Grok 4.7

grok/grok-4.7
NewFlagshipFeatured
VisionToolsJSONReasoning
by grok · 2026-09-21

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. Particularly strong at long-running software engineering and verifying its own work. Multimodal input (text, image, file), 500K-token context, up to 450K output tokens, reasoning with configurable effort, tools and structured outputs.

ctx500K tokens
Max output450K
Inputtext + image + file
Outputtext
INPUT$2.00/ 1M tokens
OUTPUT$6.00/ 1M tokens
p50 TTFTCollecting…
p95 TTFTCollecting…
TRAFFICCollecting…

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

What is Grok 4.7?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="grok/grok-4.7",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • logprobs
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • seed
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_logprobs
  • top_p

Pricing

TierInput / 1M tokensOutput / 1M tokensCache read / 1M
200K$2.00$6.00$0.500
$4.00$12.00$1.00
Tier selected by input token count of each request

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $32.00 · With prompt caching $26.75

Estimate based on list price

Tiered pricing — this estimate uses base-tier rates.

Token & cost estimator

Input tokens: 20Cost per request: $0.003040

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
Collecting…
Output speed
Collecting…
p95 TTFT
Collecting…
Error rate
100.0%

Public benchmarks

46.4
AA Intelligence
Better than 90% of models compared
#14 of 145
Humanity's Last Exam
43.1
Long-Context Recall
76.7
SciCode
57.4
Source: artificialanalysis.ai

Community buzz

What developers are saying this week

Hacker News7 mentions · 7dup 7 vs the previous week

How it compares

Grok 4.7grok/grok-4.3Grok 4.5Grok 4.6
Input $/M$2.00$1.25$2.00$2.00
Output $/M$6.00$2.50$6.00$6.00
Context500K1.0M500K500K
Quality9/1010/109/109/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is Grok 4.7?
It is SpaceXAI's flagship model, the successor to Grok 4.6, for coding, agentic tasks and knowledge work. It is especially strong at long-running software engineering and verifying its own work.
What inputs does it accept?
Text, images and files, with text output. It serves a 500K-token context window with an unusually large output budget of up to 450K tokens.
What capabilities does it support?
Reasoning with configurable effort (reasoning_effort), function calling / tools, structured (JSON) outputs via response_format, plus temperature, seed and logprobs — through the OpenAI-compatible API.
Which endpoints can call it?
The OpenAI-compatible Chat Completions API (/v1/chat/completions) and the Responses API (/v1/responses). Any OpenAI SDK works by pointing the base URL at OrcaRouter.
How is it priced?
Pricing is tiered by prompt size: a standard rate up to 200K input tokens, stepping up for prompts beyond that. See the pricing on this page for the current rate.

Embed this badge

Grok 4.7$2.00/M invia OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/grok/grok-4.7" target="_blank"> <img src="https://www.orcarouter.ai/embed/grok/grok-4.7.svg" alt="Grok 4.7 on OrcaRouter" /> </a>
Markdown [![Grok 4.7](https://www.orcarouter.ai/embed/grok/grok-4.7.svg)](https://www.orcarouter.ai/models/grok/grok-4.7)

Model card as data

GET /api/public/models/grok/grok-4.7Open
Machine-readable:/llms.txt/llms-full.txt