xAI: Grok 4 Fast

Description

Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast). Reasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)

Raw fields snapshot

{
  "id": "x-ai/grok-4-fast",
  "name": "xAI: Grok 4 Fast",
  "description": "Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast).\n\nReasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)",
  "created": 1758240090,
  "canonical_slug": "x-ai/grok-4-fast",
  "hugging_face_id": "",
  "source_type": "openrouter_only",
  "context_length": 2000000,
  "max_completion_tokens": 30000,
  "is_moderated": false,
  "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
      "text",
      "image"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "Grok",
    "instruct_type": null
  },
  "input_modalities": [
    "text",
    "image"
  ],
  "output_modalities": [
    "text"
  ],
  "modality": "text+image->text",
  "tokenizer": "Grok",
  "instruct_type": null,
  "supported_parameters": [
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
  ],
  "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
  },
  "per_request_limits": null,
  "top_provider": {
    "context_length": 2000000,
    "max_completion_tokens": 30000,
    "is_moderated": false
  },
  "pricing": {
    "prompt": "0.0000002",
    "completion": "0.0000005",
    "web_search": "0.005",
    "input_cache_read": "0.00000005"
  },
  "PPM": {
    "prompt": 0.2,
    "completion": 0.5,
    "web_search": 5000,
    "input_cache_read": 0.05
  },
  "openrouter_raw": {
    "id": "x-ai/grok-4-fast",
    "canonical_slug": "x-ai/grok-4-fast",
    "hugging_face_id": "",
    "name": "xAI: Grok 4 Fast",
    "created": 1758240090,
    "description": "Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast).\n\nReasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)",
    "context_length": 2000000,
    "architecture": {
      "modality": "text+image->text",
      "input_modalities": [
        "text",
        "image"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "Grok",
      "instruct_type": null
    },
    "pricing": {
      "prompt": "0.0000002",
      "completion": "0.0000005",
      "web_search": "0.005",
      "input_cache_read": "0.00000005"
    },
    "top_provider": {
      "context_length": 2000000,
      "max_completion_tokens": 30000,
      "is_moderated": false
    },
    "per_request_limits": null,
    "supported_parameters": [
      "include_reasoning",
      "logprobs",
      "max_tokens",
      "reasoning",
      "response_format",
      "seed",
      "structured_outputs",
      "temperature",
      "tool_choice",
      "tools",
      "top_logprobs",
      "top_p"
    ],
    "default_parameters": {
      "temperature": null,
      "top_p": null,
      "frequency_penalty": null
    },
    "expiration_date": null
  }
}