Grok

grok-4.20-0309-non-reasoning

xAI按量收費

xAI 的 grok-4.20-0309-non-reasoning 模型。支持文本、图像输入和文本输出。

textimagefunction_callingtoolsstructured_outputjson_modevisioncontext:1000000
起始價格
輸入 / 輸出 · 1M
上下文
1M
最大輸入窗口
模態
→
發佈於
Mar 2026

Pricing by Supplier

xAI
省40%
xAI 官方
輸入$2$1.2/ 1M
輸出$6$3.6/ 1M
緩存讀取$0.2$0.12/ 1M

能力 / 支援的模態

函數呼叫工具結構化輸出JSON 模式視覺
輸入
輸出

廠商與數據私隱

供應商
分詞器
Grok tokenizer (BPE)
許可證
Proprietary (commercial)商業閉源
數據保留87 日預設不會用於上游訓練

效能

About grok-4.20-0309-non-reasoning

xAI 的 grok-4.20-0309-non-reasoning 模型。支持文本、图像输入和文本输出。

Use cases and prompting

Starting points for evaluation; supported inputs and options are listed in API access.

Use cases to explore

  • Draft and revise text with explicit audience, tone and format requirements.
  • Summarize supplied documents and compare answers against the original sources.

Practical tips

Separate instructions from source material, describe the desired output and provide an example. Test tool use or structured output only when listed as supported.

Example prompt

Summarize the following document in five bullet points. Separate confirmed facts from open questions, cite the relevant passages and do not invent missing information. Document: [paste your text]

API access

呼叫示例

請求POST/v1/chat/completions
請求範例
參數
參數類型預設值 / 範圍說明資訊
reasoning_effort
enum
=medium
控制模型回答前的推理深度
max_completion_tokens
integer>= 1最大 token 數(含隱藏的推理 token)
stop
array—最多 4 個停止生成的字串
seed
integer—盡量保證可復現的採樣種子
stream
boolean
=false
透過 SSE 串流返回 token
response_format
object—強制輸出 JSON 物件或符合 Schema 的結果
tools
array—模型可呼叫的工具 / 函數聲明
tool_choice
string
autononerequired
工具選擇策略或具體工具名
user
string—用於風險審計的終端用戶標識

替換 <YOUR_API_KEY> 替換為令牌設定中的 API Key。

身份驗證

所有請求必須攜帶 Authorization: Bearer <TOKEN> 請求頭。Anthropic 格式的端點也接受 x-api-key 請求頭。

在「令牌」頁面生成 API Key,可以按模型、分組、IP、速率等維度精細化授權。

支援的參數

Generation parameters
參數類型預設值 / 範圍說明資訊
reasoning_effort
enum
=medium
控制模型回答前的推理深度
max_completion_tokens
integer>= 1最大 token 數(含隱藏的推理 token)
stop
array—最多 4 個停止生成的字串
seed
integer—盡量保證可復現的採樣種子
stream
boolean
=false
透過 SSE 串流返回 token
response_format
object—強制輸出 JSON 物件或符合 Schema 的結果
tools
array—模型可呼叫的工具 / 函數聲明
tool_choice
string
autononerequired
工具選擇策略或具體工具名
user
string—用於風險審計的終端用戶標識

速率限制

供應商RPMTPMRPD
xAI800321K16K

RPM = 每分鐘請求數,TPM = 每分鐘 token 數,RPD = 每日請求數。限制按令牌分組生效。

Frequently asked questions about grok-4.20-0309-non-reasoning

What is grok-4.20-0309-non-reasoning?

xAI 的 grok-4.20-0309-non-reasoning 模型。支持文本、图像输入和文本输出。

How do I call grok-4.20-0309-non-reasoning?

Create an API key with access to grok-4.20-0309-non-reasoning, 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-4.20-0309-non-reasoning 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-4.20-0309-non-reasoning?

The model catalog lists a context window of 1000000 tokens. Check the selected endpoint for request limits.

How should I evaluate grok-4.20-0309-non-reasoning for my project?

Separate instructions from source material, describe the desired output and provide an example. Test tool use or structured output only when listed as supported.