500 | $3.00 | xAI | 500,000 |
| Qwen3.8 Max | $2.00 | $6.00 | $0.250 | $3.00 | Alibaba | 1,000,000 |
| Mistral Large | $2.00 | $6.00 | $0.200 | $3.00 | Mistral AI | 128,000 |
| mistral-medium-3-5 | $1.50 | $7.50 | $0.750 | $3.00 | Mistral AI | 256,000 |
| Mistral Medium 3.5 128B | $1.50 | $7.50 | — | $3.00 | Mistral AI | 256,000 |
| Grok 4.6 (Bedrock) | $2.20 | $6.60 | $0.550 | $3.30 | AWS Bedrock | 500,000 |
| Gemini 3.5 Flash | $1.50 | $9.00 | $0.150 | $3.38 | 1,048,576 | |
| Kimi K2.7 Code HighSpeed | $1.90 | $8.00 | $0.380 | $3.43 | Moonshot AI | 262,144 |
| GPT-5 | $1.25 | $10.00 | $0.125 | $3.44 | OpenAI | 128,000 |
| Gemini 2.5 Pro | $1.25 | $10.00 | $0.125 | $3.44 | 1,048,576 | |
| GPT-5.1 | $1.25 | $10.00 | $0.125 | $3.44 | OpenAI | 400,000 |
| GPT-5.1 Codex | $1.25 | $10.00 | $0.125 | $3.44 | OpenAI | 400,000 |
| GPT-5.1 Codex Max | $1.25 | $10.00 | $0.125 | $3.44 | OpenAI | 400,000 |
| GPT-5-Codex | $1.25 | $10.00 | $0.125 | $3.44 | OpenAI | 400,000 |
| GPT-4.1 | $2.00 | $8.00 | $0.500 | $3.50 | OpenAI | 1,000,000 |
| o3 | $2.00 | $8.00 | $0.500 | $3.50 | OpenAI | 200,000 |
| Sonar Reasoning Pro | $2.00 | $8.00 | — | $3.50 | Perplexity | 128,000 |
| Sonar Deep Research | $2.00 | $8.00 | — | $3.50 | Perplexity | 128,000 |
| o4-mini-deep-research | $2.00 | $8.00 | $0.500 | $3.50 | OpenAI | 200,000 |
| Qwen-MT Plus | $2.46 | $7.37 | — | $3.69 | Alibaba | 16,384 |
| Qwen3.7 Max | $2.50 | $7.50 | $0.500 | $3.75 | Alibaba | 1,000,000 |
| Step 1 (32K) | $2.05 | $9.59 | $0.410 | $3.93 | StepFun | 32,768 |
| Claude Sonnet 5 | $2.00 | $10.00 | $0.200 | $4.00 | Anthropic | 1,000,000 |
| Claude Sonnet 5 (Bedrock) | $2.00 | $10.00 | $0.200 | $4.00 | AWS Bedrock | 1,000,000 |
| GPT 5.6 Sol Pro | $2.00 | $10.00 | $0.200 | $4.00 | OpenAI | 1,050,000 |
| Qwen2.5-VL 72B Instruct | $2.80 | $8.40 | — | $4.20 | Alibaba | 131,072 |
| GPT-4o | $2.50 | $10.00 | $1.25 | $4.38 | OpenAI | 128,000 |
| Command A | $2.50 | $10.00 | — | $4.38 | Cohere | 256,000 |
| Command R+ | $2.50 | $10.00 | — | $4.38 | Cohere | 128,000 |
| GPT-5.6 Terra | $2.00 | $12.00 | $0.200 | $4.50 | OpenAI | 1,050,000 |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | $0.200 | $4.50 | 1,048,576 | |
| GPT 5.6 Terra Pro | $2.00 | $12.00 | $0.200 | $4.50 | OpenAI | 1,050,000 |
| GPT-5.2 | $1.75 | $14.00 | $0.175 | $4.81 | OpenAI | 400,000 |
| GPT-5.2 Codex | $1.75 | $14.00 | $0.175 | $4.81 | OpenAI | 400,000 |
| GPT-5.3 Codex | $1.75 | $14.00 | $0.175 | $4.81 | OpenAI | 400,000 |
| GPT-5.3 Codex Spark | $1.75 | $14.00 | $0.175 | $4.81 | OpenAI | 128,000 |
| GPT-5.6 Terra (India) (Bedrock) | $2.20 | $13.20 | $0.220 | $4.95 | AWS Bedrock | 1,050,000 |
| Amazon Nova Premier | $2.50 | $12.50 | — | $5.00 | AWS Bedrock | 1,000,000 |
| Claude 4 Sonnet | $2.60 | $13.00 | $0.260 | $5.20 | Anthropic | 983,040 |
| GPT-5.4 | $2.50 | $15.00 | $0.250 | $5.63 | OpenAI | 1,050,000 |
| GPT-5.6 Terra (Bedrock) | $2.50 | $15.00 | $0.250 | $5.63 | AWS Bedrock | 272,000 |
| Claude Sonnet 4.6 | $3.00 | $15.00 | $0.300 | $6.00 | Anthropic | 1,000,000 |
| Sonar Pro | $3.00 | $15.00 | — | $6.00 | Perplexity | 200,000 |
| Kimi K3 | $3.00 | $15.00 | $0.300 | $6.00 | Moonshot AI | 1,048,576 |
| Claude Sonnet 4.5 (latest) | $3.00 | $15.00 | $0.300 | $6.00 | Anthropic | 1,000,000 |
| Grok 4 | $3.00 | $15.00 | $0.750 | $6.00 | xAI | 256,000 |
| Kimi K3 Fast | $3.00 | $15.00 | $0.300 | $6.00 | Moonshot AI | 1,048,560 |
| GPT-5.4 (Bedrock) | $2.75 | $16.50 | $0.275 | $6.19 | AWS Bedrock | 272,000 |
| Anthropic Claude Sonnet 4.6 (Bedrock) | $3.30 | $16.50 | $0.330 | $6.60 | AWS Bedrock | 1,000,000 |
| GPT-5.6 | $4.00 | $20.00 | $0.400 | $8.00 | OpenAI | 1,050,000 |
| GPT-5.6 Sol | $4.00 | $20.00 | $0.400 | $8.00 | OpenAI | 1,050,000 |
| Step 2 (16K) | $5.21 | $16.44 | $1.04 | $8.02 | StepFun | 16,384 |
| Claude Opus 4.8 | $5.00 | $25.00 | $0.500 | $10.00 | Anthropic | 1,000,000 |
| Claude Opus 4.8 (Bedrock) | $5.00 | $25.00 | $0.500 | $10.00 | AWS Bedrock | 1,000,000 |
| Claude Opus 4.6 | $5.00 | $25.00 | $0.500 | $10.00 | Anthropic | 1,000,000 |
| Claude Opus 4.6 (Bedrock) | $5.00 | $25.00 | $0.500 | $10.00 | AWS Bedrock | 1,000,000 |
| Claude Opus 4.7 | $5.00 | $25.00 | $0.500 | $10.00 | Anthropic | 1,000,000 |
| Claude Opus 4.7 (Bedrock) | $5.00 | $25.00 | $0.500 | $10.00 | AWS Bedrock | 1,000,000 |
| Claude Opus 4.5 (latest) | $5.00 | $25.00 | $0.500 | $10.00 | Anthropic | 200,000 |
| Claude Opus 5 | $5.00 | $25.00 | $0.500 | $10.00 | Anthropic | 1,000,000 |
| Claude Opus 5 (Bedrock) | $5.50 | $27.50 | $0.550 | $11.00 | AWS Bedrock | 1,000,000 |
| GPT-5.5 | $5.00 | $30.00 | $0.500 | $11.25 | OpenAI | 1,050,000 |
| GPT-5.6 Sol (Bedrock) | $5.00 | $30.00 | $0.500 | $11.25 | AWS Bedrock | 272,000 |
| GPT-5.5 (Bedrock) | $5.50 | $33.00 | $0.550 | $12.38 | AWS Bedrock | 272,000 |
| GPT-4 Turbo | $10.00 | $30.00 | — | $15.00 | OpenAI | 128,000 |
| o3-deep-research | $10.00 | $40.00 | $2.50 | $17.50 | OpenAI | 200,000 |
| Claude Fable 5 | $10.00 | $50.00 | $1.00 | $20.00 | Anthropic | 1,000,000 |
| Claude Fable 5 (Bedrock) | $10.00 | $50.00 | $1.00 | $20.00 | AWS Bedrock | 1,000,000 |
| Claude Fable 5.1 | $10.00 | $50.00 | $0.250 | $20.00 | Anthropic | 1,000,000 |
| GPT-6 Astra | $10.00 | $50.00 | $1.00 | $20.00 | OpenAI | 1,050,000 |
| Claude Opus 5 Fast | $10.00 | $50.00 | $1.00 | $20.00 | Anthropic | 1,000,000 |
| GPT 6 Astra Pro | $10.00 | $50.00 | $1.00 | $20.00 | OpenAI | 1,050,000 |
| Claude Fable 5.1 (Bedrock) | $11.00 | $55.00 | $0.275 | $22.00 | AWS Bedrock | 1,000,000 |
| GPT-6 Astra (Bedrock) | $11.00 | $55.00 | $1.10 | $22.00 | AWS Bedrock | 1,050,000 |
| Claude 4 Opus | $13.00 | $64.00 | $1.30 | $25.75 | Anthropic | 192,512 |
| o1 | $15.00 | $60.00 | $7.50 | $26.25 | OpenAI | 200,000 |
| Claude Opus 4.1 (latest) | $15.00 | $75.00 | $1.50 | $30.00 | Anthropic | 200,000 |
| o3-pro | $20.00 | $80.00 | — | $35.00 | OpenAI | 200,000 |
| GPT-4 | $30.00 | $60.00 | — | $37.50 | OpenAI | 8,192 |
| GPT-5 Pro | $15.00 | $120.00 | — | $41.25 | OpenAI | 400,000 |
| GPT-5.2 Pro | $21.00 | $168.00 | — | $57.75 | OpenAI | 400,000 |
| GPT-5.4 Pro | $30.00 | $180.00 | — | $67.50 | OpenAI | 1,050,000 |
| GPT-5.5 Pro | $30.00 | $180.00 | — | $67.50 | OpenAI | 1,050,000 |
| o1-pro | $150.00 | $600.00 | — | $262.50 | OpenAI | 200,000 |
How to read this table
Input is what you pay per 1M tokens you send (your prompt, system message, retrieved context and conversation history). Output is what you pay per 1M tokens the model generates — usually the more expensive side. Blended weights input and output 3:1 to give a single number for ranking; your real mix may differ.
To turn these rates into a real bill, use the LLM API cost calculator or compare models head-to-head in the model cost comparison.