DeepSeek: DeepSeek V3.1

Description

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.

Raw fields snapshot

{
  "id": "deepseek/deepseek-chat-v3.1",
  "name": "DeepSeek: DeepSeek V3.1",
  "description": "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)\n\nThe 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. \n\nIt succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.",
  "created": 1755779628,
  "canonical_slug": "deepseek/deepseek-chat-v3.1",
  "hugging_face_id": "deepseek-ai/DeepSeek-V3.1",
  "source_type": "openrouter_only",
  "context_length": 32768,
  "max_completion_tokens": 7168,
  "is_moderated": false,
  "architecture": {
    "modality": "text->text",
    "input_modalities": [
      "text"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "DeepSeek",
    "instruct_type": "deepseek-v3.1"
  },
  "input_modalities": [
    "text"
  ],
  "output_modalities": [
    "text"
  ],
  "modality": "text->text",
  "tokenizer": "DeepSeek",
  "instruct_type": "deepseek-v3.1",
  "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
  ],
  "default_parameters": {},
  "per_request_limits": null,
  "top_provider": {
    "context_length": 32768,
    "max_completion_tokens": 7168,
    "is_moderated": false
  },
  "pricing": {
    "prompt": "0.00000015",
    "completion": "0.00000075"
  },
  "PPM": {
    "prompt": 0.15,
    "completion": 0.75
  },
  "openrouter_raw": {
    "id": "deepseek/deepseek-chat-v3.1",
    "canonical_slug": "deepseek/deepseek-chat-v3.1",
    "hugging_face_id": "deepseek-ai/DeepSeek-V3.1",
    "name": "DeepSeek: DeepSeek V3.1",
    "created": 1755779628,
    "description": "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)\n\nThe 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. \n\nIt succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.",
    "context_length": 32768,
    "architecture": {
      "modality": "text->text",
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "DeepSeek",
      "instruct_type": "deepseek-v3.1"
    },
    "pricing": {
      "prompt": "0.00000015",
      "completion": "0.00000075"
    },
    "top_provider": {
      "context_length": 32768,
      "max_completion_tokens": 7168,
      "is_moderated": false
    },
    "per_request_limits": null,
    "supported_parameters": [
      "frequency_penalty",
      "include_reasoning",
      "logit_bias",
      "logprobs",
      "max_tokens",
      "min_p",
      "presence_penalty",
      "reasoning",
      "repetition_penalty",
      "response_format",
      "seed",
      "stop",
      "structured_outputs",
      "temperature",
      "tool_choice",
      "tools",
      "top_k",
      "top_logprobs",
      "top_p"
    ],
    "default_parameters": {},
    "expiration_date": null
  }
}