Mistral Small 3.2 Token Counter & Cost Calculator
Count tokens for Mistral Small 3.2 and estimate the exact API cost — $0.10
per 1M input tokens, $0.30 per 1M output tokens — using a real
o200k_base BPE tokenizer. Everything runs in your browser; nothing is uploaded.
Counts are exact for OpenAI models (o200k_base is GPT-4o/4.1/5's tokenizer). For Claude, Gemini and other vendors — whose tokenizers are not public — treat the count as a close estimate (typically within ±15%).
Model price data failed to load — cost estimates are unavailable right now. Token counts above still work; try reloading the page.
Cost of this text across popular models
| Model | Input $/1M | Output $/1M | This text (input) | +500 output tokens |
|---|
Close estimate (±15%): Mistral does not publish its tokenizer, so this count uses OpenAI's o200k_base as an approximation.
Cost lookup — Mistral Small 3.2
| Tokens | Cost on Mistral Small 3.2 |
|---|---|
| 1K input tokens | 0.01¢ |
| 10K input tokens | 0.1¢ |
| 100K input tokens | $0.0100 |
| 1M input tokens | $0.1000 |
| 1K output tokens | 0.03¢ |
| 10K output tokens | 0.3¢ |
FAQ
How accurate is the Mistral Small 3.2 token count?
Close estimate (±15%): Mistral does not publish its tokenizer, so this count uses OpenAI's o200k_base as an approximation. Paste your own text above to see the exact number for your prompt.
How is Mistral Small 3.2 API cost calculated?
Cost = (input tokens ÷ 1,000,000) × $0.10 + (output tokens ÷ 1,000,000) × $0.30 — Mistral Small 3.2's official per-1M-token prices from Artificial Analysis.
See full Mistral Small 3.2 pricing & benchmarks, or the main token counter for every model.