GPAI Ledger › Model catalog (developer docs) (xAI) › Capture 4 Oct 2026

Model catalog (developer docs) — capture 20261004T114227Z

Verify: sha256sum f3cad1de829c7c4162a0a7db1b4e1de819b5591c713f887368fdd60c816b1ca2.html.txt must equal the hash above (the filename IS the expected hash); ots verify f3cad1de829c7c4162a0a7db1b4e1de819b5591c713f887368fdd60c816b1ca2.html.20261004T114227Z.ots -f f3cad1de829c7c4162a0a7db1b4e1de819b5591c713f887368fdd60c816b1ca2.html.txt (opentimestamps.org) proves the bytes existed no later than the attestation time — an upper bound on the capture time; the fetch time above is the archive's own record (a freshly captured proof reports 'pending' here: the calendars anchor within hours, but this archive only upgrades the stored proof to its anchor on a later run, so expect a day or two). ots verify needs a local Bitcoin Core node (a pruned one is fine); without one, ots info on the proof prints the attesting block height and merkle path to check on any block explorer.

Extracted text

Machine-extracted text (layout may be lost; the authoritative content is the stored file above).

Grok Models & Pricing | SpaceXAI Docs
API
Grok Build
Grok Bot
Grok
Search
⌘
K
API Console
Products
Grok
Status
Loading...
Resources
llms.txt
Discord
Email support
Terms and Policies
Get Started
Overview
Quickstart
Grok 4.7
Latest
Models
Pricing
Release Notes
Text
Text Generation
Streaming
Reasoning
Structured Outputs
Image Understanding
Multi Agent
Imagine
Overview
Image Generation
Image Editing
Multi-Image Editing
Video Generation
Image-to-Video
Reference-to-Video
New
Video Editing
Video Extension
Voice
Overview
Speech to Speech
Text to Speech
Speech to Text
New
Custom Voices
Ephemeral Tokens
Files & Collections
Files Overview
Managing Files
Public URLs
New
Chat with Files
Collections
Collections via API
Collection Metadata
Generated Media
Tools
Overview
Function Calling
Web Search
X Search
Code Execution
Image Generation
Collections Search (RAG)
Remote MCP Tools
In Depth
Advanced API Usage
Rate Limits
Prompt Caching
Context Compaction
Priority Processing
Batch API
Deferred Completions
Async Requests
WebSocket Mode
mTLS Authentication
Regional Endpoints
New
Cost Tracking
Debugging Errors
Platforms
Community Integrations
Google Cloud Vertex AI
Microsoft Foundry
Docs MCP
Migration Guides
Imagine Image Quality Retirement (Nov 2, 2026)
New
Model Retirement (May 15, 2026)
Migrating to Responses API
Chat Completions (Legacy)
FAQ
Data & Privacy
General
API
Docs
REST Reference
Grok Build
Grok Bot
Grok
Get Started
Overview
Quickstart
Grok 4.7
Latest
Models
Pricing
Release Notes
Text
Text Generation
Streaming
Reasoning
Structured Outputs
Image Understanding
Multi Agent
Imagine
Overview
Image Generation
Image Editing
Multi-Image Editing
Video Generation
Image-to-Video
Reference-to-Video
New
Video Editing
Video Extension
Voice
Overview
Speech to Speech
Text to Speech
Speech to Text
New
Custom Voices
Ephemeral Tokens
Files & Collections
Files Overview
Managing Files
Public URLs
New
Chat with Files
Collections
Collections via API
Collection Metadata
Generated Media
Tools
Overview
Function Calling
Web Search
X Search
Code Execution
Image Generation
Collections Search (RAG)
Remote MCP Tools
In Depth
Advanced API Usage
Rate Limits
Prompt Caching
Context Compaction
Priority Processing
Batch API
Deferred Completions
Async Requests
WebSocket Mode
mTLS Authentication
Regional Endpoints
New
Cost Tracking
Debugging Errors
Platforms
Community Integrations
Google Cloud Vertex AI
Microsoft Foundry
Docs MCP
Migration Guides
Imagine Image Quality Retirement (Nov 2, 2026)
New
Model Retirement (May 15, 2026)
Migrating to Responses API
Chat Completions (Legacy)
FAQ
Data & Privacy
General

Key Information
Models
Copy for LLM
View as Markdown
Create API key
Meet grok-4.7
Grok 4.7
New
grok-4.7
Our flagship model for code and everything else: agentic tool calling, minimal hallucinations, configurable reasoning.
Context
500k tokens
Input
$2.00 / 1M tokens
Output
$6.00 / 1M tokens
Reasoning
Configurable
View model
Try in playground
Voice API
Real-time conversations, speech-to-text, and text-to-speech.
STS
$0.08 / min
TTS
$15.00 / 1M chars
STT (Batch)
$0.10 / hour
STT (Streaming)
$0.20 / hour
Read docs
Try in playground
Imagine API
Turn ideas into reality with image and video generation.
Modes
Generation & editing
Speed
Industry-leading
Image · 1K / 2K
Starting at
$0.02 / image
Video · 480p / 720p / 1080p
Starting at
$0.02 / sec
Read docs
Try in playground
Which model should I choose?
Your choice depends on your use case. We have dedicated models and APIs for audio, image, and video capabilities. For everything else, including code, use Grok 4.7. It is the most capable model we’ve built.
Use case
Model
Code
Grok 4.7
Chat
Grok 4.7
Images
Grok Imagine Image 2.0
Videos
Grok Imagine Video 1.5
Voice
Grok Voice API
Additional Information Regarding Models

No access to realtime events without search tools enabled

Grok has no knowledge of current events or data beyond what was present in its training data.

To incorporate realtime data with your request, enable server-side search tools (Web Search / X Search). See
Web Search
 and
X Search
.

Chat models

No role order limitation: You can mix
system
,
user
, or
assistant
 roles in any sequence for your conversation context.

logprobs
 and
top_logprobs
 are not supported by models
grok-4.20
 and newer. These fields will be silently ignored if set.

Image input models

Maximum image size:
20MiB

Maximum number of images: No limit

Supported image file types:
jpg/jpeg
 or
png
.

Any image/text input order is accepted (e.g. text prompt can precede image prompt)

Batch API

Not every model accepts
Batch API
 requests. See Details on each model page.

Encrypted reasoning

On the
Responses API
,
grok-4.7
 always returns
reasoning.encrypted_content
, even when
include
 does not list it. See
Encrypted reasoning content
.

The knowledge cut-off date of Grok 4.7 is May 2026.
Model Aliases
Some models have aliases to help users automatically migrate to the next version of the same model. In general:

<modelname>
 is aliased to the latest stable version.

<modelname>-latest
 is aliased to the latest version. This is suitable for users who want to access the latest features.

<modelname>-<date>
 refers directly to a specific model release. This will not be updated and is for workflows that demand consistency.

For most users, the aliased
<modelname>
 or
<modelname>-latest
 are recommended, as you would receive the latest features automatically.
Last updated:
September 21, 2026