DeepSeek-V4-Pro
Preview 2026-04-24, GA snapshot DeepSeek-V4-Pro-0813 on 2026-08-13 (same id deepseek-v4-pro). Text-only (no vision). DeepSeek said service continues past 2026-09-14 until further notice. Knowledge cutoff not published.
- Context window
- 1,000,000 tokens
- Max output
- 384,000 tokens
- Input
- text
- Output
- text
- License
- mit
- Pricing
- input: $1.32 · output: $3.96 · cache read: $0.044 (per 1M tokens (USD), peak-hour list price; off-peak is half (input 0.66, output 1.98, cache hit 0.022). Peak = 01:00-04:00 and 06:00-10:00 UTC Mon-Fri) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| DeepSeek API | deepseek-v4-pro | https://api.deepseek.com | docs |
| DeepSeek API (Anthropic format) | deepseek-v4-pro | https://api.deepseek.com/anthropic | docs |
| Alibaba Cloud Model Studio | deepseek-v4-pro-0813 | — | docs |
| OpenRouter | deepseek/deepseek-v4-pro-0813 | openrouter.ai/deepseek/deepseek-v4-pro-0813 | — |
| OpenRouter (preview 0423) | deepseek/deepseek-v4-pro | openrouter.ai/deepseek/deepseek-v4-pro | — |
| Hugging Face | — | huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813 | — |
| Web app | — | chat.deepseek.com | — |
Notable capabilities (5)
- Open-weight 1.6T MoE with 1M context: 1.6T total / 49B active parameters, MIT license, 1M-token context (paper: 'Towards Highly Efficient Million-Token Context Intelligence'). source
- Agentic GA upgrade (0813) (found after launch): GA release greatly strengthened agent performance in production (e.g. Terminal Bench 2.1 87.9, Toolathlon-Verified 74.1 per DeepSeek). source
- Reasoning effort low/high/max (found after launch): Thinking mode supports three effort levels; non-thinking mode also available. source
- Native OpenAI Responses API + Codex (found after launch): DeepSeek API natively speaks the Responses API format and is adapted for Codex; Anthropic Messages format also supported. source
- DSpark speculative decoding module (found after launch): 0813 weights ship with an attached DSpark speculative-decoding module for faster inference. source
DeepSeek's strongest model: long-horizon coding agents, reasoning, 1M-context tasks. Open weights (MIT).
curl https://api.deepseek.com/chat/completions \
-H "Authorization: Bearer $DEEPSEEK_API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-pro","reasoning_effort":"high","messages":[{"role":"user","content":"Hello"}]}'
Sources: https://api-docs.deepseek.com/quick_start/pricing · https://api-docs.deepseek.com/updates · https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813