DeepSeek: DeepSeek V3.1
By Deepseek
Released: 2025-08-21
Deepseek Deepseek Chat V3 1, developed by DeepSeek, features 671B parameters and 128-token context window. DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks. Available at $0.15/1M tokens.
Visit DeepSeek: DeepSeek V3.1AI-Powered
Leverages advanced AI technology to deliver cutting-edge capabilities and results.
Fast & Efficient
Optimized performance ensures quick results without compromising on quality.
Purpose-Built
Specifically designed for llms tasks and workflows.
Deepseek Model Timeline
164k tokens context
164k tokens context
164k tokens context
164k tokens context
164k tokens context
33k tokens context
164k tokens context
164k tokens context
164k tokens context
33k tokens context
131k tokens context
64k tokens context
164k tokens context
Specifications
AI Evaluation
Combines language understanding with search capabilities. Excels at finding and synthesizing information from various sources.
Pros
- Competitive pricing ($0.15/1M)
- 128 token context window
- Large-scale 671B architecture
- Strong code generation and debugging
Cons
- Requires substantial compute
- May lack creative flair
Related Tools
FLUX
FLUX, from Black Forest Labs, is a family of high-quality open and commercial image generation models prized for photorealism and prompt adherence. Widely integrated across third-party tools and APIs, it has become a default backbone for image generation.
Claude Opus 4.8
Claude Opus 4.8 is Anthropic's June 2026 flagship model, succeeding Opus 4.7. It posts a headline score of 81 on the hardest agentic coding and reasoning suites, holds long-horizon tool-use plans together across far more steps, and is notably more candid about its own uncertainty - refusing to fabricate rather than confidently pressing on. It is the default choice for serious agentic and software-engineering workloads.
Anthropic Mythos 1
Mythos 1 is the full release of Anthropic's specialised, security-focused system, graduating from the guarded Claude Mythos Preview. Built around Project Glasswing, it pairs frontier reasoning with defensive security tooling - vulnerability analysis, triage and incident response - deployed with heavy oversight and auditability. It runs alongside the general-purpose Claude family rather than replacing it.