Top models, OpenAI-compatible. 主流模型，OpenAI 兼容中转。
Hachimi Cloud relays Grok, GPT & Gemini in OpenAI-compatible format — each provider on its own channel. Carpool the cost, keep native tools working out of the box. 哈基米云以 OpenAI 兼容格式中转 Grok、GPT、Gemini —— 每家模型各走独立渠道。拼车共享、分摊成本，原生工具开箱即用、无缝直连。
data: {"delta":" ⚡ Speed: 84 tok/s | Cost: $0.0004"}
data: [DONE]
01Available Models可用模型
GPT — OpenAI models.GPT — OpenAI 模型。
| Model | Context上下文 | Output输出 |
|---|---|---|
gpt-6-astra GPT-6-Astra | 400K | 128K |
gpt-6-sol GPT-6-Sol | 400K | 128K |
gpt-6-luna GPT-6-Luna | 400K | 128K |
codex-auto-review Codex Auto Review | — | — |
Context limits vary by model. All GPT models pass store: false to prevent API-side conversation storage.上下文上限因模型而异。所有 GPT 模型均设置 store: false 以阻止 API 端存储对话。
Grok — xAI models.Grok — xAI 模型。
| Model | Context上下文 | Output输出 |
|---|---|---|
grok-4.6 Grok-4.6 | — | — |
Full model list lives in the docs.完整模型列表见文档。
02Pricing定价
Pay per token, metered in real time. Prices shown per 1M tokens; GPT rates are in USD ($) and Grok rates remain in CNY (¥).按 token 实时计费，下表价格均为每 100 万 tokens（1M）；GPT 价格以 美元（$）计，Grok 价格仍按人民币（¥）计。
| Model | Input输入 | Output输出 | Cache write (5m)缓存写入（5m）? | Cache read缓存读取? |
|---|---|---|---|---|
gpt-6-astra |
$5 | $25 | $6.25 | $0.5 |
gpt-6-sol |
$0.5 | $2.5 | $0.625 | $0.05 |
gpt-6-luna |
$0.05 | $0.25 | $0.0625 | $0.005 |
| Model | Input输入 | Output输出 | Cache write (5m)缓存写入（5m）? | Cache read缓存读取? |
|---|---|---|---|---|
grok-4.6 |
¥0.3 | ¥0.9 | ¥0 (Free) | ¥0.065 |
Prices are shown per 1M tokens. Final rates may vary by user group — see your console for live quotas.以上价格均为每 100 万 tokens（1M）。实际倍率可能因用户组而异，实时额度以控制台为准。
03Why Hachimi Cloud为什么选哈基米云
OpenAI-compatible relayOpenAI 兼容中转
Reach Grok, GPT & Gemini in OpenAI-compatible format — each provider runs as its own channel. Point Claude Code, Codex or OpenCode at it and native tools just work.以 OpenAI 兼容格式访问 Grok、GPT、Gemini —— 每家模型对应独立渠道。Claude Code、Codex、OpenCode 直连即用，原生工具无缝可用。
Carpool & pooling拼车 · 账号池
Multi-account load balancing with sticky sessions. Share subscriptions, split the bill, and stay efficient.多账号负载均衡 + 粘性会话。订阅拼车共享，分摊成本，更高效。
Realtime billing实时计费配额
Usage metered in real time with transparent quotas — see exactly where every token goes.用量实时计费，额度透明可查 —— 每个 token 的去向一目了然。
04Works with your tools兼容你的工具
Drop-in for the agents and providers you already use.无缝接入你已经在用的 Agent 与模型厂商。
05Quick start快速开始
Pick your favorite tool, copy the snippet, drop in your API key, and you're ready to code. 选择你喜爱的工具，复制配置片段并填入密钥，即刻开启 AI 编程。
Config file:配置文件： ~/.claude/settings.json
{
"env": {
"ANTHROPIC_AUTH_TOKEN": "sk-your-api-key-here",
"ANTHROPIC_BASE_URL": "https://api.hachimi.cloud",
"ANTHROPIC_MODEL": "gpt-6-sol",
"ANTHROPIC_DEFAULT_SONNET_MODEL": "gpt-6-sol",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "gpt-6-luna",
"ANTHROPIC_DEFAULT_OPUS_MODEL": "gpt-6-astra"
}
}{
"env": {
"ANTHROPIC_AUTH_TOKEN": "sk-your-api-key-here",
"ANTHROPIC_BASE_URL": "https://api.hachimi.cloud",
"ANTHROPIC_MODEL": "grok-4.6"
}
}Config file:配置文件： ~/.config/opencode/opencode.json
{
"provider": {
"hachimi-cloud": {
"options": {
"baseURL": "https://api.hachimi.cloud/v1",
"apiKey": "sk-your-api-key-here",
"store": false
},
"models": {
"gpt-6-astra": {
"name": "GPT-6-Astra",
"limit": { "context": 400000, "output": 128000 }
},
"gpt-6-sol": {
"name": "GPT-6-Sol",
"limit": { "context": 400000, "output": 128000 }
},
"gpt-6-luna": {
"name": "GPT-6-Luna",
"limit": { "context": 400000, "output": 128000 }
},
"grok-4.6": {
"name": "Grok-4.6"
}
}
}
},
"model": "hachimi-cloud/gpt-6-sol",
"small_model": "hachimi-cloud/gpt-6-luna"
}Config file:配置文件： ~/.codex/config.toml
model_provider = "OpenAI"
model = "gpt-6-astra"
web_search = "live"
model_reasoning_effort = "medium"
[model_providers.OpenAI]
name = "OpenAI"
base_url = "https://api.hachimi.cloud/v1"
wire_api = "responses"
requires_openai_auth = true
supports_websockets = true
experimental_bearer_token = "sk-your-api-key-here"Endpoint:端点地址： https://api.hachimi.cloud/v1/chat/completions
curl https://api.hachimi.cloud/v1/chat/completions \
-H "Authorization: Bearer sk-your-api-key-here" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6-sol",
"messages": [{"role": "user", "content": "Hello Hachimi Cloud!"}]
}'