Skip to content

2 official pages marked 403/skipped — not freshly scraped.

Products / Grok API / Console

grok-api

Grok API / Console

The xAI API and console at console.x.ai expose Grok models, Imagine, and Voice. Grok 4.7 is the current flagship for coding, agentic tasks, and knowledge work: 500k context, reasoning effort including xhigh, cached-input pricing, and no text output limit. Partners include OpenRouter, Vercel, Cloudflare, Amazon Bedrock, and GitHub Copilot.

What version is Grok API / Console?

Grok API / Console current_version is 2026-09. last_updated is 2026-10-28. The catalog lists no channel versions for this product. Catalog generated_at is 2026-11-10T18:01:19+00:00. One API for text, images, video, voice, and search. Catalog status is ga. Organization is spacexai. Official source URL: https://console.x.ai.

id
grok-api
current_version
2026-09
last_updated
generated_at
published_at (this UI deploy)
SpaceXAIGAX Stack
ProductDocsUpstream changelog

Features

  • Flagship models

    Grok 4.7 (grok-4.7) for agents, coding, and knowledge work. Text and image in, text out.

    apimodel

  • Media and voice

    Imagine image/video generation and editing plus Voice realtime, TTS, and STT on the same API.

    apimediavoice

  • Console

    Keys, playground, usage, and changelog at console.x.ai.

    consoleapi

  • Partner surfaces

    OpenRouter, Vercel, Cloudflare, Amazon Bedrock, GitHub Copilot.

    availabilityapi

Changelog

  • Feature

    Custom moderation controls

    can · text API adds guidelines array

    Custom moderation controls

    You can now set content guidelines on text API requests. Add a guidelines array to a Chat Completions or Responses API request to set how Grok handles content in the nsfw, violence, and profanity categories. Grok follows the guidelines as it writes its response. See [Custom Moderation Controls](/developers/advanced-api-usage/custom-moderation-controls).

    source · docs.x.ai
  • Feature

    safety_identifier request field

    can · adds safety_identifier request field

    safety_identifier request field

    You can now send safety_identifier, an opaque end-user identifier assigned by your application, on Chat Completions, the Responses API, deferred chat completions, the Batch API, and the gRPC GetCompletionsRequest. It lets SpaceXAI attribute a policy violation to one of your end users rather than to your API key. The legacy user field is still accepted. See the Security FAQ on identifying which end user caused a policy violation.

    source · docs.x.ai
  • Release

    Grok 4.7 on the xAI API

    can · API serves Grok 4.7 (grok-4.7)

    grok-4.7 on the API: 500k context; same $2 / $0.50 / $6 tiers below 200k prompt tokens ($4 / $1 / $12 above); reasoning low / medium / high / xhigh; US regional endpoint; Responses API always returns reasoning.encrypted_content.

    source · docs.x.ai
  • Release

    Grok 4.6 on the xAI API

    can · API serves Grok 4.6 (500k context)

    500k context; $2 / $0.50 / $6 per 1M tokens below 200k prompt tokens, $4 / $1 / $12 above; reasoning low / medium / high / xhigh.

    source · docs.x.ai