Output vs input tokens: which costs more?
Need to understand the cost gap between output and input tokens? Tokens are the unit AI providers bill in, and getting the count wrong throws off every cost estimate. This page helps teams optimizing token cost get an accurate count and the cost that follows from it.
Start here: Output Token Cost Calculator
Results update automatically as you type.
Result
$0.00800 per response
~$240.00/month at 1,000 calls/day
- Output tokens
- 800 tokens
- Output rate
- $10/M
- Per response
- $0.00800
- Per month
- $240.00
- Model max output
- 128,000 tokens
Then: Prompt Cost Across All Providers
Paste your prompt. Token count is measured with an accurate tokenizer (o200k_base).
Results update automatically as you type.
Result
Llama 3.2 1B Instruct: $0.00000500 per prompt
~0 input tokens + 500 output tokens across 338 models
- Cheapest
- Llama 3.2 1B Instruct — $0.00000500
- Most expensive
- o1-pro — $0.3000
- Input tokens(estimated)
- 0
| Llama 3.2 1B Instruct | Meta | $0.0000 | $0.00000500 | $0.00000500 | $0.00500 |
| Llama 3.2 3b Instruct | Meta | $0.0000 | $0.0000100 | $0.0000100 | $0.0100 |
| Llama 3.1 8b Instruct | Meta | $0.0000 | $0.0000200 | $0.0000200 | $0.0200 |
| Ministral 3B | Mistral AI | $0.0000 | $0.0000200 | $0.0000200 | $0.0200 |
| Llama 3.2 11B Vision Instruct | Meta | $0.0000 | $0.0000275 | $0.0000275 | $0.0275 |
| gemma-3-4b-it | $0.0000 | $0.0000400 | $0.0000400 | $0.0400 | |
| Gemma 3 4B IT (Bedrock) | AWS Bedrock | $0.0000 | $0.0000400 | $0.0000400 | $0.0400 |
| Gemma 4 E2B IT (Bedrock) | AWS Bedrock | $0.0000 | $0.0000400 | $0.0000400 | $0.0400 |
| Gemma 3 12B IT | $0.0000 | $0.0000500 | $0.0000500 | $0.0500 | |
| Ministral 3 3B (Bedrock) | AWS Bedrock | $0.0000 | $0.0000500 | $0.0000500 | $0.0500 |
| GPT OSS 20B | OpenAI | $0.0000 | $0.0000500 | $0.0000500 | $0.0500 |
| Mistral 7B Instruct v0.3 | Mistral AI | $0.0000 | $0.0000550 | $0.0000550 | $0.0550 |
| Qwen3.7 Flash | Alibaba | $0.0000 | $0.0000564 | $0.0000564 | $0.0564 |
| DeepSeek R1 Distill Llama 70B | DeepSeek | $0.0000 | $0.0000650 | $0.0000650 | $0.0650 |
| Amazon Nova Micro | AWS Bedrock | $0.0000 | $0.0000700 | $0.0000700 | $0.0700 |
| Phi 4 | Microsoft | $0.0000 | $0.0000700 | $0.0000700 | $0.0700 |
| GPT OSS 120B | OpenAI | $0.0000 | $0.0000700 | $0.0000700 | $0.0700 |
| nova-micro-v1 (Bedrock) | AWS Bedrock | $0.0000 | $0.0000700 | $0.0000700 | $0.0700 |
| Command R7B | Cohere | $0.0000 | $0.0000750 | $0.0000750 | $0.0750 |
| Ministral 3 8B (Bedrock) | AWS Bedrock | $0.0000 | $0.0000750 | $0.0000750 | $0.0750 |
| Mistral Nemo | Mistral AI | $0.0000 | $0.0000750 | $0.0000750 | $0.0750 |
| Open Mistral Nemo | Mistral AI | $0.0000 | $0.0000750 | $0.0000750 | $0.0750 |
| Pixtral 12B | Mistral AI | $0.0000 | $0.0000750 | $0.0000750 | $0.0750 |
| Qwen3.5 9B | Alibaba | $0.0000 | $0.0000750 | $0.0000750 | $0.0750 |
| Gemma 3 27B IT | $0.0000 | $0.0000800 | $0.0000800 | $0.0800 | |
| Nemotron 3 Nano 30B A3B | Nvidia | $0.0000 | $0.000100 | $0.000100 | $0.1000 |
| Ministral 14B 3.0 (Bedrock) | AWS Bedrock | $0.0000 | $0.000100 | $0.000100 | $0.1000 |
| Qwen Turbo | Alibaba | $0.0000 | $0.000100 | $0.000100 | $0.1000 |
| Muse Spark 1.2 Contributor | Meta | $0.0000 | $0.000100 | $0.000100 | $0.1000 |
| Muse Spark 1.3 Contributor | Meta | $0.0000 | $0.000100 | $0.000100 | $0.1000 |
| Nemotron 3.5 Lightning 30B | Nvidia | $0.0000 | $0.000100 | $0.000100 | $0.1000 |
| nvidia-nemotron-3-nano-30b-a3b | Nvidia | $0.0000 | $0.000100 | $0.000100 | $0.1000 |
| Qwen2.5-Coder 32B Instruct | Alibaba | $0.0000 | $0.000100 | $0.000100 | $0.1000 |
| gemma-4-26b-a4b-it | $0.0000 | $0.000110 | $0.000110 | $0.1100 | |
| NVIDIA Nemotron Nano 9B v2 (Bedrock) | AWS Bedrock | $0.0000 | $0.000115 | $0.000115 | $0.1150 |
| nova-lite-v1 (Bedrock) | AWS Bedrock | $0.0000 | $0.000119 | $0.000119 | $0.1190 |
| Amazon Nova Lite | AWS Bedrock | $0.0000 | $0.000120 | $0.000120 | $0.1200 |
| NVIDIA Nemotron Nano 3 30B (Bedrock) | AWS Bedrock | $0.0000 | $0.000120 | $0.000120 | $0.1200 |
| Mistral 7B | Mistral AI | $0.0000 | $0.000125 | $0.000125 | $0.1250 |
| GLM-5.3-Flash | Z.ai (Zhipu AI) | $0.0000 | $0.000125 | $0.000125 | $0.1250 |
| gemma-4-31b-it | $0.0000 | $0.000125 | $0.000125 | $0.1250 | |
| Mistral Small 3.2 24B Instruct | Mistral AI | $0.0000 | $0.000125 | $0.000125 | $0.1250 |
| Qwen-Omni Turbo | Alibaba | $0.0000 | $0.000135 | $0.000135 | $0.1350 |
| MiMo-V2.5 | Xiaomi | $0.0000 | $0.000140 | $0.000140 | $0.1400 |
| DeepSeek Chat | DeepSeek | $0.0000 | $0.000140 | $0.000140 | $0.1400 |
| DeepSeek Reasoner | DeepSeek | $0.0000 | $0.000140 | $0.000140 | $0.1400 |
| MiMo-V2-Flash | Xiaomi | $0.0000 | $0.000140 | $0.000140 | $0.1400 |
| MiMo-V2-Omni | Xiaomi | $0.0000 | $0.000140 | $0.000140 | $0.1400 |
| Qwen3.5 Flash | Alibaba | $0.0000 | $0.000143 | $0.000143 | $0.1435 |
| Google Gemma 3 12B (Bedrock) | AWS Bedrock | $0.0000 | $0.000145 | $0.000145 | $0.1450 |
| Qwen3 30B A3B | Alibaba | $0.0000 | $0.000145 | $0.000145 | $0.1450 |
| Hy-MT2 Plus | Tencent | $0.0000 | $0.000148 | $0.000148 | $0.1475 |
| Gemini 2.0 Flash-Lite | $0.0000 | $0.000150 | $0.000150 | $0.1500 | |
| gpt-oss-20b (Bedrock) | AWS Bedrock | $0.0000 | $0.000150 | $0.000150 | $0.1500 |
| Step 3.5 Flash | StepFun | $0.0000 | $0.000150 | $0.000150 | $0.1500 |
| DeepSeek R1 Distill Qwen 32B | DeepSeek | $0.0000 | $0.000150 | $0.000150 | $0.1500 |
| Llama 4 Scout 17B 16E Instruct | Meta | $0.0000 | $0.000150 | $0.000150 | $0.1500 |
| Mistral Small 3.1 24B Instruct | Mistral AI | $0.0000 | $0.000150 | $0.000150 | $0.1500 |
| Llama-3.3-70B-Instruct | Meta | $0.0000 | $0.000160 | $0.000160 | $0.1600 |
| Qwen3 30B A3b fp8 | Alibaba | $0.0000 | $0.000168 | $0.000168 | $0.1675 |
| Llama 4 Scout | Meta | $0.0000 | $0.000170 | $0.000170 | $0.1700 |
| Qwen3.8 27B | Alibaba | $0.0000 | $0.000175 | $0.000175 | $0.1750 |
| Google Gemma 3 27B Instruct (Bedrock) | AWS Bedrock | $0.0000 | $0.000190 | $0.000190 | $0.1900 |
| GPT-4.1 Nano | OpenAI | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| Gemini 2.5 Flash-Lite | $0.0000 | $0.000200 | $0.000200 | $0.2000 | |
| Gemini 2.0 Flash | $0.0000 | $0.000200 | $0.000200 | $0.2000 | |
| GLM-4.7-Flash | Z.ai (Zhipu AI) | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| GLM-4.7-Flash (Bedrock) | AWS Bedrock | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| GLM-4.7-FlashX | Z.ai (Zhipu AI) | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| GPT-5 Nano | OpenAI | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| Qwen Flash | Alibaba | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| Qwen2.5-Omni 7B | Alibaba | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| Gemma 4 26B A4B IT (Bedrock) | AWS Bedrock | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| Gemma 4 31B IT (Bedrock) | AWS Bedrock | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| deepseek-v4-1-flash | DeepSeek | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| Llama 3.1 70B Instruct | Meta | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| QwQ 32B | Alibaba | $0.0000 | $0.000200 | $0.000200 | $0.2000 |
| Qwen 2.5 72B Instruct | Alibaba | $0.0000 | $0.000204 | $0.000204 | $0.2040 |
| Qwen3 VL 32B Instruct | Alibaba | $0.0000 | $0.000208 | $0.000208 | $0.2080 |
| DeepSeek V3.2 | DeepSeek | $0.0000 | $0.000210 | $0.000210 | $0.2100 |
| Nemotron 3 Super 120B A12B | Nvidia | $0.0000 | $0.000228 | $0.000228 | $0.2275 |
| Qwen3.8 Flash | Alibaba | $0.0000 | $0.000235 | $0.000235 | $0.2350 |
| Qwen3.8 Omni Flash | Alibaba | $0.0000 | $0.000235 | $0.000235 | $0.2350 |
| MiniMax M2.1 Lightning | MiniMax | $0.0000 | $0.000240 | $0.000240 | $0.2400 |
| Qwen-MT Turbo | Alibaba | $0.0000 | $0.000245 | $0.000245 | $0.2450 |
| WizardLM-2 8x22B | Microsoft | $0.0000 | $0.000247 | $0.000247 | $0.2465 |
| Qwen3 Coder | Alibaba | $0.0000 | $0.000250 | $0.000250 | $0.2500 |
| Qwen3 VL 8B Instruct | Alibaba | $0.0000 | $0.000250 | $0.000250 | $0.2500 |
| Qwen3 VL 30B A3B Instruct | Alibaba | $0.0000 | $0.000260 | $0.000260 | $0.2600 |
| Hunyuan A13B Instruct | Tencent | $0.0000 | $0.000285 | $0.000285 | $0.2850 |
| Mistral Saba | Mistral AI | $0.0000 | $0.000297 | $0.000297 | $0.2975 |
| GPT-4o mini | OpenAI | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| Llama 3.3 70B | Meta | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| Mistral Small 4 | Mistral AI | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| DeepSeek V4 Flash | DeepSeek | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| Command R | Cohere | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| NVIDIA Nemotron Nano 12B v2 VL BF16 (Bedrock) | AWS Bedrock | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| gpt-oss-120b (Bedrock) | AWS Bedrock | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| DeepSeek V4.1 Flash | DeepSeek | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| Qwen-VL Plus | Alibaba | $0.0000 | $0.000315 | $0.000315 | $0.3150 |
| NVIDIA Nemotron 3 Super 120B A12B (Bedrock) | AWS Bedrock | $0.0000 | $0.000325 | $0.000325 | $0.3250 |
| qwen3-coder-next | Alibaba | $0.0000 | $0.000338 | $0.000338 | $0.3375 |
| Mixtral 8x7B | Mistral AI | $0.0000 | $0.000350 | $0.000350 | $0.3500 |
| Qwen2.5 7B Instruct | Alibaba | $0.0000 | $0.000350 | $0.000350 | $0.3500 |
| Qwen3 8B | Alibaba | $0.0000 | $0.000350 | $0.000350 | $0.3500 |
| DeepSeek V3.1 Terminus | DeepSeek | $0.0000 | $0.000350 | $0.000350 | $0.3500 |
| DeepSeek V3.1 | DeepSeek | $0.0000 | $0.000355 | $0.000355 | $0.3550 |
| Llama 3 70B Instruct | Meta | $0.0000 | $0.000370 | $0.000370 | $0.3700 |
| meta-llama-3-3-70b-instruct | Meta | $0.0000 | $0.000395 | $0.000395 | $0.3950 |
| Hunyuan Hy3 | Tencent | $0.0000 | $0.000400 | $0.000400 | $0.4000 |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | Meta | $0.0000 | $0.000400 | $0.000400 | $0.4000 |
| Qwen3-VL 30B-A3B | Alibaba | $0.0000 | $0.000400 | $0.000400 | $0.4000 |
| DeepSeek Chat V3.1 | DeepSeek | $0.0000 | $0.000400 | $0.000400 | $0.4000 |
| Muse Glimmer 30B | Meta | $0.0000 | $0.000400 | $0.000400 | $0.4000 |
| Qwen3 235B A22B FP8 | Alibaba | $0.0000 | $0.000400 | $0.000400 | $0.4000 |
| Llama 4 Maverick | Meta | $0.0000 | $0.000425 | $0.000425 | $0.4250 |
| DeepSeek V4 Pro | DeepSeek | $0.0000 | $0.000435 | $0.000435 | $0.4350 |
| MiMo-V2.5-Pro | Xiaomi | $0.0000 | $0.000435 | $0.000435 | $0.4350 |
| MiMo-V2-Pro | Xiaomi | $0.0000 | $0.000435 | $0.000435 | $0.4350 |
| Qwen3 VL 235B A22B Instruct | Alibaba | $0.0000 | $0.000440 | $0.000440 | $0.4400 |
| Devstral 2 | Mistral AI | $0.0000 | $0.000450 | $0.000450 | $0.4500 |
| GLM-4.6V | Z.ai (Zhipu AI) | $0.0000 | $0.000450 | $0.000450 | $0.4500 |
| Sonar | Perplexity | $0.0000 | $0.000500 | $0.000500 | $0.5000 |
| DeepSeek V3 | DeepSeek | $0.0000 | $0.000500 | $0.000500 | $0.5000 |
| Qwen3 VL 30B A3B Thinking | Alibaba | $0.0000 | $0.000500 | $0.000500 | $0.5000 |
| Qwen2.5-VL 7B Instruct | Alibaba | $0.0000 | $0.000525 | $0.000525 | $0.5250 |
| GLM-4.5-Air | Z.ai (Zhipu AI) | $0.0000 | $0.000550 | $0.000550 | $0.5500 |
| Step 3.7 Flash | StepFun | $0.0000 | $0.000555 | $0.000555 | $0.5550 |
| MiniMax 01 | MiniMax | $0.0000 | $0.000561 | $0.000561 | $0.5610 |
| Qwen3.6 Flash | Alibaba | $0.0000 | $0.000563 | $0.000563 | $0.5625 |
| MiniMax-M3 | MiniMax | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| MiniMax-M2.7 | MiniMax | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| GPT-5.6 Luna | OpenAI | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| MiniMax-M2 | MiniMax | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| MiniMax M2 (Bedrock) | AWS Bedrock | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| MiniMax-M2.1 | MiniMax | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| MiniMax M2.1 (Bedrock) | AWS Bedrock | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| MiniMax-M2.5 | MiniMax | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| MiniMax M2.5 (Bedrock) | AWS Bedrock | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| Qwen Plus | Alibaba | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| Qwen3 Coder Next (Bedrock) | AWS Bedrock | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| Qwen/Qwen3-Next-80B-A3B-Instruct (Bedrock) | AWS Bedrock | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| GPT 5.6 Luna Pro | OpenAI | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| MiniMax M2-her | MiniMax | $0.0000 | $0.000600 | $0.000600 | $0.6000 |
| GPT-5.4 nano | OpenAI | $0.0000 | $0.000625 | $0.000625 | $0.6250 |
| Claude Haiku 3 | Anthropic | $0.0000 | $0.000625 | $0.000625 | $0.6250 |
| MiniMax M1 | MiniMax | $0.0000 | $0.000627 | $0.000627 | $0.6270 |
| GPT-5.6 Luna (India) (Bedrock) | AWS Bedrock | $0.0000 | $0.000660 | $0.000660 | $0.6600 |
| Grok Code Fast 1 | xAI | $0.0000 | $0.000675 | $0.000675 | $0.6750 |
| Qwen Plus Character (Japanese) | Alibaba | $0.0000 | $0.000700 | $0.000700 | $0.7000 |
| Qwen2.5 14B Instruct | Alibaba | $0.0000 | $0.000700 | $0.000700 | $0.7000 |
| Qwen3 14B | Alibaba | $0.0000 | $0.000700 | $0.000700 | $0.7000 |
| Qwen3.6 35B-A3B | Alibaba | $0.0000 | $0.000743 | $0.000743 | $0.7425 |
| Mistral Large 3 | Mistral AI | $0.0000 | $0.000750 | $0.000750 | $0.7500 |
| Mistral Large 3 (Bedrock) | AWS Bedrock | $0.0000 | $0.000750 | $0.000750 | $0.7500 |
| Gemini 3.1 Flash Lite | $0.0000 | $0.000750 | $0.000750 | $0.7500 | |
| GPT-3.5-turbo | OpenAI | $0.0000 | $0.000750 | $0.000750 | $0.7500 |
| Magistral Small | Mistral AI | $0.0000 | $0.000750 | $0.000750 | $0.7500 |
| Qwen3 Coder Flash | Alibaba | $0.0000 | $0.000750 | $0.000750 | $0.7500 |
| GPT-4.1 Mini | OpenAI | $0.0000 | $0.000800 | $0.000800 | $0.8000 |
| Qwen3-VL Plus | Alibaba | $0.0000 | $0.000800 | $0.000800 | $0.8000 |
| Qwen3-Omni Flash | Alibaba | $0.0000 | $0.000830 | $0.000830 | $0.8300 |
| DeepSeek R1 | DeepSeek | $0.0000 | $0.000850 | $0.000850 | $0.8500 |
| GLM-4.5V | Z.ai (Zhipu AI) | $0.0000 | $0.000900 | $0.000900 | $0.9000 |
| GPT-3.5 Turbo Instruct | OpenAI | $0.0000 | $0.000900 | $0.000900 | $0.9000 |
| Kimi K2 Instruct | Moonshot AI | $0.0000 | $0.000900 | $0.000900 | $0.9000 |
| GPT-5 Mini | OpenAI | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| Mistral Medium 3.1 | Mistral AI | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| GPT-5.1 Codex mini | OpenAI | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| Devstral 2 123B (Bedrock) | AWS Bedrock | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| Qwen3.5 35B-A3B | Alibaba | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| Qwen3-Next 80B-A3B Instruct | Alibaba | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| Mistral Medium 3 | Mistral AI | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| NVIDIA Nemotron 3 Ultra | Nvidia | $0.0000 | $0.00108 | $0.00108 | $1.08 |
| GLM-4.5 | Z.ai (Zhipu AI) | $0.0000 | $0.00110 | $0.00110 | $1.10 |
| GLM-4.6 | Z.ai (Zhipu AI) | $0.0000 | $0.00110 | $0.00110 | $1.10 |
| GLM-4.7 | Z.ai (Zhipu AI) | $0.0000 | $0.00110 | $0.00110 | $1.10 |
| GLM-4.7 (Bedrock) | AWS Bedrock | $0.0000 | $0.00110 | $0.00110 | $1.10 |
| MiniMax M1 80K | MiniMax | $0.0000 | $0.00110 | $0.00110 | $1.10 |
| Qwen3-Coder 30B-A3B Instruct | Alibaba | $0.0000 | $0.00113 | $0.00113 | $1.13 |
| MiniMax-M2.5-highspeed | MiniMax | $0.0000 | $0.00120 | $0.00120 | $1.20 |
| MiniMax-M2.7-highspeed | MiniMax | $0.0000 | $0.00120 | $0.00120 | $1.20 |
| Qwen3.5 27B | Alibaba | $0.0000 | $0.00120 | $0.00120 | $1.20 |
| Qwen3.5 Plus | Alibaba | $0.0000 | $0.00120 | $0.00120 | $1.20 |
| QwQ Plus | Alibaba | $0.0000 | $0.00120 | $0.00120 | $1.20 |
| Gemini 3 Flash | $0.0000 | $0.00120 | $0.00120 | $1.20 | |
| Gemini 2.5 Flash | $0.0000 | $0.00125 | $0.00125 | $1.25 | |
| Grok 4.3 | xAI | $0.0000 | $0.00125 | $0.00125 | $1.25 |
| Grok 4.3 (Bedrock) | AWS Bedrock | $0.0000 | $0.00125 | $0.00125 | $1.25 |
| Kimi K2 Thinking | Moonshot AI | $0.0000 | $0.00125 | $0.00125 | $1.25 |
| Kimi K2 Thinking (Bedrock) | AWS Bedrock | $0.0000 | $0.00125 | $0.00125 | $1.25 |
| Gemini 3.5 Flash Lite | $0.0000 | $0.00125 | $0.00125 | $1.25 | |
| Grok 4.20 | xAI | $0.0000 | $0.00125 | $0.00125 | $1.25 |
| Kimi K2 | Moonshot AI | $0.0000 | $0.00125 | $0.00125 | $1.25 |
| Nova 2 Lite (Bedrock) | AWS Bedrock | $0.0000 | $0.00125 | $0.00125 | $1.25 |
| MiMo-V2.5-Pro-UltraSpeed | Xiaomi | $0.0000 | $0.00130 | $0.00130 | $1.31 |
| Qwen/Qwen3-VL-235B-A22B-Instruct (Bedrock) | AWS Bedrock | $0.0000 | $0.00133 | $0.00133 | $1.33 |
| Qwen3-VL 235B-A22B | Alibaba | $0.0000 | $0.00140 | $0.00140 | $1.40 |
| Qwen2.5 32B Instruct | Alibaba | $0.0000 | $0.00140 | $0.00140 | $1.40 |
| Qwen3 235B-A22B | Alibaba | $0.0000 | $0.00140 | $0.00140 | $1.40 |
| Qwen3 32B | Alibaba | $0.0000 | $0.00140 | $0.00140 | $1.40 |
| Qwen3 VL 235B A22B Thinking | Alibaba | $0.0000 | $0.00143 | $0.00143 | $1.43 |
| Qwen3.6 Plus | Alibaba | $0.0000 | $0.00150 | $0.00150 | $1.50 |
| Kimi K2.5 | Moonshot AI | $0.0000 | $0.00150 | $0.00150 | $1.50 |
| Kimi K2.5 (Bedrock) | AWS Bedrock | $0.0000 | $0.00150 | $0.00150 | $1.50 |
| Qwen3.7 Plus | Alibaba | $0.0000 | $0.00150 | $0.00150 | $1.50 |
| GLM-5.1 FP8 | Z.ai (Zhipu AI) | $0.0000 | $0.00154 | $0.00154 | $1.54 |
| glm-5-2-fp8 | Z.ai (Zhipu AI) | $0.0000 | $0.00155 | $0.00155 | $1.55 |
| Nova Pro 1.0 (Bedrock) | AWS Bedrock | $0.0000 | $0.00160 | $0.00160 | $1.60 |
| Amazon Nova Pro | AWS Bedrock | $0.0000 | $0.00160 | $0.00160 | $1.60 |
| GLM-5 | Z.ai (Zhipu AI) | $0.0000 | $0.00160 | $0.00160 | $1.60 |
| GLM-5 (Bedrock) | AWS Bedrock | $0.0000 | $0.00160 | $0.00160 | $1.60 |
| Qwen-VL Max | Alibaba | $0.0000 | $0.00160 | $0.00160 | $1.60 |
| Qwen3.5 122B-A10B | Alibaba | $0.0000 | $0.00160 | $0.00160 | $1.60 |
| Nemotron 3 Ultra 550B A55B | Nvidia | $0.0000 | $0.00180 | $0.00180 | $1.80 |
| Qwen3.5 397B-A17B | Alibaba | $0.0000 | $0.00180 | $0.00180 | $1.80 |
| Qwen3.6 27B | Alibaba | $0.0000 | $0.00180 | $0.00180 | $1.80 |
| Gemini 3.6 Flash | $0.0000 | $0.00187 | $0.00187 | $1.88 | |
| Gemini 3.7 Flash | $0.0000 | $0.00187 | $0.00187 | $1.88 | |
| Gemini 3.8 Flash | $0.0000 | $0.00187 | $0.00187 | $1.88 | |
| Qwen3 Max Thinking | Alibaba | $0.0000 | $0.00195 | $0.00195 | $1.95 |
| Kimi K2.7 Code | Moonshot AI | $0.0000 | $0.00200 | $0.00200 | $2.00 |
| GLM-5-Turbo | Z.ai (Zhipu AI) | $0.0000 | $0.00200 | $0.00200 | $2.00 |
| GLM-5V-Turbo | Z.ai (Zhipu AI) | $0.0000 | $0.00200 | $0.00200 | $2.00 |
| Kimi K2.6 | Moonshot AI | $0.0000 | $0.00200 | $0.00200 | $2.00 |
| Claude 3.5 Haiku | Anthropic | $0.0000 | $0.00200 | $0.00200 | $2.00 |
| o3 Mini High | OpenAI | $0.0000 | $0.00200 | $0.00200 | $2.00 |
| Muse Spark 1.1 | Meta | $0.0000 | $0.00213 | $0.00213 | $2.13 |
| Muse Spark 1.2 | Meta | $0.0000 | $0.00213 | $0.00213 | $2.13 |
| Muse Spark 1.3 | Meta | $0.0000 | $0.00213 | $0.00213 | $2.13 |
| o4-mini | OpenAI | $0.0000 | $0.00220 | $0.00220 | $2.20 |
| GLM-5.2 | Z.ai (Zhipu AI) | $0.0000 | $0.00220 | $0.00220 | $2.20 |
| GLM-5.1 | Z.ai (Zhipu AI) | $0.0000 | $0.00220 | $0.00220 | $2.20 |
| o3-mini | OpenAI | $0.0000 | $0.00220 | $0.00220 | $2.20 |
| GLM-5.3 | Z.ai (Zhipu AI) | $0.0000 | $0.00220 | $0.00220 | $2.20 |
| GLM-5.2 | Mistral AI | $0.0000 | $0.00220 | $0.00220 | $2.20 |
| GLM-5.3 | Mistral AI | $0.0000 | $0.00220 | $0.00220 | $2.20 |
| o4 Mini High | OpenAI | $0.0000 | $0.00220 | $0.00220 | $2.20 |
| MAI-Code-1-Flash | Microsoft | $0.0000 | $0.00225 | $0.00225 | $2.25 |
| GPT-5.4 mini | OpenAI | $0.0000 | $0.00225 | $0.00225 | $2.25 |
| GLM 5.2 Fast | Z.ai (Zhipu AI) | $0.0000 | $0.00225 | $0.00225 | $2.25 |
| QVQ Max | Alibaba | $0.0000 | $0.00240 | $0.00240 | $2.40 |
| Claude Haiku 4.5 | Anthropic | $0.0000 | $0.00250 | $0.00250 | $2.50 |
| Qwen3 Coder Plus | Alibaba | $0.0000 | $0.00250 | $0.00250 | $2.50 |
| Qwen2.5 72B Instruct | Alibaba | $0.0000 | $0.00280 | $0.00280 | $2.80 |
| Qwen3.8 2.4T A95B | Alibaba | $0.0000 | $0.00298 | $0.00298 | $2.98 |
| Grok 4.5 | xAI | $0.0000 | $0.00300 | $0.00300 | $3.00 |
| Qwen3 Max | Alibaba | $0.0000 | $0.00300 | $0.00300 | $3.00 |
| GPT-5.6 Luna (Bedrock) | AWS Bedrock | $0.0000 | $0.00300 | $0.00300 | $3.00 |
| Mixtral 8x22B | Mistral AI | $0.0000 | $0.00300 | $0.00300 | $3.00 |
| Qwen3-Next 80B-A3B (Thinking) | Alibaba | $0.0000 | $0.00300 | $0.00300 | $3.00 |
| Grok 4.6 | xAI | $0.0000 | $0.00300 | $0.00300 | $3.00 |
| Qwen3.8 Max | Alibaba | $0.0000 | $0.00300 | $0.00300 | $3.00 |
| Mistral Large | Mistral AI | $0.0000 | $0.00300 | $0.00300 | $3.00 |
| Qwen Max | Alibaba | $0.0000 | $0.00320 | $0.00320 | $3.20 |
| Grok 4.6 (Bedrock) | AWS Bedrock | $0.0000 | $0.00330 | $0.00330 | $3.30 |
| Qwen-MT Plus | Alibaba | $0.0000 | $0.00369 | $0.00369 | $3.69 |
| Qwen3.7 Max | Alibaba | $0.0000 | $0.00375 | $0.00375 | $3.75 |
| Qwen3-Coder 480B-A35B Instruct | Alibaba | $0.0000 | $0.00375 | $0.00375 | $3.75 |
| mistral-medium-3-5 | Mistral AI | $0.0000 | $0.00375 | $0.00375 | $3.75 |
| Mistral Medium 3.5 128B | Mistral AI | $0.0000 | $0.00375 | $0.00375 | $3.75 |
| GPT-4.1 | OpenAI | $0.0000 | $0.00400 | $0.00400 | $4.00 |
| o3 | OpenAI | $0.0000 | $0.00400 | $0.00400 | $4.00 |
| Sonar Reasoning Pro | Perplexity | $0.0000 | $0.00400 | $0.00400 | $4.00 |
| Sonar Deep Research | Perplexity | $0.0000 | $0.00400 | $0.00400 | $4.00 |
| Kimi K2.7 Code HighSpeed | Moonshot AI | $0.0000 | $0.00400 | $0.00400 | $4.00 |
| Kimi K2 Thinking Turbo | Moonshot AI | $0.0000 | $0.00400 | $0.00400 | $4.00 |
| o4-mini-deep-research | OpenAI | $0.0000 | $0.00400 | $0.00400 | $4.00 |
| Qwen2.5-VL 72B Instruct | Alibaba | $0.0000 | $0.00420 | $0.00420 | $4.20 |
| Gemini 3.5 Flash | $0.0000 | $0.00450 | $0.00450 | $4.50 | |
| Step 1 (32K) | StepFun | $0.0000 | $0.00479 | $0.00479 | $4.80 |
| GPT-5 | OpenAI | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| GPT-4o | OpenAI | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| Claude Sonnet 5 | Anthropic | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| Claude Sonnet 5 (Bedrock) | AWS Bedrock | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| Gemini 2.5 Pro | $0.0000 | $0.00500 | $0.00500 | $5.00 | |
| Command A | Cohere | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| Command R+ | Cohere | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| GPT-5.1 | OpenAI | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| GPT-5.1 Codex | OpenAI | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| GPT-5.1 Codex Max | OpenAI | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| GPT-5-Codex | OpenAI | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| GPT 5.6 Sol Pro | OpenAI | $0.0000 | $0.00500 | $0.00500 | $5.00 |
| GPT-5.6 Terra | OpenAI | $0.0000 | $0.00600 | $0.00600 | $6.00 |
| Gemini 3.1 Pro Preview | $0.0000 | $0.00600 | $0.00600 | $6.00 | |
| GPT 5.6 Terra Pro | OpenAI | $0.0000 | $0.00600 | $0.00600 | $6.00 |
| Amazon Nova Premier | AWS Bedrock | $0.0000 | $0.00625 | $0.00625 | $6.25 |
| Claude 4 Sonnet | Anthropic | $0.0000 | $0.00650 | $0.00650 | $6.50 |
| GPT-5.6 Terra (India) (Bedrock) | AWS Bedrock | $0.0000 | $0.00660 | $0.00660 | $6.60 |
| GPT-5.2 | OpenAI | $0.0000 | $0.00700 | $0.00700 | $7.00 |
| GPT-5.2 Codex | OpenAI | $0.0000 | $0.00700 | $0.00700 | $7.00 |
| GPT-5.3 Codex | OpenAI | $0.0000 | $0.00700 | $0.00700 | $7.00 |
| GPT-5.3 Codex Spark | OpenAI | $0.0000 | $0.00700 | $0.00700 | $7.00 |
| GPT-5.4 | OpenAI | $0.0000 | $0.00750 | $0.00750 | $7.50 |
| Claude Sonnet 4.6 | Anthropic | $0.0000 | $0.00750 | $0.00750 | $7.50 |
| Sonar Pro | Perplexity | $0.0000 | $0.00750 | $0.00750 | $7.50 |
| Kimi K3 | Moonshot AI | $0.0000 | $0.00750 | $0.00750 | $7.50 |
| Claude Sonnet 4.5 (latest) | Anthropic | $0.0000 | $0.00750 | $0.00750 | $7.50 |
| GPT-5.6 Terra (Bedrock) | AWS Bedrock | $0.0000 | $0.00750 | $0.00750 | $7.50 |
| Grok 4 | xAI | $0.0000 | $0.00750 | $0.00750 | $7.50 |
| Kimi K3 Fast | Moonshot AI | $0.0000 | $0.00750 | $0.00750 | $7.50 |
| Step 2 (16K) | StepFun | $0.0000 | $0.00822 | $0.00822 | $8.22 |
| GPT-5.4 (Bedrock) | AWS Bedrock | $0.0000 | $0.00825 | $0.00825 | $8.25 |
| Anthropic Claude Sonnet 4.6 (Bedrock) | AWS Bedrock | $0.0000 | $0.00825 | $0.00825 | $8.25 |
| GPT-5.6 | OpenAI | $0.0000 | $0.0100 | $0.0100 | $10.00 |
| GPT-5.6 Sol | OpenAI | $0.0000 | $0.0100 | $0.0100 | $10.00 |
| Claude Opus 4.8 | Anthropic | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Opus 4.8 (Bedrock) | AWS Bedrock | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Opus 4.6 | Anthropic | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Opus 4.6 (Bedrock) | AWS Bedrock | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Opus 4.7 | Anthropic | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Opus 4.7 (Bedrock) | AWS Bedrock | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Opus 4.5 (latest) | Anthropic | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Opus 5 | Anthropic | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Opus 5 (Bedrock) | AWS Bedrock | $0.0000 | $0.0138 | $0.0138 | $13.75 |
| GPT-4 Turbo | OpenAI | $0.0000 | $0.0150 | $0.0150 | $15.00 |
| GPT-5.5 | OpenAI | $0.0000 | $0.0150 | $0.0150 | $15.00 |
| GPT-5.6 Sol (Bedrock) | AWS Bedrock | $0.0000 | $0.0150 | $0.0150 | $15.00 |
| GPT-5.5 (Bedrock) | AWS Bedrock | $0.0000 | $0.0165 | $0.0165 | $16.50 |
| o3-deep-research | OpenAI | $0.0000 | $0.0200 | $0.0200 | $20.00 |
| Claude Fable 5 | Anthropic | $0.0000 | $0.0250 | $0.0250 | $25.00 |
| Claude Fable 5 (Bedrock) | AWS Bedrock | $0.0000 | $0.0250 | $0.0250 | $25.00 |
| Claude Fable 5.1 | Anthropic | $0.0000 | $0.0250 | $0.0250 | $25.00 |
| GPT-6 Astra | OpenAI | $0.0000 | $0.0250 | $0.0250 | $25.00 |
| Claude Opus 5 Fast | Anthropic | $0.0000 | $0.0250 | $0.0250 | $25.00 |
| GPT 6 Astra Pro | OpenAI | $0.0000 | $0.0250 | $0.0250 | $25.00 |
| Claude Fable 5.1 (Bedrock) | AWS Bedrock | $0.0000 | $0.0275 | $0.0275 | $27.50 |
| GPT-6 Astra (Bedrock) | AWS Bedrock | $0.0000 | $0.0275 | $0.0275 | $27.50 |
| GPT-4 | OpenAI | $0.0000 | $0.0300 | $0.0300 | $30.00 |
| o1 | OpenAI | $0.0000 | $0.0300 | $0.0300 | $30.00 |
| Claude 4 Opus | Anthropic | $0.0000 | $0.0320 | $0.0320 | $32.00 |
| Claude Opus 4.1 (latest) | Anthropic | $0.0000 | $0.0375 | $0.0375 | $37.50 |
| o3-pro | OpenAI | $0.0000 | $0.0400 | $0.0400 | $40.00 |
| GPT-5 Pro | OpenAI | $0.0000 | $0.0600 | $0.0600 | $60.00 |
| GPT-5.2 Pro | OpenAI | $0.0000 | $0.0840 | $0.0840 | $84.00 |
| GPT-5.4 Pro | OpenAI | $0.0000 | $0.0900 | $0.0900 | $90.00 |
| GPT-5.5 Pro | OpenAI | $0.0000 | $0.0900 | $0.0900 | $90.00 |
| o1-pro | OpenAI | $0.0000 | $0.3000 | $0.3000 | $300.00 |
Why this isn't trivial
The part people underestimate: most models price output several times higher than input, so output length often matters more than prompt length. In practice the biggest savings come from capping output length where possible, so it is worth modelling before you commit.
How it's calculated
We estimate this by comparing the input and output token cost for a typical request at model rates. Every figure uses the current provider prices baked into the site (reviewed daily), and you can override any input to match your own assumptions.
Frequently asked questions
Why is output pricier?+
Generating tokens is more compute-intensive, so providers charge more for output.
What does this change?+
Trimming answers often saves more than trimming prompts.
Are these prices up to date?+
Yes. The model prices behind this calculator are refreshed and reviewed daily, so your estimate reflects current provider rates rather than a stale snapshot.
Related
Which model is cheapest for high-output generation?
Find the cheapest model when your workload generates lots of output tokens.
How much does output length change my cost?
See how capping or extending output length changes your per-request cost.
How many tokens is my text?
Count the exact tokens in any text and see what it costs at each model's rate.
How do I convert words to tokens (and cost)?
Convert a word count to tokens and estimate the cost across models.
Calculator
Output Token Cost Calculator
Calculator
Prompt Cost Across All Providers
Estimates for planning. Pricing data last reviewed 18 September 2026.