$ cat wiki/models/deepseek-v4.md
DeepSeek V4
modelupdated 2026-08-14created 2026-07-20
Compared with
Spec
| Attribute | Value |
|---|---|
| Developer | DeepSeek |
| Released | 2026-07-16 (GA; preview: 2026-04-24) |
| Announced | 2026-04-24 |
| Context window | 1M tokens (384K max output) |
| Pricing | Peak: 2× off-peak API rates; off-peak rates not disclosed |
| License | MIT (open-weight) |
| Availability | DeepSeek API, Hugging Face (deepseek-ai/DeepSeek-V4-Pro) |
Release Date
Preview: April 24, 2026. GA: mid-July 2026.
Benchmarks
- DeepSeek-V4-Pro-Max: 80.6% SWE-bench Verified — highest open-weights score, tied with Gemini 3.1 Pro
Variants
| Variant | Total Params | Active Params | Use Case |
|---|---|---|---|
| V4-Pro | 1.6T | 49B | Quality-sensitive reasoning |
| V4-Flash | 284B | 13B | Faster, lower-cost serving |
| V4-Pro's GA build now has its own page — DeepSeek V4-Pro-0813. On | |||
| 2026-08-13 DeepSeek replaced the preview edition of V4-Pro in its API docs with build | |||
0813, adding Responses-API and Codex support and reporting large agentic gains | |||
| against the preview; the independent Artificial Analysis index moved by one point | |||
| (source). Everything on this | |||
| page describing V4-Pro refers to the July GA / preview state. |
V4-Flash now has its own page — DeepSeek V4-Flash. It was released
officially on 2026-07-31 as build 0731, a post-training-only refresh of the same
284B/13B architecture, and on vendor-stated agent benchmarks it overtakes
V4-Pro-Preview (Terminal Bench 2.1 82.7 vs 72.1)
(source). The same
announcement states the official V4-Pro release "will follow soon", which this page
does not yet record as shipped.
Architecture
- Mixture-of-Experts (MoE)
- Hybrid Compressed Sparse Attention (CSA) + Heavily Compressed Attention (HCA)
- 1M-token context at only 27% of single-token inference FLOPs (vs V3.2)
- Only 10% of KV cache footprint of V3.2 at 1M tokens
- Dual mode: Thinking (chain-of-thought) / Non-Thinking
Use Cases
- Agentic coding (SWE-bench frontier open-weight)
- Long-context reasoning
- Cost-efficient frontier tasks
Deprecation Notice
deepseek-chatanddeepseek-reasoner(legacy models) retired July 24, 2026 15:59 UTC
Compared To
| Model | SWE-bench Verified | Open? |
|---|---|---|
| DeepSeek V4-Pro-Max | 80.6% | Yes (MIT) |
| Claude Fable 5 | 80.3% (SWE-bench Pro) | No |
| Gemini 3.1 Pro | 80.6% | No |
| GLM-5.2 | unknown | Yes (MIT) |
Sources
- DeepSeek API changelog: updates
- Preview announcement: April 24
- Hugging Face: DeepSeek-V4-Pro