xAI

Grok 4.6

x-ai/grok-4.6
/v1/chat/completions/v1/messages/v1/responses/v1/completions/v1beta/models/*/v1/models/*

Grok 4.6 是 SpaceXAI 目前最先进的智能模型,在编程、知识处理以及 STEM 领域都表现出色。

Input / output modalities
文本 · 图像 · 文件 to 文本
Reference input / output price
Input¥14Output¥42per 1M tokens
Context window
500K
Added to catalog
Aug 14, 2026

Providers and pricing

ProviderInput lengthInput /MOutput /MCached /MContextMax outputDetails
OpenRouter≤ 200K¥14¥42¥3.5500K500K
≥ 200K¥28¥84¥7
Azure—¥14¥42¥3.5200K128K

OpenRouter

Latency
2.67s
Throughput
61 tokens/s
Context
500K

Pricing

Input
¥14/M tokens
Output
¥42/M tokens
Cached
¥3.5/M tokens

Tiered pricing

Pricing varies by input token range.

0–200K Token

Input tier
¥14/M tokens
Output tier
¥42/M tokens
Cache read tier
¥3.5/M tokens

200K–∞ Token

Input tier
¥28/M tokens
Output tier
¥84/M tokens
Cache read tier
¥7/M tokens

Specifications

Context
500K
Max output
500K
Supported APIs
/v1/chat/completions/v1/messages/v1/responses/v1/completions/v1beta/models/*/v1/models/*

Azure

Latency
4.38s
Throughput
426 tokens/s
Context
200K

Pricing

Input
¥14/M tokens
Output
¥42/M tokens
Cached
¥3.5/M tokens

Specifications

Context
200K
Max output
128K
Supported APIs
/v1/chat/completions/v1/messages/v1/responses/v1/completions/v1beta/models/*/v1/models/*

Grok 4.6 code examples and API guide

Modelmesh normalizes requests and responses across service providers behind one consistent API.

Modelmesh provides an OpenAI-compatible Completion API for more than 300 models and service providers. Call it directly, through the OpenAI SDK, or with supported third-party SDKs.

Modelmesh-specific request headers in these examples are optional. When supplied, your application can appear on the Modelmesh rankings.

Supported endpointsSelect an endpoint to switch the example below.
/v1/chat/completions
from openai import OpenAI API_KEY = "$SSY_API_KEY" client = OpenAI( base_url="https://router.shengsuanyun.com/api/v1", api_key=API_KEY, ) try: completion = client.chat.completions.create( model="x-ai/grok-4.6", messages=[{"role": "user", "content": "Which number is larger, 9.11 or 9.8?"}], temperature=0.6, top_p=0.7, stream=True, ) response_text = "" for chunk in completion: if chunk.choices and chunk.choices[0].delta.content is not None: content = chunk.choices[0].delta.content print(content, end="", flush=True) response_text += content except Exception as error: print(f"Request failed: {error}")
                
              

Related Models