Grok 4.3 is a reasoning model from xAI that supports text and image inputs with text output. It is suited for agentic workflows, instruction following, long-document analysis, and deep research. The model supports a 1M token context window. Requests above 200K total tokens are billed at a higher rate.
| 規格 | 價格 |
|---|---|
| 輸入 | $2.5/ M tokens |
| 輸出 | $5/ M tokens |
| 快取讀 | $0.4/ M tokens |
| 快取寫 | -- |
可直接貼上執行下方範例程式碼。Gate.AI API 與 OpenAI 相容，多數 SDK 只需替換 base URL；切換模型時，只需修改模型 ID。
Sign in to the Gate.AI console and create a new key under "API Keys". Keep it safe and send it via the Authorization header on every request.
前往控制台建立金鑰Send a POST request to the Chat Completions endpoint with a model ID and an array of messages to get a reply.
curl --location "https://api.gate.ai/openai/v1/chat/completions" \
--header "Authorization: Bearer {API_KEY}" \
--header "Content-Type: application/json" \
--data '{
"model": "grok-4.3",
"messages": [
{"role": "user", "content": "Hello"}
]
}'By default a full JSON response is returned. Add "stream": true to the request body to receive incremental chunks over SSE.
curl --no-buffer --location "https://api.gate.ai/openai/v1/chat/completions" \
--header "Authorization: Bearer {API_KEY}" \
--header "Content-Type: application/json" \
--data '{
"model": "grok-4.3",
"messages": [
{"role": "user", "content": "Hello"}
],
"stream": true
}'基礎 URL、請求方法與必要請求頭，皆依當前模型的協議模板渲染。
以 OpenAI Responses API 格式建立串流或非串流回應。
Grok 4.6Grok's agent-oriented release, built for long-running multi-step work across a codebase. Accepts text, image, and file inputs. Suited for research and interactive or visual output.
Grok 4.5Grok's flagship reasoning model, running an internal chain of thought before responding. Strong performance on coding and STEM tasks, with support for text, image, and file inputs. Suited for technical problem-solving and long-document analysis.
Grok 4.20Reasoning-oriented Grok variant built for multi-step problem solving and agentic tool use, with strict prompt adherence and low hallucination.
Grok 4.20 Multi-AgentMulti-agent variant that dispatches sub-agents in parallel for deep research, multi-step reasoning, and tool orchestration.
Grok 4.20 V2 ReasoningReasoning-oriented Grok variant built for multi-step problem solving and agentic tool use, with strict prompt adherence and low hallucination.