DeepSeek-V3.1

DeepSeek-V3.1 sits within the broader DeepSeek family as a text-only large language model positioned for developers who want open-weight access to a capable reasoning and tool-using system. Independent commentary treats its launch as a notable step in the open-model landscape, marking it as a release worth evaluating against both proprietary and other open alternatives. Its placement in third-party inference catalogs suggests it has been packaged for self-hosting and enterprise deployment beyond the original launch, reflecting broader adoption of the DeepSeek lineage in production environments.

Practically, the model fits workloads that blend chain-of-thought reasoning with structured tool calls, making it well suited to agentic pipelines, code assistants, and retrieval-augmented applications where controllable decoding and function integration matter. Because the weights are openly distributed, teams can fine-tune or distill from it for domain-specific tasks while still benefiting from the base model's general capabilities. The availability of a distinct Terminus point-release on enterprise inference platforms indicates ongoing iteration around stability and deployment polish, giving integrators a path to a hardened variant without abandoning the underlying v3.1 design.

TokenGodeepseek/deepseek-v3.1deepseek

Open provider page Provider docs

Quick Info

Provider: TokenGo
Model key: deepseek/deepseek-v3.1
Release date: Aug 21, 2025
Last updated: Aug 21, 2025
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.19
Output token cost: $0.71

Limits

Output tokens: 8,192 tokens
Context window: 131,072 tokens

Transparent token rates

Compare DeepSeek-V3.1 pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about DeepSeek-V3.1

Qiniu

Official sourceAnnouncement

DeepSeek announced DeepSeek-V3.1 on August 20, 2025, positioning it as the company's first step toward the agent era. The model introduces a hybrid inference design that lets a single model operate in both Think and Non-Think modes, with DeepSeek-V3.1-Think reportedly reaching answers faster than DeepSeek-R1-0528. Post-training improvements target stronger tool use and multi-step agent task performance, with gains cited on SWE and Terminal-Bench benchmarks. The release ships open-source weights for both V3.1 Base and V3.1 on Hugging Face, built on a V3.1-Base checkpoint that continued pretraining with 840 billion tokens for long-context extension. The tokenizer and chat template were updated, and the context window expands to 128K. API changes map deepseek-chat to non-thinking mode and deepseek-reasoner to thinking mode, add Anthropic API format support, and enable strict Function Calling as a beta feature.

Qiniu

Official sourceAnnouncement

DeepSeek's API documentation page confirms the DeepSeek-V3.1 release as the company's first step toward the agent era, introducing hybrid Think and Non-Think inference in a single model. DeepSeek-V3.1-Think is described as reaching answers faster than DeepSeek-R1-0528, with stronger agent skills from post-training that boost tool use and multi-step task execution. Results on SWE and Terminal-Bench are highlighted as improved. The API update routes deepseek-chat to non-thinking mode and deepseek-reasoner to thinking mode, both supporting a 128K context window. Anthropic API format compatibility and a strict Function Calling beta are added, while the V3.1 Base checkpoint adds 840 billion tokens of continued pretraining over V3 for long-context extension. Open-source weights for V3.1 Base and V3.1 are published on Hugging Face alongside a new tokenizer configuration.

Vercel AI Gateway

CoverageAnalysis

RunPod published a technical analysis examining DeepSeek V3.1's architectural changes relative to the V3-0324 model, describing V3.1 as a breakthrough hybrid reasoning model that dynamically toggles between fast inference and deep chain-of-thought logic within a single architecture. The piece situates the V3.1 release The analysis details how V3.1's hybrid behavior is governed by chat template parameters rather than separate model paths: the thinking mode uses the