General DeepSeek chat endpoint for apps already wired to the chat model id. Compare against V4 Flash on price and against GPT Mini on quality for your prompts.
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 | $0.280 |
| Output / 1M | $0.420 |
| Cached input / 1M | $0.028 |
Model details
| Detail | Value |
|---|---|
| Provider | DeepSeek |
| Context window | 128K |
| Tokenizer | Approx |
| Last verified | 2026-08-02 |
| API model id | deepseek-chat |