Grok

Grok 4.7

xAIToken-based
Alias:grok-4.7
Create API Key

Compare grok-4.7 API pricing, supported endpoints, capabilities and access options on Modelsell.

textimagefunction_callingtoolsjson_modestructured_outputreasoningvisioncontext:500000
Starting price
Input / Output · 1M
Context
500K
Maximum input window
Max output
450K
Maximum tokens per response
Modalities
→
Knowledge cutoff
May 2026

Pricing by Supplier

xAI
-40%
xAI 官方
Input$2$1.2/ 1M
Output$6$3.6/ 1M
Cache Read$0.5$0.3/ 1M

Capabilities / Supported modalities

StreamingFunction callingToolsJSON modeStructured outputReasoningVision
Input
Output

Provider & data privacy

Provider
xAIDocs
Tokenizer
Grok tokenizer (BPE)
License
Proprietary (commercial)Proprietary
Data retention81 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·Grok 4.7

Intelligence Index

Grok 4.7

46.4

Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.

About Grok 4.7

既能分析材料,也能协作解决问题

Grok 4.7适合代码辅助、知识分析和多步骤智能体任务。它可以根据项目上下文定位实现问题,结合图片解释界面或图表,也可以围绕多份资料比较说法、整理证据并形成工作文档。

研究近期内容时,让检索参与

通过应用启用的网页搜索、X搜索或其他检索工具,模型可以把外部资料带入分析。适合整理产品发布后的用户反馈、比较不同来源的观点,或查找某个技术问题的最新说明。应要求保留出处、区分发布时间与事件时间,并把原始事实和评论观点分开,避免将热度当作结论。

编程任务则可以结合函数调用和代码执行工具,将分析接到实际验证。提供错误输入、预期行为和项目约定,让模型先找出原因,再给出范围清楚的修复;运行结果应作为下一轮判断的依据。

多轮工作保留连续信息

Grok 4.7支持不同推理强度,可按任务难度选择。长工具循环要保留关键结果并管理上下文,避免重复检索或丢失已确定的限制。使用Responses API时,返回的加密推理内容应按要求原样续接。没有启用检索工具时,近期问题需要用户提供资料,不能把普通回答视作实时查询结果。

Use cases and prompting

发布反馈研究示例

“使用已启用的检索工具整理本次产品发布后的反馈。分别归纳官方说明、用户实际遇到的问题和个人观点,保留出处与日期。不要按转发量判断真实性;重复说法合并,无法核实的情况单独列出。最后提出需要进一步验证的三个问题。”

能自动搜索网页和X吗?

需要应用实际启用相应搜索工具。普通对话不会自动获得实时资料。

多轮工具调用怎样保持连续性?

保留工具结果与必要上下文。通过Responses API返回的reasoning.encrypted_content应原样传回后续请求,避免手动改写。

代码任务可要求先提供失败示例,再验证修复结果。

API access

API documentation

Code samples

RequestPOST/v1/chat/completions
Example request
Parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum number of tokens in the response
frequency_penalty
number
=0-2 ~ 2
Penalises repetition of frequent tokens
presence_penalty
number
=0-2 ~ 2
Encourages introducing new topics
stop
array—Up to 4 strings that stop generation
seed
integer—Deterministic sampling seed (best-effort)
n
integer
=1>= 1
Number of completions to generate
stream
boolean
=false
Stream tokens via Server-Sent Events
response_format
object—Force JSON object or schema-conforming output
tools
array—Tool / function declarations the model may call
tool_choice
string
autononerequired
Tool-choice policy or specific tool name
logprobs
boolean
=false
Return per-token log probabilities
top_logprobs
integer0 ~ 20Number of top log probabilities returned per token
logit_bias
object—Per-token logit bias map
user
string—End-user identifier for abuse monitoring

Replace <YOUR_API_KEY> with the API key from your token settings.

Authentication

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Supported parameters

Generation parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum number of tokens in the response
frequency_penalty
number
=0-2 ~ 2
Penalises repetition of frequent tokens
presence_penalty
number
=0-2 ~ 2
Encourages introducing new topics
stop
array—Up to 4 strings that stop generation
seed
integer—Deterministic sampling seed (best-effort)
n
integer
=1>= 1
Number of completions to generate
stream
boolean
=false
Stream tokens via Server-Sent Events
response_format
object—Force JSON object or schema-conforming output
tools
array—Tool / function declarations the model may call
tool_choice
string
autononerequired
Tool-choice policy or specific tool name
logprobs
boolean
=false
Return per-token log probabilities
top_logprobs
integer0 ~ 20Number of top log probabilities returned per token
logit_bias
object—Per-token logit bias map
user
string—End-user identifier for abuse monitoring

Rate limits

SupplierRPMTPMRPD
xAIUnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about grok-4.7

What is grok-4.7?

Compare grok-4.7 API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call grok-4.7?

Create an API key with access to grok-4.7, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is grok-4.7 priced?

Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.

What is the context window of grok-4.7?

The model catalog lists a context window of 500000 tokens. Check the selected endpoint for request limits.

What is the maximum output of grok-4.7?

The model catalog lists a maximum output of 450000 tokens. Your request settings may set a lower limit.

How should I evaluate grok-4.7 for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.