DeepSeek
DeepSeek-V3.2 (Non-thinking Mode)
DeepSeek chat model for instruction following, coding, and analysis
Model facts
- Context window
- 128K tokens
- Maximum output
- 64K tokens
- Cheapest paid input
- $0.28 per 1M tokens
- Cheapest paid output
- $0.42 per 1M tokens
- Open weights
- no
- Providers
- 1
Capabilities and modalities
tool calling, temperature control, text.
Observed price history
- 2026-08-24: $0.28 input / $0.42 output per 1M tokens
API providers
- ZenMux — model id deepseek/deepseek-chat; $0.28 input / $0.42 output per 1M tokens; provider documentation