Qwen2.5 72B on Together for multilingual and coding-leaning workloads. Trial against Qwen3 on Groq for latency-sensitive apps.
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 | $1.20 |
| Output / 1M | $1.20 |
Model details
| Detail | Value |
|---|---|
| Provider | Together AI |
| Context window | 32.8K |
| Tokenizer | Approx |
| Last verified | 2026-08-02 |
| API model id | Qwen/Qwen2.5-72B-Instruct-Turbo |