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 managing long context, and it improves on its predecessor at professional knowledge work such as drafting documents and presentations.

The model was trained with a longer reinforcement learning run weighted toward problems that take many hours to complete, and natively understands the Grok Bot harness for conversational tasks. It ships with a new safeguard stack that pairs strong jailbreak resistance with low refusal rates for legitimate cybersecurity and biology work. SpaceXAI's reported benchmark results use the xhigh reasoning effort.

xai/grok-4.7

Organization: xAI
Family: grok
Providers: 19
Context: 500,000
Output limit: 500,000
Knowledge: 2026-05
Release: 2026-09-21
Updated: 2026-09-21
Weights: Closed
Input: text, image, pdf
Output: text
Capabilities: Tools, Reasoning, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

25 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
AIHubMix	grok-4.7	500,000	500,000	$2.20 / $6.60	Yes	Yes	Yes	View
Amazon Bedrock	us.xai.grok-4.7	500,000	500,000	$2.20 / $6.60	Yes	Yes	Yes	View
Amazon Bedrock	global.xai.grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
Cloudflare AI Gateway	xai/grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
CrossModel	x-ai/grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
Eden AI	xai/grok-latest	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
Eden AI	xai/grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
GitHub Copilot	grok-4.7	500,000	128,000	$2.00 / $6.00	Yes	Yes	Yes	View
Kilo Gateway	x-ai/grok-4.7	500,000	450,000	$2.00 / $6.00	Yes	Yes	Yes	View
Merge Gateway	xai/grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
NanoGPT	x-ai/grok-4.7	500,000	500,000	$1.60 / $4.80	Yes	Yes	Yes	View
Ofox	x-ai/grok-4.7	500,000	65,536	$2.00 / $6.00	Yes	Yes	Yes	View
OpenCode Go	grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
OpenCode Zen	grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
xAIvia OpenRouter	x-ai/grok-4.7 unknown	500,000	450,000	$4.00 / $12.00	Yes	Yes	Yes	View
xAIvia OpenRouter	x-ai/grok-4.7 unknown	500,000	450,000	$2.20 / $6.60	Yes	Yes	Yes	View
xAIvia OpenRouter	x-ai/grok-4.7 unknown	500,000	450,000	$2.00 / $6.00	Yes	Yes	Yes	View
xAIvia OpenRouter	x-ai/grok-4.7 unknown	500,000	450,000	$2.00 / $6.00	Yes	Yes	Yes	View
xAIvia OpenRouter	x-ai/grok-4.7 unknown	500,000	450,000	$4.00 / $12.00	Yes	Yes	Yes	View
Requesty	grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
Tempr Gateway	xai/grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
Venice AI	grok-4-7	500,000	200,000	$2.27 / $6.80	Yes	Yes	Yes	View
Vercel AI Gateway	spacexai/grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View
xAI	grok-4.7	500,000	500,000	$2.00 / $6.00	Yes	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$1.60Per 1M input tokens

Output from$4.80Per 1M output tokens

Available offers25Across 19 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 5 lowest-priced configurations

InputOutput

xAIxai

$2.00$6.00

xAIxai/zdr

$2.00$6.00

xAIxai/zdr/us

$2.20$6.60

xAIxai/zdr/priority

$4.00$12.00

xAIxai/priority

$4.00$12.00

x-ai/grok-4.7Observed Oct 4, 2026, 11:31 AM UTC

Input: $2.00
Output: $6.00
Cache read: $0.50

Additional fees and pricing conditions

web search: $0.005 / search

overrides · USD per token for token prices; time windows use UTC.

[
  {
    "prompt": "0.000004",
    "completion": "0.000012",
    "input_cache_read": "0.000001",
    "min_prompt_tokens": 200000
  }
]

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
xAIxai/zdr/priority	$4.00	$12.00	$1.00	—
xAIxai/zdr/us	$2.20	$6.60	$0.55	—
xAIxai	$2.00	$6.00	$0.50	—
xAIxai/zdr	$2.00	$6.00	$0.50	—
xAIxai/priority	$4.00	$12.00	$1.00	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 4 endpoints

P50P75P90P99

xAIxai/zdr/priority

2,974–3,699.05 ms

xAIxai/zdr/us

784.5–1,043.97 ms

xAIxai

2,421–13,104.25 ms

xAIxai/zdr

1,969.5–17,825.64 ms

All latency percentiles 4 endpoints

Endpoint	P50	P75	P90	P99
xAIxai/zdr/priority	2,974 ms	3,364.25 ms	3,573.5 ms	3,699.05 ms
xAIxai/zdr/us	784.5 ms	805.5 ms	899.7 ms	1,043.97 ms
xAIxai	2,421 ms	3,371 ms	5,091.7 ms	13,104.25 ms
xAIxai/zdr	1,969.5 ms	2,891.5 ms	4,943.2 ms	17,825.64 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 4 endpoints

P50P75P90P99

xAIxai/zdr/priority

32–63.36 t/s

xAIxai/zdr/us

84.5–90.86 t/s

xAIxai

82.5–164.09 t/s

xAIxai/zdr

82–198.56 t/s

All throughput percentiles 4 endpoints

Endpoint	P50	P75	P90	P99
xAIxai/zdr/priority	32 t/s	48 t/s	57.6 t/s	63.36 t/s
xAIxai/zdr/us	84.5 t/s	86.75 t/s	89.6 t/s	90.86 t/s
xAIxai	82.5 t/s	101 t/s	119 t/s	164.09 t/s
xAIxai/zdr	82 t/s	108 t/s	137.8 t/s	198.56 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 5 endpoints

Endpoint5 minutes30 minutes24 hours

xAIxai/zdr/priorityObserved Oct 4, 2026, 11:31 AM UTC

—

98.48%

xAIxai/zdr/usObserved Oct 4, 2026, 11:31 AM UTC

—

99.8%

xAIxaiObserved Oct 4, 2026, 11:31 AM UTC

99.58%

99.84%

99.32%

xAIxai/zdrObserved Oct 4, 2026, 11:31 AM UTC

100%

99.9%

99.72%

xAIxai/priorityObserved Oct 4, 2026, 11:31 AM UTC

—

97.62%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

x-ai/grok-4.7Observed Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 50

Intelligence

46.4

Design Arena	Category	Elo	Win rate	Rank
models	dataviz	1,244	44.8%	33
models	gamedev	1,302	51.3%	15
models	uicomponent	1,250	44.8%	36
models	website	1,239	43.2%	42

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation	Configuration	Source	Results	Details
models · dataviz	Grok 4.7x-ai/grok-4.7-20260916	Design Arena	1,244 Elo	Details
models · gamedev	Grok 4.7x-ai/grok-4.7-20260916	Design Arena	1,302 Elo	Details
models · uicomponent	Grok 4.7x-ai/grok-4.7-20260916	Design Arena	1,250 Elo	Details
models · website	Grok 4.7x-ai/grok-4.7-20260916	Design Arena	1,239 Elo	Details
Composite indices	Grok 4.7 (xhigh)x-ai/grok-4.7-20260916	Artificial Analysis	Intelligence 46.4 · Coding — · Agentic —	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	x-ai/grok-4.7-20260916	1 turn	$0.016817	Details
Hermes Agent	x-ai/grok-4.7-20260916	10–49 turns	$0.903761	Details
Hermes Agent	x-ai/grok-4.7-20260916	2–9 turns	$0.090544	Details
Hermes Agent	x-ai/grok-4.7-20260916	50+ turns	$4.862789	Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days

Daily token usage484,795,531,602 reported tokens · 7 days with observations

120B0

2026-09-22
60,056,505,962 tokens

2026-09-25
119,618,395,558 tokens

2026-09-26
58,178,059,008 tokens

2026-09-27
42,424,862,081 tokens

2026-09-30
57,682,516,553 tokens

2026-10-01
51,991,618,562 tokens

2026-10-02
94,843,573,878 tokens

Jul 6, 2026Oct 3, 2026

Daily observations · 7 days

Date (UTC)	Reported tokens	Reported routes
Oct 2, 2026	94,843,573,878	1
Oct 1, 2026	51,991,618,562	1
Sep 30, 2026	57,682,516,553	1
Sep 27, 2026	42,424,862,081	1
Sep 26, 2026	58,178,059,008	1
Sep 25, 2026	119,618,395,558	1
Sep 22, 2026	60,056,505,962	1

Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

x-ai/grok-4.7Observed Oct 4, 2026, 11:31 AM UTC

Context: 500,000
Maximum output: 450,000
Tokenizer: Grok
Input: text, image, file
Output: text
Moderation: No
Added to OpenRouter: 2026-09-21

Base URLhttps://openrouter.ai/api/v1

Model IDx-ai/grok-4.7

Version IDx-ai/grok-4.7-20260916

Reasoning

Required: Yes
Enabled by default: Yes
Default effort: high
Supported efforts: xhigh, high, medium, low

Supported parameters

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

Default parameters

top p: 0.95
temperature: 0.7

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Grok 4.7 cost?

Listed rates start at $1.60 per million input tokens and $4.80 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Grok 4.7?

There are 25 cataloged offers across 19 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 500,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Catalog history · 1 recorded revision

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 22, 2026 · 6977607ecb7a