grok-4.7-build-fast

Reasoning
Tools
Vision

Standard & Paid Price

Standard Price
MeterStandard Price
Input price$4.0000 / 1M tokens
Completion price$12.0000 / 1M tokens
Cache read price$1.0000 / 1M tokens
Dynamic pricing · 2 tiers
Billing details
Vendor list price comparison

Description

Grok 4.7-build-fast, supplied through a single reseller route. Supports text and image input, streaming, and function tools in Chat Completions and Responses. Reasoning is billed as output; output limits apply to visible text. The supplier adds a billable input prefix. On Responses, send the full conversation and preserve encrypted reasoning items; previous_response_id, conversation references and server-side tools are not supported. Published context limit: 500K tokens; the full limit is not independently qualified. When total input is > 200,000 tokens, input/cache-read/output rates for the entire request, not only the excess, are 1.5 times the short-context rates: USD 6 / 1.5 / 18 per million tokens.

Capabilities

Input modalities
text, image
Output modalities
text
Tasks
chat, reasoning, vision

API endpoints

  • POST /v1/chat/completions (openai)
  • POST /v1/responses (openai-response)