TNG: DeepSeek R1T2 Chimera

Description

DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0324 checkpoints with an Assembly-of-Experts merge. The tri-parent design yields strong reasoning performance while running roughly 20 % faster than the original R1 and more than 2× faster than R1-0528 under vLLM, giving a favorable cost-to-intelligence trade-off. The checkpoint supports contexts up to 60 k tokens in standard use (tested to ~130 k) and maintains consistent <think> token behaviour, making it suitable for long-context analysis, dialogue and other open-ended generation tasks.

Raw fields snapshot

{
  "id": "tngtech/deepseek-r1t2-chimera",
  "name": "TNG: DeepSeek R1T2 Chimera",
  "description": "DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0324 checkpoints with an Assembly-of-Experts merge. The tri-parent design yields strong reasoning performance while running roughly 20 % faster than the original R1 and more than 2× faster than R1-0528 under vLLM, giving a favorable cost-to-intelligence trade-off. The checkpoint supports contexts up to 60 k tokens in standard use (tested to ~130 k) and maintains consistent <think> token behaviour, making it suitable for long-context analysis, dialogue and other open-ended generation tasks.",
  "created": 1751986985,
  "canonical_slug": "tngtech/deepseek-r1t2-chimera",
  "hugging_face_id": "tngtech/DeepSeek-TNG-R1T2-Chimera",
  "source_type": "openrouter_only",
  "context_length": 163840,
  "max_completion_tokens": 163840,
  "is_moderated": false,
  "architecture": {
    "modality": "text->text",
    "input_modalities": [
      "text"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "DeepSeek",
    "instruct_type": null
  },
  "input_modalities": [
    "text"
  ],
  "output_modalities": [
    "text"
  ],
  "modality": "text->text",
  "tokenizer": "DeepSeek",
  "instruct_type": null,
  "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
  ],
  "default_parameters": {},
  "per_request_limits": null,
  "top_provider": {
    "context_length": 163840,
    "max_completion_tokens": 163840,
    "is_moderated": false
  },
  "pricing": {
    "prompt": "0.00000025",
    "completion": "0.00000085",
    "input_cache_read": "0.000000125"
  },
  "PPM": {
    "prompt": 0.25,
    "completion": 0.85,
    "input_cache_read": 0.125
  },
  "openrouter_raw": {
    "id": "tngtech/deepseek-r1t2-chimera",
    "canonical_slug": "tngtech/deepseek-r1t2-chimera",
    "hugging_face_id": "tngtech/DeepSeek-TNG-R1T2-Chimera",
    "name": "TNG: DeepSeek R1T2 Chimera",
    "created": 1751986985,
    "description": "DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0324 checkpoints with an Assembly-of-Experts merge. The tri-parent design yields strong reasoning performance while running roughly 20 % faster than the original R1 and more than 2× faster than R1-0528 under vLLM, giving a favorable cost-to-intelligence trade-off. The checkpoint supports contexts up to 60 k tokens in standard use (tested to ~130 k) and maintains consistent <think> token behaviour, making it suitable for long-context analysis, dialogue and other open-ended generation tasks.",
    "context_length": 163840,
    "architecture": {
      "modality": "text->text",
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "DeepSeek",
      "instruct_type": null
    },
    "pricing": {
      "prompt": "0.00000025",
      "completion": "0.00000085",
      "input_cache_read": "0.000000125"
    },
    "top_provider": {
      "context_length": 163840,
      "max_completion_tokens": 163840,
      "is_moderated": false
    },
    "per_request_limits": null,
    "supported_parameters": [
      "frequency_penalty",
      "include_reasoning",
      "max_tokens",
      "presence_penalty",
      "reasoning",
      "repetition_penalty",
      "response_format",
      "seed",
      "stop",
      "structured_outputs",
      "temperature",
      "tool_choice",
      "tools",
      "top_k",
      "top_p"
    ],
    "default_parameters": {},
    "expiration_date": null
  }
}