DeepSeek
DeepSeek V4 Pro (Thinking)
Open MoE flagship with million-token context for coding and long agent runs
Model facts
- Context window
- 1.05M tokens
- Maximum output
- 384K tokens
- Cheapest paid input
- $1.1 per 1M tokens
- Cheapest paid output
- $2.2 per 1M tokens
- Open weights
- yes
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, open weights, text.
Observed price history
- 2026-08-24: $1.1 input / $2.2 output per 1M tokens
API providers
- NanoGPT — model id deepseek/deepseek-v4-pro:thinking; $1.1 input / $2.2 output per 1M tokens; provider documentation