grok-4.7

Input price
$1.52/1M tokens
Output price
$4.56/1M tokens
Context window
1M
Modalities
Text · Image → Text

Pricing

Per million tokens

API call price5% OFF

0 – 200K

Input

$1.52

Output

$4.56

Cache write

—

Cache read

$0.38

> 200K

Input

$3.04

Output

$9.12

Cache write

—

Cache read

$0.76

Server tools

Billed per successful upstream call

  • Web Search

    The model searches the live web. The search runs upstream.

    $5.00/1K calls

  • Web Fetch

    The model opens a given page and reads its content. The fetch runs upstream.

    $5.00/1K calls



Integration & capabilities

Supported protocols

Responses API
Compatible formatOpenAI
Routes
POST /v1/responses
FeaturesStreaming · Reasoning · Prompt caching
Request parametersmodel, input, stream, tools, instructions

cURL Example

curl -X POST https://api.openmodel.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "grok-4.7",
    "input": "Hello"
  }'

Supported capabilities

Function Calling
Function calling (also known as tool calling) provides a powerful and flexible way for models to interface with external systems and access data outside their training data.
Tool Choice
By default the model will determine when and how many tools to use. You can force specific behavior with the tool_choice parameter.
Structured Outputs
Ensures the model will always generate responses that adhere to your supplied JSON Schema.
Reasoning
Reasoning models use internal reasoning tokens before producing a response.
Prompt Caching
Optimizes API usage by allowing resuming from specific prefixes in your prompts. This significantly reduces processing time and costs for repetitive tasks or prompts with consistent elements.
Vision
Models can process image inputs and analyze them — a capability known as vision.
Web Search
Allows models to access up-to-date information from the internet and provide answers with sourced citations.

Context & limits

Context window

1M

Max output tokens

1M