DeepSeek: DeepSeek V3.1 Terminus (exacto)

Description

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. 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.

Raw fields snapshot

{
  "id": "deepseek/deepseek-v3.1-terminus:exacto",
  "canonical_slug": "deepseek/deepseek-v3.1-terminus",
  "name": "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
  "display_name": "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
  "provider": "deepseek",
  "description": "DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. 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. ",
  "context_length": null,
  "source_type": "model_only",
  "best_rank": null,
  "pricing": {
    "prompt": null,
    "completion": null
  },
  "pricing_summary": {},
  "capabilities": {
    "modalities": [
      "text"
    ],
    "context_length": null,
    "architecture": {
      "modality": "text->text",
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "DeepSeek",
      "instruct_type": "deepseek-v3.1"
    }
  },
  "__detail_source": "model_snapshot",
  "__raw_snapshot": {
    "model": {
      "id": "deepseek/deepseek-v3.1-terminus:exacto",
      "slug": "deepseek/deepseek-v3.1-terminus",
      "display_name": "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
      "provider": "deepseek",
      "description": "DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. 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. ",
      "context_length": null,
      "modalities": [
        "text"
      ],
      "tags": [],
      "source_type": "model_only",
      "updated_at": "2026-03-01T02:42:38.283858+00:00",
      "source": "model_only"
    },
    "overall_score": null,
    "best_rank": null,
    "ranks_by_category": {},
    "scores_by_category": {},
    "pricing_summary": {},
    "capabilities": {
      "modalities": [
        "text"
      ],
      "context_length": null,
      "architecture": {
        "modality": "text->text",
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "DeepSeek",
        "instruct_type": "deepseek-v3.1"
      }
    }
  }
}