xAI: Grok 4下线

x-ai/grok-4

Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not exposed, reasoning cannot be disabled, and the reasoning effort cannot be specified. Pricing increases once the total tokens in a given request is greater than 128k tokens. See more details on the xAI docs

由:xAI输入类型:输出类型:发布时间:2025-07-09

供应商

在多个供应商之间路由请求。复制供应商标识以设置偏好供应商。

供应商缓存命中率上下文

xAI下线

x-ai

97.8%$3-6/ 百万 token$15-30/ 百万 token读取：0.75/ 百万 token写入：-/ 百万 token256K--

可用率

24 小时

AI Gateway 直连请求及各供应商的成功率。

May 16, 05:59

xAI100.00%

吞吐量

24 小时

AI Gateway 实时流量的 P50 吞吐量，单位为每秒 token 数（TPS）。

No data

延迟

24 小时

AI Gateway 实时流量的 P50 首 token 延迟（TTFT），单位为毫秒。

该时段暂无延迟样本。

活动

该模型随时间变化的 token 用量和请求流量。

Token 消耗

May 15

xAI2.4K

按实际处理请求的供应商拆分 token 用量。区块越大，表示该供应商处理的模型流量越多。

基准测试

标准化评测得分。百分比越高越好，并展示排名百分位。

指标来源：Artificial Analysis

Gemini 3.5 Flash Lite

GLM 4.7

Grok 4 xAI

Intelligence Index22.5

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All

Token 排行

No app usage is available for this period.

相关模型

更多模型来自 xAI

xAI: Grok 4.7

1.49Btoken

Grok 4.7 is xAI’s most capable model for coding and knowledge work, designed to spend longer on difficult tasks and verify its work more carefully. It is optimized for complex agentic workflows, long-context reasoning, and high-reliability outputs in demanding professional use cases.

xAI: Grok 4.6

6.87Btoken

Grok 4.6, released by xAI on August 13, 2026, builds on Grok 4.5 with a strong focus on long-running multi-step agentic tasks and interactive visual project creation, matching GPT-5.6 Sol on the composite intelligence index and excelling at rapidly turning a broad product idea into a structured, interactive, working first version of an application.

Grok Imagine Image 2.0

-token

Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and medium quality modes.