LLM Pricing Comparison
Compare input, output and cached prices across models.
Result
LLM pricing compared
43 models, per 1M tokens
| Model | Provider | Input/1M | Output/1M | Cached/1M |
|---|---|---|---|---|
| Amazon Nova Micro | aws-bedrock | $0.0350 | $0.1400 | — |
| Command R7B | cohere | $0.0375 | $0.1500 | — |
| Amazon Nova Lite | aws-bedrock | $0.0600 | $0.2400 | — |
| DeepSeek V4 Flash | deepseek | $0.1400 | $0.2800 | $0.00280 |
| Llama 4 Scout | meta | $0.1100 | $0.3400 | — |
| GPT-4.1 Nano | openai | $0.1000 | $0.4000 | $0.0250 |
| Gemini 2.5 Flash-Lite | $0.1000 | $0.4000 | $0.0100 | |
| DeepSeek V3.2 | deepseek | $0.2800 | $0.4200 | $0.0300 |
| GPT-4o mini | openai | $0.1500 | $0.6000 | $0.0750 |
| Mistral Small 4 | mistral | $0.1500 | $0.6000 | — |
| Command R | cohere | $0.1500 | $0.6000 | — |
| Llama 4 Maverick | meta | $0.2200 | $0.8500 | — |
| Llama 3.3 70B | meta | $0.6000 | $0.6000 | — |
| Devstral 2 | mistral | $0.4000 | $0.9000 | — |
| DeepSeek V4 Pro | deepseek | $0.4350 | $0.8700 | $0.00363 |
| GPT-4.1 Mini | openai | $0.4000 | $1.60 | $0.1000 |
| Mistral Large 3 | mistral | $0.5000 | $1.50 | — |
| Sonar | perplexity | $1.00 | $1.00 | — |
| GPT-5 Mini | openai | $0.2500 | $2.00 | $0.0250 |
| Mistral Medium 3.1 | mistral | $0.4000 | $2.00 | — |
| Gemini 2.5 Flash | $0.3000 | $2.50 | $0.0300 | |
| Grok 4.3 | xai | $1.25 | $2.50 | $0.2000 |
| Amazon Nova Pro | aws-bedrock | $0.8000 | $3.20 | — |
| o4-mini | openai | $1.10 | $4.40 | $0.2750 |
| Claude Haiku 4.5 | anthropic | $1.00 | $5.00 | $0.1000 |
| Grok 4.5 | xai | $2.00 | $6.00 | — |
| GPT-4.1 | openai | $2.00 | $8.00 | $0.5000 |
| o3 | openai | $2.00 | $8.00 | $0.5000 |
| Sonar Reasoning Pro | perplexity | $2.00 | $8.00 | — |
| Sonar Deep Research | perplexity | $2.00 | $8.00 | — |
| GPT-5 | openai | $1.25 | $10.00 | $0.1250 |
| Gemini 2.5 Pro | $1.25 | $10.00 | $0.1250 | |
| Claude Sonnet 5 | anthropic | $2.00 | $10.00 | $0.2000 |
| GPT-4o | openai | $2.50 | $10.00 | $1.25 |
| Command A | cohere | $2.50 | $10.00 | — |
| Command R+ | cohere | $2.50 | $10.00 | — |
| Amazon Nova Premier | aws-bedrock | $2.50 | $12.50 | — |
| GPT-5.4 | openai | $2.50 | $15.00 | $0.2500 |
| Claude Sonnet 4.6 | anthropic | $3.00 | $15.00 | $0.3000 |
| Sonar Pro | perplexity | $3.00 | $15.00 | — |
| Claude Opus 4.8 | anthropic | $5.00 | $25.00 | $0.5000 |
| Claude Opus 4.6 | anthropic | $5.00 | $25.00 | $0.5000 |
| Claude Fable 5 | anthropic | $10.00 | $50.00 | $1.00 |
Compare the input, output and cached-input prices of every model in one ranked table, cheapest first, to find the best value for your workload.
How this is calculated
This calculator uses the comparisons formulas described in our methodology. All figures are estimates for planning; verify current pricing with each provider before relying on them.
Worked example (defaults)
With the default inputs above, here is the result:
Result
LLM pricing compared
43 models, per 1M tokens
| Model | Provider | Input/1M | Output/1M | Cached/1M |
|---|---|---|---|---|
| Amazon Nova Micro | aws-bedrock | $0.0350 | $0.1400 | — |
| Command R7B | cohere | $0.0375 | $0.1500 | — |
| Amazon Nova Lite | aws-bedrock | $0.0600 | $0.2400 | — |
| DeepSeek V4 Flash | deepseek | $0.1400 | $0.2800 | $0.00280 |
| Llama 4 Scout | meta | $0.1100 | $0.3400 | — |
| GPT-4.1 Nano | openai | $0.1000 | $0.4000 | $0.0250 |
| Gemini 2.5 Flash-Lite | $0.1000 | $0.4000 | $0.0100 | |
| DeepSeek V3.2 | deepseek | $0.2800 | $0.4200 | $0.0300 |
| GPT-4o mini | openai | $0.1500 | $0.6000 | $0.0750 |
| Mistral Small 4 | mistral | $0.1500 | $0.6000 | — |
| Command R | cohere | $0.1500 | $0.6000 | — |
| Llama 4 Maverick | meta | $0.2200 | $0.8500 | — |
| Llama 3.3 70B | meta | $0.6000 | $0.6000 | — |
| Devstral 2 | mistral | $0.4000 | $0.9000 | — |
| DeepSeek V4 Pro | deepseek | $0.4350 | $0.8700 | $0.00363 |
| GPT-4.1 Mini | openai | $0.4000 | $1.60 | $0.1000 |
| Mistral Large 3 | mistral | $0.5000 | $1.50 | — |
| Sonar | perplexity | $1.00 | $1.00 | — |
| GPT-5 Mini | openai | $0.2500 | $2.00 | $0.0250 |
| Mistral Medium 3.1 | mistral | $0.4000 | $2.00 | — |
| Gemini 2.5 Flash | $0.3000 | $2.50 | $0.0300 | |
| Grok 4.3 | xai | $1.25 | $2.50 | $0.2000 |
| Amazon Nova Pro | aws-bedrock | $0.8000 | $3.20 | — |
| o4-mini | openai | $1.10 | $4.40 | $0.2750 |
| Claude Haiku 4.5 | anthropic | $1.00 | $5.00 | $0.1000 |
| Grok 4.5 | xai | $2.00 | $6.00 | — |
| GPT-4.1 | openai | $2.00 | $8.00 | $0.5000 |
| o3 | openai | $2.00 | $8.00 | $0.5000 |
| Sonar Reasoning Pro | perplexity | $2.00 | $8.00 | — |
| Sonar Deep Research | perplexity | $2.00 | $8.00 | — |
| GPT-5 | openai | $1.25 | $10.00 | $0.1250 |
| Gemini 2.5 Pro | $1.25 | $10.00 | $0.1250 | |
| Claude Sonnet 5 | anthropic | $2.00 | $10.00 | $0.2000 |
| GPT-4o | openai | $2.50 | $10.00 | $1.25 |
| Command A | cohere | $2.50 | $10.00 | — |
| Command R+ | cohere | $2.50 | $10.00 | — |
| Amazon Nova Premier | aws-bedrock | $2.50 | $12.50 | — |
| GPT-5.4 | openai | $2.50 | $15.00 | $0.2500 |
| Claude Sonnet 4.6 | anthropic | $3.00 | $15.00 | $0.3000 |
| Sonar Pro | perplexity | $3.00 | $15.00 | — |
| Claude Opus 4.8 | anthropic | $5.00 | $25.00 | $0.5000 |
| Claude Opus 4.6 | anthropic | $5.00 | $25.00 | $0.5000 |
| Claude Fable 5 | anthropic | $10.00 | $50.00 | $1.00 |
Frequently asked questions
Which LLM is cheapest per token?+
Open-weight and small models (Nova Micro, Command R7B, Gemini Flash-Lite, DeepSeek V4 Flash) are cheapest. The table ranks all models by combined input+output price.