Grok 4.7

x-ai/grok-4.7

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Grok 4.7

reasoning tools

xAI x-ai/grok-4.7

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

Input $/1M: $1.60
Output $/1M: $4.80
Context: 500K
Max output: 450K
Released: Sep 21, 2026
Modalities: textimagefile

Cached input reads $0.40 per 1M

On this deployment

Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.

Not available here yet

Signed in, add the model under Model providers; self-hosting, add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Grok 4.7
targets:
  - id: grok-4-7
    kind: llm
    name: Grok 4.7
    metadata:
      model: x-ai/grok-4.7          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 500000
    cost:
      usd_per_1k_tokens: 0.003200

Price among xAI models

Input list price per million tokens; Grok 4.7 is the 6th cheapest of 9 listed.

1
Grok Build 0.1
$1.00
2
Grok 4.3 (batch)
$1.00
3
Grok 4.3
$1.25
4
Grok 4.20 Multi-Agent
$1.25
5
Grok 4.20
$1.25
6
Grok 4.7
$1.60
7
Grok Latest
$1.60
8
Grok 4.6
$2.00
9
Grok 4.5
$2.00

More from xAI

Other models by the same vendor in the catalogue.