DeepSeek

DeepSeek V3.1

deepseek/deepseek-chat-v3.1

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

DeepSeek V3.1

reasoning open weights tools

DeepSeek deepseek/deepseek-chat-v3.1

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...

Input $/1M: $0.55
Output $/1M: $1.65
Context: 164K
Max output: 145K
Released: Aug 21, 2025
Modalities: text

Cached input reads $0.55 per 1M · weights on Hugging Face as deepseek-ai/DeepSeek-V3.1

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs DeepSeek V3.1
targets:
  - id: deepseek-chat-v3-1
    kind: llm
    name: DeepSeek V3.1
    metadata:
      model: deepseek/deepseek-chat-v3.1          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 163840
    cost:
      usd_per_1k_tokens: 0.001100

Price among DeepSeek models

Input list price per million tokens; DeepSeek V3.1 is the 10th cheapest of 13 listed.

More from DeepSeek

Other models by the same vendor in the catalogue.