Paste your text and see estimated token counts for all 49 models. Instantly calculate input costs across OpenAI, Anthropic, DeepSeek, and more.
| Model | Input Tokens | Cost / call | Cost / month |
|---|---|---|---|
| Claude 2.1 | 0 | $0.000000 | $0.00 |
| Claude 3.5 Sonnet (Oct 2024) | 0 | $0.000000 | $0.00 |
| Claude 3 Haiku | 0 | $0.000000 | $0.00 |
| Claude 3 Opus | 0 | $0.000000 | $0.00 |
| Claude Fable 5 | 0 | $0.000000 | $0.00 |
| Claude Haiku 4.5 | 0 | $0.000000 | $0.00 |
| Claude Opus 4 | 0 | $0.000000 | $0.00 |
| Claude Opus 4.6 | 0 | $0.000000 | $0.00 |
| Claude Sonnet 4 | 0 | $0.000000 | $0.00 |
| Claude Sonnet 4.5 | 0 | $0.000000 | $0.00 |
| Claude Sonnet 5 | 0 | $0.000000 | $0.00 |
| Command | 0 | $0.000000 | $0.00 |
| Command R | 0 | $0.000000 | $0.00 |
| Command R+ | 0 | $0.000000 | $0.00 |
| DeepSeek V3 Chat | 0 | $0.000000 | $0.00 |
| DeepSeek Coder | 0 | $0.000000 | $0.00 |
| DeepSeek R1 Reasoner | 0 | $0.000000 | $0.00 |
| DeepSeek V4 Flash | 0 | $0.000000 | $0.00 |
| Gemini 1.0 Pro | 0 | $0.000000 | $0.00 |
| Gemini 1.5 Flash | 0 | $0.000000 | $0.00 |
| Gemini 1.5 Flash 8B | 0 | $0.000000 | $0.00 |
| Gemini 1.5 Pro | 0 | $0.000000 | $0.00 |
| Gemini 2.0 Flash | 0 | $0.000000 | $0.00 |
| Llama 3.1 8B | 0 | $0.000000 | $0.00 |
| Llama 3.3 70B | 0 | $0.000000 | $0.00 |
| Codestral | 0 | $0.000000 | $0.00 |
| Mistral Large | 0 | $0.000000 | $0.00 |
| Mistral Medium | 0 | $0.000000 | $0.00 |
| Mistral Small | 0 | $0.000000 | $0.00 |
| Mistral 7B | 0 | $0.000000 | $0.00 |
| Mixtral 8x22B | 0 | $0.000000 | $0.00 |
| Mixtral 8x7B | 0 | $0.000000 | $0.00 |
| GPT-3.5 Turbo | 0 | $0.000000 | $0.00 |
| GPT-4 | 0 | $0.000000 | $0.00 |
| GPT-4 Turbo | 0 | $0.000000 | $0.00 |
| GPT-4o | 0 | $0.000000 | $0.00 |
| GPT-4o Mini | 0 | $0.000000 | $0.00 |
| o1 | 0 | $0.000000 | $0.00 |
| o1 Mini | 0 | $0.000000 | $0.00 |
| o3 | 0 | $0.000000 | $0.00 |
| o3 Mini | 0 | $0.000000 | $0.00 |
| Grok 2 | 0 | $0.000000 | $0.00 |
Estimate tokens here, then calculate your costs or compress your prompts to save more.
This tool estimates tokens. Tokonomics counts exact tokens from your real API calls and alerts you on cost overruns.
Start Free →The budget-first AI cost metering proxy for any stack. Track every LLM token, set budget alerts, and never get surprised by your AI bill again.