Open-weights MoE model from the DeepSeek-V4 family (284B total, 13B active), 1M-token context, three reasoning modes. MIT license.
Context window
1M
tokens
Parameters
284B (13B aktywowanych)
parameters
Release date
22 June 2026
Access:DownloadAPIHostedDeployment:๐ป Localโ Cloud
Overview
Access & deployment
DownloadAPIHosted
LocalCloud
Weights: Open source
Key parameters
๐ Context: 1M
๐งฉ Parameters: 284B (13B aktywowanych)
โ Tools
๐ฅ Input: text
Technical specification
Context window
1M
tokens
Parameters
284B (13B aktywowanych)
parameters
License
MIT
Features:โ Tool use
Modalities
โฌ Input
text
โฌ Output
textcode
Capabilities and applications
Native model capabilities
Advanced reasoning
The ability to perform multi-step, structured reasoning: analysing problems, planning steps, and drawing conclusions from hypotheses. Reasoning-first models (e.g. GPT-5.1 Thinking) dedicate a portion of inference to chains of thought before responding.
Category: reasoning
Extended thinking mode
A reasoning-model variant with a larger inference budget: more thinking cycles, higher answer precision at the cost of response time. Choice between 'standard' and 'extended' thinking is left to the user (e.g. the selector in GPT-5.2 Pro).
Category: reasoning
Adaptive reasoning effort
The model decides how much 'thinking' to allocate to a given query: simple questions are answered quickly, complex problems receive more inference cycles. A GPT-5.1 feature (both Instant and Thinking) that shortens time on easy tasks and extends it for hard ones.
Category: reasoning
Multi-step reasoning
Carrying out multi-step chains of reasoning across long, complex tasks.
Category: reasoning
Mathematical reasoning
The model's ability to solve mathematical tasks requiring multi-step reasoning โ equations, proofs, combinatorics, geometry, calculus and competition-level problems.
Category: reasoning
Coding
Generating, analysing and modifying code in many programming languages. Covers writing functions, debugging, refactoring, code review, and creating tests. Measured by benchmarks such as HumanEval and SWE-bench.
Category: coding
Agentic coding
Multi-hour, multi-step programming tasks performed autonomously by the model: cloning a repository, running tests, iterating on fixes, integrating with CLI tools. Characteristic of Codex variants (GPT-5.1-Codex-Mini, Codex-Max).
Category: coding
Agentic capability
The model's ability to autonomously plan and execute multi-step tasks by sequentially using tools, maintaining context, and adapting to intermediate results.
Category: planning
Tool use
The model's ability to call external functions, APIs and tools during a conversation: calculator, search engine, code editor, database. The model decides when and how to use a tool and interprets its result.
Category: planning
Long context
Support for large context windows โ tens to hundreds of thousands (or millions) of input tokens. Enables analysis of entire codebases, long documents, and many parallel conversations without losing earlier information. GPT-5.1 supports 400,000 tokens.
Category: language
Multilingual
Competence in many natural languages (from a few to over a hundred): understanding, generation, translation, and code-switching within a single conversation. Frontier models support a wide range of languages with comparable quality.
Category: language
Benchmark results
6 benchmarks
MMLU-Pro
EM ยท Think Max mode
86.2%
๐ technical_report
GPQA Diamond
Pass@1 ยท Think Max mode
88.1%
๐ technical_report
LiveCodeBench
Pass@1 ยท Think Max mode
91.6%
๐ technical_report
SWE-bench Verified
Resolved ยท Think Max mode
79.0%
๐ technical_report
HMMT 2026 Feb
Pass@1 ยท Think Max mode
94.8%
๐ technical_report
MRCR 1M
MMR ยท Think Max mode, 1M long context
78.7
๐ technical_report
Technical architecture
Core Architecture