Mistral 7B Instruct on Together for cheap OpenAI-compatible endpoints. Step up to Mixtral or Llama 70B when evals fail.
Privacy first counting
TokenCALC counts tokens in your browser when an Exact encoding is available. Prompt text does not need to leave your device for local counting.
Pricing snapshot
USD per 1 million tokens. Verify against the provider source before you lock budget.
| Rate | USD |
|---|---|
| Input / 1M | $0.200 |
| Output / 1M | $0.200 |
Model details
| Detail | Value |
|---|---|
| Provider | Together AI |
| Context window | 32.8K |
| Tokenizer | Approx |
| Last verified | 2026-08-02 |
| API model id | mistralai/Mistral-7B-Instruct-v0.3 |