Tiny Llama on Together for cheap OpenAI-compatible routing. Compare Groq 3B Instant-class hosts when latency is the main constraint.
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 | $0.060 |
| Output / 1M | $0.060 |
Model details
| Detail | Value |
|---|---|
| Provider | Together AI |
| Context window | 128K |
| Tokenizer | Approx |
| Last verified | 2026-08-02 |
| API model id | meta-llama/Llama-3.2-3B-Instruct-Turbo |