Relace: Relace Apply 3

Description

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 tokens/sec on average. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update> Zero Data Retention is enabled for Relace. Learn more about this model in their [documentation](https://docs.relace.ai/api-reference/instant-apply/apply)

Raw fields snapshot

{
  "id": "relace/relace-apply-3",
  "name": "Relace: Relace Apply 3",
  "description": "Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 tokens/sec on average.\n\nThe model requires the prompt to be in the following format: \n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\n\nZero Data Retention is enabled for Relace. Learn more about this model in their [documentation](https://docs.relace.ai/api-reference/instant-apply/apply)",
  "created": 1758891572,
  "canonical_slug": "relace/relace-apply-3",
  "hugging_face_id": "",
  "source_type": "openrouter_only",
  "context_length": 256000,
  "max_completion_tokens": 128000,
  "is_moderated": false,
  "architecture": {
    "modality": "text->text",
    "input_modalities": [
      "text"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
  },
  "input_modalities": [
    "text"
  ],
  "output_modalities": [
    "text"
  ],
  "modality": "text->text",
  "tokenizer": "Other",
  "instruct_type": null,
  "supported_parameters": [
    "max_tokens",
    "seed",
    "stop"
  ],
  "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
  },
  "per_request_limits": null,
  "top_provider": {
    "context_length": 256000,
    "max_completion_tokens": 128000,
    "is_moderated": false
  },
  "pricing": {
    "prompt": "0.00000085",
    "completion": "0.00000125"
  },
  "PPM": {
    "prompt": 0.85,
    "completion": 1.25
  },
  "openrouter_raw": {
    "id": "relace/relace-apply-3",
    "canonical_slug": "relace/relace-apply-3",
    "hugging_face_id": "",
    "name": "Relace: Relace Apply 3",
    "created": 1758891572,
    "description": "Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 tokens/sec on average.\n\nThe model requires the prompt to be in the following format: \n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\n\nZero Data Retention is enabled for Relace. Learn more about this model in their [documentation](https://docs.relace.ai/api-reference/instant-apply/apply)",
    "context_length": 256000,
    "architecture": {
      "modality": "text->text",
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "Other",
      "instruct_type": null
    },
    "pricing": {
      "prompt": "0.00000085",
      "completion": "0.00000125"
    },
    "top_provider": {
      "context_length": 256000,
      "max_completion_tokens": 128000,
      "is_moderated": false
    },
    "per_request_limits": null,
    "supported_parameters": [
      "max_tokens",
      "seed",
      "stop"
    ],
    "default_parameters": {
      "temperature": null,
      "top_p": null,
      "frequency_penalty": null
    },
    "expiration_date": null
  }
}