xAILLM
Grok 4.5 API
xai/grok-4.5Grok 4.5 through the Hermes chat catalog.
- 500K context
- 工具
- 视觉
- 推理
在 Playground 中运行 Grok 4.5
Send a chat request with your account and see the exact token charge. Code needs an API key.
参数
请求预览
{"model": "xai/grok-4.5","messages": [],"stream": true,"max_tokens": 1024}网页 Playground 使用你的登录会话发送此请求体。在代码中请使用 API Key 发送相同内容。
结果
发送一条消息,用你的账号运行 Grok 4.5。
收到回复后,这里会显示用量和扣费。
Grok 4.5 价格
美元 / 百万 token。按每次请求的提示词长度选择档位。
- Reserve请求被接受时,Hermes 会按估算的提示词长度加上 max_tokens(未设置时为 8,192)预留额度。设置 max_tokens 可以减少预留。
- Settle响应结束后,按模型返回的实际用量结算:提示词 token 按输入价、命中缓存的 token 按缓存读取价、输出 token 按输出价,预留的剩余部分立即释放。
- Failures模型拒绝请求时不收费。流式输出在已生成内容后中断时,会按已生成文本估算并扣费。
Grok 4.5 能做什么
xAI positions Grok 4.5 for agentic software engineering and workflow tasks. See xAI's model page for native details. Native server-side search tools and current-events access should not be assumed to be available through the Hermes chat route.
Hermes lists xai/grok-4.5 with a 500,000-token context, vision, tools and streaming. Reasoning is listed and structured output is not listed in the current Hermes catalog. Check status and token pricing before making a request.
使用场景
Analyze information or code
Evaluate the model using representative inputs.
Use function tools
Handle calls in your application and verify results.
Review supported images
Combine image input with a written question.
用代码调用 Grok 4.5
任意 OpenAI SDK 都可用:设置 base URL 和你的 Hermes Key。
- 1
创建 API Key
In the dashboard, with the chat:create scope. API 密钥 - 2
Point your SDK at Hermes
Base URLhttps://api.hermes-ai.net/api/v1 - 3
发送对话补全请求
POST /chat/completionswithxai/grok-4.5
代码示例
Set HERMES_API_KEY in your environment.
export HERMES_API_KEY=your_api_keycurl https://api.hermes-ai.net/api/v1/chat/completions \
-H "Authorization: Bearer $HERMES_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "xai/grok-4.5",
"messages": [{"role": "user", "content": "Say hello in one sentence."}],
"max_tokens": 200
}'请求
POST https://api.hermes-ai.net/api/v1/chat/completions 带 chat:create 权限的 API Key,或已登录会话。
| 字段 | 类型 | 说明 |
|---|---|---|
| model | string | xai/grok-4.5 |
| messages | array | OpenAI 对话消息:system、user、assistant、tool 角色;text 和 image_url 内容块。 |
| stream | boolean | SSE 流式输出,最后一个事件包含 usage。 |
| max_tokens | integer | 输出上限,同时决定预留额度。 |
| tools / tool_choice | array / object | 仅支持 function 工具。 |
| response_format | object | 模型支持时可用 JSON 模式和 JSON schema。 |
| temperature, top_p, stop, seed, reasoning_effort | 原样透传。 |
响应
| 字段 | 说明 |
|---|---|
| choices[].message / delta | OpenAI chat completion 结构。 |
| usage | 模型返回的 prompt_tokens、completion_tokens 和 prompt_tokens_details.cached_tokens。 |
| hermes.charged_micros | 精确扣费(微美元,JSON 响应)。流式请求可在 GET /api/v1/chat/requests 查看。 |
| x-hermes-request | 请求 id 响应头,账单流水中使用同一 id。 |
| error.code | 文档中的 Hermes 错误码;请按错误码而非消息文本分支。 |
Grok 4.5 API 常见问题
Answers built from the model's catalog entry and the Hermes AI API contract.
Does Grok automatically know current events?
No. xAI's native documentation says current information requires search tools. Do not assume its hosted search tools are included in Hermes chat.
What is the Grok 4.5 API on Hermes AI?
Grok 4.5 by xAI is served through the OpenAI-compatible chat completions endpoint, https://api.hermes-ai.net/api/v1/chat/completions, with the model ID xai/grok-4.5.
What is the context window of Grok 4.5?
500,000 tokens, shared by the prompt and the output.
Does Grok 4.5 support vision, tools and JSON output?
Supported: 工具, 视觉 和 推理. Not supported: JSON 和 音频. Streaming works with stream: true.
How is Grok 4.5 billed?
Per token, from prepaid credits. When a request is accepted, credits are reserved for the estimated prompt plus max_tokens of output (8,192 when you set none); when it finishes, the exact charge is taken from the usage the model reports and the rest is released. A rejected request is not charged. Rates are in the pricing table.
Can I use the OpenAI SDK with Grok 4.5?
Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send xai/grok-4.5 as the model. Chat completions, streaming, tools and JSON output work unchanged.
What happens when I hit a rate limit?
Too many requests per minute return 429 RATE_LIMITED and too many in flight return 429 CONCURRENCY_LIMITED. If the model provider rate limits, you get 429 UPSTREAM_RATE_LIMITED and nothing is charged. Retry with backoff.
How do I get an API key for Grok 4.5?
Create one under API 密钥 in the dashboard with the chat:create scope, then add credits on the Billing page.