Prompt Cost Across All Providers
Paste a prompt and see what it costs on every major AI model at once.
Paste your prompt. Token count is measured with an accurate tokenizer (o200k_base).
Results update automatically as you type.
Result
Amazon Nova Micro: $0.0000700 per prompt
~0 input tokens + 500 output tokens across 43 models
- Cheapest
- Amazon Nova Micro — $0.0000700
- Most expensive
- Claude Fable 5 — $0.0250
- Input tokens(estimated)
- 0
| Model | Provider | Input | Output | Total / prompt | Per 1K prompts |
|---|---|---|---|---|---|
| Amazon Nova Micro | aws-bedrock | $0.0000 | $0.0000700 | $0.0000700 | $0.0700 |
| Command R7B | cohere | $0.0000 | $0.0000750 | $0.0000750 | $0.0750 |
| Amazon Nova Lite | aws-bedrock | $0.0000 | $0.000120 | $0.000120 | $0.1200 |
| DeepSeek V4 Flash | deepseek | $0.0000 | $0.000140 | $0.000140 | $0.1400 |
| Llama 4 Scout | meta | $0.0000 | $0.000170 | $0.000170 | $0.1700 |
| 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 | |
| DeepSeek V3.2 | deepseek | $0.0000 | $0.000210 | $0.000210 | $0.2100 |
| 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 | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| Command R | cohere | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| Llama 4 Maverick | meta | $0.0000 | $0.000425 | $0.000425 | $0.4250 |
| DeepSeek V4 Pro | deepseek | $0.0000 | $0.000435 | $0.000435 | $0.4350 |
| Devstral 2 | mistral | $0.0000 | $0.000450 | $0.000450 | $0.4500 |
| Sonar | perplexity | $0.0000 | $0.000500 | $0.000500 | $0.5000 |
| Mistral Large 3 | mistral | $0.0000 | $0.000750 | $0.000750 | $0.7500 |
| GPT-4.1 Mini | openai | $0.0000 | $0.000800 | $0.000800 | $0.8000 |
| GPT-5 Mini | openai | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| Mistral Medium 3.1 | mistral | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| Gemini 2.5 Flash | $0.0000 | $0.00125 | $0.00125 | $1.25 | |
| Grok 4.3 | xai | $0.0000 | $0.00125 | $0.00125 | $1.25 |
| Amazon Nova Pro | aws-bedrock | $0.0000 | $0.00160 | $0.00160 | $1.60 |
| o4-mini | openai | $0.0000 | $0.00220 | $0.00220 | $2.20 |
| Claude Haiku 4.5 | anthropic | $0.0000 | $0.00250 | $0.00250 | $2.50 |
| Grok 4.5 | xai | $0.0000 | $0.00300 | $0.00300 | $3.00 |
| 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 |
| 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 |
| 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 |
| Amazon Nova Premier | aws-bedrock | $0.0000 | $0.00625 | $0.00625 | $6.25 |
| 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 |
| Claude Opus 4.8 | anthropic | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Opus 4.6 | anthropic | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Fable 5 | anthropic | $0.0000 | $0.0250 | $0.0250 | $25.00 |
Paste any prompt to see exactly what it costs on every major LLM at once. We count your prompt's tokens with a real tokenizer, then rank every model from cheapest to most expensive per request — the fastest way to find the best-value model for your exact input.
How this is calculated
This calculator uses the tokens 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
Amazon Nova Micro: $0.0000700 per prompt
~0 input tokens + 500 output tokens across 43 models
- Cheapest
- Amazon Nova Micro — $0.0000700
- Most expensive
- Claude Fable 5 — $0.0250
- Input tokens(estimated)
- 0
| Model | Provider | Input | Output | Total / prompt | Per 1K prompts |
|---|---|---|---|---|---|
| Amazon Nova Micro | aws-bedrock | $0.0000 | $0.0000700 | $0.0000700 | $0.0700 |
| Command R7B | cohere | $0.0000 | $0.0000750 | $0.0000750 | $0.0750 |
| Amazon Nova Lite | aws-bedrock | $0.0000 | $0.000120 | $0.000120 | $0.1200 |
| DeepSeek V4 Flash | deepseek | $0.0000 | $0.000140 | $0.000140 | $0.1400 |
| Llama 4 Scout | meta | $0.0000 | $0.000170 | $0.000170 | $0.1700 |
| 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 | |
| DeepSeek V3.2 | deepseek | $0.0000 | $0.000210 | $0.000210 | $0.2100 |
| 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 | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| Command R | cohere | $0.0000 | $0.000300 | $0.000300 | $0.3000 |
| Llama 4 Maverick | meta | $0.0000 | $0.000425 | $0.000425 | $0.4250 |
| DeepSeek V4 Pro | deepseek | $0.0000 | $0.000435 | $0.000435 | $0.4350 |
| Devstral 2 | mistral | $0.0000 | $0.000450 | $0.000450 | $0.4500 |
| Sonar | perplexity | $0.0000 | $0.000500 | $0.000500 | $0.5000 |
| Mistral Large 3 | mistral | $0.0000 | $0.000750 | $0.000750 | $0.7500 |
| GPT-4.1 Mini | openai | $0.0000 | $0.000800 | $0.000800 | $0.8000 |
| GPT-5 Mini | openai | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| Mistral Medium 3.1 | mistral | $0.0000 | $0.00100 | $0.00100 | $1.00 |
| Gemini 2.5 Flash | $0.0000 | $0.00125 | $0.00125 | $1.25 | |
| Grok 4.3 | xai | $0.0000 | $0.00125 | $0.00125 | $1.25 |
| Amazon Nova Pro | aws-bedrock | $0.0000 | $0.00160 | $0.00160 | $1.60 |
| o4-mini | openai | $0.0000 | $0.00220 | $0.00220 | $2.20 |
| Claude Haiku 4.5 | anthropic | $0.0000 | $0.00250 | $0.00250 | $2.50 |
| Grok 4.5 | xai | $0.0000 | $0.00300 | $0.00300 | $3.00 |
| 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 |
| 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 |
| 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 |
| Amazon Nova Premier | aws-bedrock | $0.0000 | $0.00625 | $0.00625 | $6.25 |
| 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 |
| Claude Opus 4.8 | anthropic | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Opus 4.6 | anthropic | $0.0000 | $0.0125 | $0.0125 | $12.50 |
| Claude Fable 5 | anthropic | $0.0000 | $0.0250 | $0.0250 | $25.00 |
Frequently asked questions
How accurate is the token count?+
We count your prompt with OpenAI's o200k_base tokenizer (the one behind GPT-4o and GPT-5), so the input figure is exact for OpenAI models and a close approximation for Claude and Gemini, which use their own tokenizers.
Why do prices vary so much between models?+
Providers price per million input and output tokens, and rates range from a few cents to tens of dollars. Cheaper models can be 50-100x less expensive for the same prompt, so picking the right one matters at scale.
Does my prompt get sent anywhere?+
No. Tokenization and every calculation run entirely in your browser — nothing is uploaded to a server.