Grok 4.20

Name: Grok 4.20
Author: xAI

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, de

by xAI(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Reference model card from the OpenRouter listing - model x-ai/grok-4.20. Prices are per million tokens as listed; ratings and installs below are from this marketplace.

Grok 4.20

Facts


Vendor	xAI
Context window	2,000,000 tokens
Max output	1,800,000 tokens
Input price	$1.25 / 1M tokens
Output price	$2.50 / 1M tokens
Input	text, image, file
Output	text
Tool calling	yes
Structured outputs	yes
Reasoning	yes
Open weights	no

Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model x-ai/grok-4.20

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "model-x-ai-grok-4-20", ...}

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

model-x-ai-grok-4-20.ocm.jsonjson

{
  "ocm": "1",
  "id": "model-x-ai-grok-4-20",
  "kind": "llm",
  "name": "Grok 4.20",
  "description": "Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...",
  "publisher": "xAI",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "llm",
      "x-ai",
      "openrouter",
      "reasoning",
      "tool-calling",
      "image",
      "file",
      "models"
    ],
    "languages": [
      "en"
    ],
    "modalities": [
      "text",
      "image",
      "file"
    ],
    "supports_tools": true,
    "supports_streaming": true,
    "context_window": 2000000
  },
  "quality_prior": 0.6,
  "examples": [
    "Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering..."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "models",
      "ref": "1774979019",
      "url": "https://openrouter.ai/x-ai/grok-4.20",
      "key": "x-ai/grok-4.20",
      "catalogue": "https://openrouter.ai/api/v1"
    },
    "model": "x-ai/grok-4.20",
    "pricing": {
      "input_usd_per_1m": 1.25,
      "output_usd_per_1m": 2.5,
      "cache_read_usd_per_1m": 0.2
    },
    "max_output_tokens": 1800000,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "created": 1774979019
  },
  "cost": {
    "usd_per_1k_tokens": 0.001875
  },
  "endpoints": [
    {
      "protocol": "openai",
      "url": "https://openrouter.ai/api/v1"
    }
  ]
}

Fetch it by URL: GET /api/v1/registry/model-x-ai-grok-4-20/manifest?version=1.0.0

About

Grok 4.20

Facts

Use it

Manifest

Reviews