# LLM API

{% hint style="danger" %}
此文档已停止维护，最新文档地址：<https://docs.ttapi.io>
{% endhint %}

## ChatGPT completion

<mark style="color:green;">`POST`</mark> `https://api.ttapi.io/v1/chat/completions`

TTAPI中转Openai chat completion接口，除去Header中的TT-API-KEY外，所有请求以及相应参数全都同步官方一致，具体[使用详见 ](https://platform.openai.com/docs/api-reference/chat/create)

**Headers**

| Name         | Value              |
| ------------ | ------------------ |
| Content-Type | `application/json` |
| TT-API-KEY   | `Your key`         |

**Body**

<table><thead><tr><th width="162">参数</th><th width="144">类型</th><th width="112">是否必填</th><th>描述</th></tr></thead><tbody><tr><td><pre><code>messages
</code></pre></td><td>json</td><td>是<mark style="color:red;">*</mark></td><td><p>聊天message数组<br></p><pre class="language-bash"><code class="lang-bash">[
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"

</code></pre></td></tr><tr><td><code>model</code></td><td>string</td><td>是<mark style="color:red;">\*</mark></td><td>ttapi支持使用的模型，详见<a href="#gpt-zhi-chi-mo-xing">GPT支持模型</a></td></tr><tr><td>...</td><td>...</td><td>否</td><td>其他具体详见官方文档，所有参数同步<a href="https://platform.openai.com/docs/api-reference/chat/create">官方文档</a></td></tr></tbody></table>

**Response**

{% tabs %}
{% tab title="200" %}

```json
{
        "id": "chatcmpl-9ugiTupGJUmeRNqyqUvYO34GOUzyv",
        "object": "chat.completion",
        "created": 1723297597,
        "model": "gpt-3.5-turbo-0125",
        "choices": [
            {
                "index": 0,
                "message": {
                    "content": "你好！有什么可以帮助你的吗？",
                    "role": "assistant",
                    "name": null,
                    "refusal": null
                },
                "logprobs": null,
                "finish_reason": "stop",
                "delta": null
            }
        ],
        "usage": {
            "prompt_tokens": 11,
            "completion_tokens": 17,
            "total_tokens": 28
        },
        "system_fingerprint": null
}

```

{% endtab %}

{% tab title="200(stream)" %}

```json
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{"role":"assistant","content":""},"finish_reason":null}]}
 
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{"content":"Hello"},"finish_reason":null}]}
 
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{"content":"!"},"finish_reason":null}]}
 
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{"content":" How"},"finish_reason":null}]}
 
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{"content":" can"},"finish_reason":null}]}
 
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{"content":" I"},"finish_reason":null}]}
 
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{"content":" assist"},"finish_reason":null}]}
 
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{"content":" you"},"finish_reason":null}]}
 
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{"content":" today"},"finish_reason":null}]}
 
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{"content":"?"},"finish_reason":null}]}
 
data: {"id":"chatcmpl-83jctesyk8nEkPytXDNLz1oV5dIQK","object":"chat.completion.c
hunk","created":1695901063,"model":"gpt-3.5-turbo-0613","choices":[{"index":0,"d
elta":{},"finish_reason":"stop"}]}
 
data: [DONE]
 
```

{% endtab %}
{% endtabs %}

## Claude message

<mark style="color:green;">`POST`</mark> `https://api.ttapi.io/v1/messages`

TTAPI中转Claude create  message ，除去Header中的TT-API-KEY外，所有请求以及相应参数全都同步官方一致，具体[使用详见](https://docs.anthropic.com/en/api/messages)

**Headers**

| Name         | Value              |
| ------------ | ------------------ |
| Content-Type | `application/json` |
| TT-API-KEY   | `Your key`         |

**Body**

<table><thead><tr><th width="232">参数</th><th width="155">类型</th><th width="99">是否必填</th><th>描述</th></tr></thead><tbody><tr><td><code>model</code></td><td>string</td><td>是<mark style="color:red;">*</mark></td><td>ttapi支持claude模型列表，详见<a href="#claude-zhi-chi-mo-xing">Claude支持模型</a></td></tr><tr><td><code>messages</code></td><td>string</td><td>是<mark style="color:red;">*</mark></td><td><p>消息</p><pre><code>[
    {"role": "user", "content": "Hello, Claude"}
]
</code></pre></td></tr><tr><td><code>max_tokens</code></td><td>number</td><td>是<mark style="color:red;">*</mark></td><td><p>停止之前生成的最大令牌数。</p><p>请注意，我们的模型可能会在达到此最大值<em>之前</em>停止。此参数仅指定要生成的绝对最大标记数。</p></td></tr><tr><td>...</td><td>...</td><td>否</td><td>其他具体详见官方文档，所有参数同步  <a href="https://docs.anthropic.com/en/api/messages">官方文档</a></td></tr></tbody></table>

**Response**

{% tabs %}
{% tab title="200" %}

```json
{
  "completion": " Hello! My name is Claude.",
  "id": "compl_018CKm6gsux7P8yMcwZbeCPw",
  "model": "claude-2.1",
  "stop_reason": "stop_sequence",
  "type": "completion"
}
```

{% endtab %}

{% tab title="200(stream)" %}

```json
event: completion
data: {"type": "completion", "completion": " Hello", "stop_reason": null, "model": "claude-2.0"}

event: completion
data: {"type": "completion", "completion": "!", "stop_reason": null, "model": "claude-2.0"}

event: ping
data: {"type": "ping"}

event: completion
data: {"type": "completion", "completion": " My", "stop_reason": null, "model": "claude-2.0"}

event: completion
data: {"type": "completion", "completion": " name", "stop_reason": null, "model": "claude-2.0"}

event: completion
data: {"type": "completion", "completion": " is", "stop_reason": null, "model": "claude-2.0"}

event: completion
data: {"type": "completion", "completion": " Claude", "stop_reason": null, "model": "claude-2.0"}

event: completion
data: {"type": "completion", "completion": ".", "stop_reason": null, "model": "claude-2.0"}

event: completion
data: {"type": "completion", "completion": "", "stop_reason": "stop_sequence", "model": "claude-2.0"}


```

{% endtab %}
{% endtabs %}

## Grok chat

<mark style="color:green;">`POST`</mark> `https://api.ttapi.io/v1/grok/chat/completions`

TTAPI中转grok chat，除去Header中的TT-API-KEY外，所有请求以及相应参数全都同步官方一致，具体[使用详见](https://docs.x.ai/docs/guides/chat#parameters)

**Headers**

| Name         | Value              |
| ------------ | ------------------ |
| Content-Type | `application/json` |
| TT-API-KEY   | `Your key`         |

**Body**

<table><thead><tr><th width="232">参数</th><th width="155">类型</th><th width="99">是否必填</th><th>描述</th></tr></thead><tbody><tr><td><code>model</code></td><td>string</td><td>是<mark style="color:red;">*</mark></td><td>ttapi支持grok模型列表，详见<a href="#grok-zhi-chi-mo-xing">Grok支持模型</a></td></tr><tr><td><code>messages</code></td><td>string</td><td>是<mark style="color:red;">*</mark></td><td><p>消息</p><pre><code>[
    {"role": "user", "content": "Hello"}
]
</code></pre></td></tr><tr><td>...</td><td>...</td><td>否</td><td>其他具体详见官方文档，所有参数同步  <a href="https://docs.x.ai/docs/guides/chat#parameters">官方文档</a></td></tr></tbody></table>

**Response**

{% tabs %}
{% tab title="200" %}

```json
 {
        "created": 1741164819,
        "usage": {
            "completion_tokens": 10,
            "prompt_tokens": 7,
            "prompt_tokens_details": {
                "audio_tokens": 0,
                "text_tokens": 7,
                "image_tokens": 0,
                "cached_tokens": 0
            },
            "total_tokens": 17
        },
        "model": "grok-2-1212",
        "id": "f048edbb-ae27-4fc1-8b78-841c47c72946",
        "choices": [
            {
                "finish_reason": "stop",
                "index": 0,
                "message": {
                    "role": "assistant",
                    "refusal": null,
                    "content": "Hello! How can I assist you today?"
                }
            }
        ],
        "system_fingerprint": "fp_5c0c5bd9d9",
        "object": "chat.completion"
}
```

{% endtab %}

{% tab title="200(stream)" %}

```json
data: {"id":"<completion_id>","object":"chat.completion.chunk","created":<creation_time>,"model":"grok-2-latest","choices":[{"index":0,"delta":{"content":"Ah","role":"assistant"}}],"usage":{"prompt_tokens":41,"completion_tokens":1,"total_tokens":42,"prompt_tokens_details":{"text_tokens":41,"audio_tokens":0,"image_tokens":0,"cached_tokens":0}},"system_fingerprint":"fp_xxxxxxxxxx"}
data: {"id":"<completion_id>","object":"chat.completion.chunk","created":<creation_time>,"model":"grok-2-latest","choices":[{"index":0,"delta":{"content":",","role":"assistant"}}],"usage":{"prompt_tokens":41,"completion_tokens":2,"total_tokens":43,"prompt_tokens_details":{"text_tokens":41,"audio_tokens":0,"image_tokens":0,"cached_tokens":0}},"system_fingerprint":"fp_xxxxxxxxxx"}
data: [DONE]

```

{% endtab %}
{% endtabs %}

## Gemini chat

<mark style="color:green;">`POST`</mark> `https://api.ttapi.io/gemini/chat/completions`

TTAPI中转gemini chat，除去Header中的TT-API-KEY外，所有请求以及相应参数全都同步官方一致，具体[使用详见](https://ai.google.dev/gemini-api/docs/text-generation?hl=zh-cn)

**Headers**

| Name         | Value              |
| ------------ | ------------------ |
| Content-Type | `application/json` |
| TT-API-KEY   | `Your key`         |

**Body**

<table><thead><tr><th width="232">参数</th><th width="155">类型</th><th width="99">是否必填</th><th>描述</th></tr></thead><tbody><tr><td><code>model</code></td><td>string</td><td>是<mark style="color:red;">*</mark></td><td>ttapi支持gemini模型列表，详见<a href="#gemini-zhi-chi-mo-xing">Gemini支持模型</a></td></tr><tr><td><code>messages</code></td><td>string</td><td>是<mark style="color:red;">*</mark></td><td><p>消息</p><pre><code>[
    {"role": "user", "content": "Hello"}
]
</code></pre></td></tr><tr><td>...</td><td>...</td><td>否</td><td>其他具体详见官方文档，所有参数同步  <a href="https://ai.google.dev/gemini-api/docs/text-generation?hl=zh-cn">官方文档</a></td></tr></tbody></table>

**Response**

{% tabs %}
{% tab title="200" %}

```json
{
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "你好！很高兴和你聊天。\n\n有什么可以帮你的吗？或者想聊点什么？ 😊",
                "role": "assistant"
            }
        }
    ],
    "created": 1757472417,
    "id": "oebAaMTvMfCUjMcP_prYwAs",
    "model": "gemini-2.5-pro",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 21,
        "prompt_tokens": 3,
        "total_tokens": 1466
    }
}
```

{% endtab %}

{% tab title="200(stream)" %}

```json
id:null
data:{"choices":[{"delta":{"content":"你好啊！\n\n很高兴和你交流，有什么可以帮助你的吗？无论是解答问题、寻找灵感，还是只想随便","role":"assistant"},"index":0}],"created":1757472443,"id":"sebAaI_bM5qOjMcPmNGeyQs","model":"gemini-2.5-pro","object":"chat.completion.chunk","usage":{"completion_tokens":26,"prompt_tokens":3,"total_tokens":1074}}
retry:3000

id:null
data:{"choices":[{"delta":{"content":"聊聊，我都在这里。😊","role":"assistant"},"finish_reason":"stop","index":0}],"created":1757472443,"id":"sebAaI_bM5qOjMcPmNGeyQs","model":"gemini-2.5-pro","object":"chat.completion.chunk","usage":{"completion_tokens":34,"prompt_tokens":3,"total_tokens":1082}}
retry:3000
```

{% endtab %}
{% endtabs %}

## GPT支持模型

<table><thead><tr><th width="148">模型</th><th width="242">Openai价格</th><th data-hidden>折扣比例</th></tr></thead><tbody><tr><td>gpt-3.5-turbo</td><td>$3.00 / 1M input tokens<br>$6.00 / 1M output tokens</td><td>80%</td></tr><tr><td>gpt-4-turbo</td><td>$10.00 / 1M input tokens<br>$30.00 / 1M output tokens</td><td>80%</td></tr><tr><td>gpt-4</td><td>$30.00 / 1M input tokens<br>$60.00 / 1M output tokens</td><td>80%</td></tr><tr><td>gpt-4o</td><td>$5.00 / 1M input tokens<br>$15.00 / 1M output tokens</td><td>80%</td></tr><tr><td>gpt-4o-mini</td><td>$0.150 / 1M input tokens<br>$0.600 / 1M output tokens</td><td>80%</td></tr><tr><td>o1-preview</td><td>$15.00 / 1M input tokens<br>$60.00 / 1M output tokens</td><td>80%</td></tr><tr><td>o1-mini</td><td>$3.00 / 1M input tokens<br>$12.00 / 1M output tokens</td><td>80%</td></tr><tr><td>o1</td><td>$15.00 / 1M input tokens<br>$60.00 / 1M output tokens</td><td>80%</td></tr><tr><td>...</td><td></td><td></td></tr></tbody></table>

## Claude支持模型

<table><thead><tr><th width="185">模型</th><th width="236">Claude价格</th><th>折扣比例</th></tr></thead><tbody><tr><td>claude-3-sonnet-20240229</td><td>$3.00 / 1M input tokens<br>$15.00 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-3-opus-20240229</td><td>$15.00 / 1M input tokens<br>$75.00 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-3-haiku-20240307</td><td>$0.25 / 1M input tokens<br>$1.25 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-3-5-sonnet-20240620</td><td>$3.00 / 1M input tokens<br>$15.00 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-2.0</td><td>$8.00 / 1M input tokens<br>$24.00 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-2.1</td><td>$8.00 / 1M input tokens<br>$24.00 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-instant-1.2</td><td>$0.80 / 1M input tokens<br>$2.40 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-3-5-sonnet-20241022</td><td>$3.00 / 1M input tokens<br>$15.00 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-3-5-sonnet-latest</td><td>$3.00 / 1M input tokens<br>$15.00 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-3-5-haiku-20241022</td><td>$1.00 / 1M input tokens<br>$5.00 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-3-5-haiku-latest</td><td>$1.00 / 1M input tokens<br>$5.00 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-3-7-sonnet-20250219</td><td>$3.00 / 1M input tokens<br>$15.00 / 1M output tokens</td><td>80%</td></tr><tr><td>claude-sonnet-4-20250514</td><td>$3.00 / 1M input tokens<br>$15.00 / 1M output tokens</td><td>80%</td></tr></tbody></table>

## Grok支持模型

<table><thead><tr><th width="200">模型</th><th width="226">X.AI价格</th><th width="224">TTAPI价格</th><th>折扣</th></tr></thead><tbody><tr><td>grok-beta</td><td>$5.00 / 1M input tokens<br>$15.00 / 1M output tokens</td><td>$4.00 / 1M input tokens<br>$12.00 / 1M output tokens</td><td>80%</td></tr><tr><td>grok-vision-beta</td><td>$5.00 / 1M input tokens<br>$15.00 / 1M output tokens</td><td>$4.00 / 1M input tokens<br>$12.00 / 1M output tokens</td><td>80%</td></tr><tr><td>grok-2-1212<br>grok-2<br>grok-2-latest</td><td>$2.00 / 1M input tokens<br>$10.00 / 1M output tokens</td><td>$1.60 / 1M input tokens<br>$8.00 / 1M output tokens</td><td>80%</td></tr><tr><td>grok-2-vision-1212<br>grok-2-vision<br>grok-2-vision-latest</td><td>$2.00 / 1M input tokens<br>$10.00 / 1M output tokens</td><td>$1.60 / 1M input tokens<br>$8.00 / 1M output tokens</td><td>80%</td></tr><tr><td>grok-3 <br>grok-3-beta<br>grok-3-latest</td><td>$3.00 / 1M input tokens<br>$15.00 / 1M output token</td><td>$2.40 / 1M input tokens<br>$12.00 / 1M output token</td><td>80%</td></tr><tr><td>grok-3-fast
<br>grok-3-fast-beta
<br>grok-3-fast-latest</td><td>$5.00 / 1M input tokens<br>$25.00 / 1M output token</td><td>$4.00 / 1M input tokens<br>$12.00 / 1M output tokens</td><td>80%</td></tr><tr><td>grok-3-mini
<br>grok-3-mini-beta
<br>grok-3-mini-latest</td><td>$0.30 / 1M input tokens<br>$0.50 / 1M output token</td><td>$0.24 / 1M input tokens<br>$0.40 / 1M output toke</td><td>80%</td></tr><tr><td>grok-3-mini-fast
<br>grok-3-mini-fast-beta
<br>grok-3-mini-fast-latest</td><td>$0.60 / 1M input tokens<br>$4.00 / 1M output toke</td><td>$0.48 / 1M input tokens<br>$3.20 / 1M output token</td><td>80%</td></tr><tr><td>grok-4</td><td>$3.00 / 1M input tokens<br>$15.00 / 1M output token</td><td>$2.40 / 1M input tokens<br>$12.00 / 1M output token</td><td>80%</td></tr></tbody></table>

## Gemini支持模型

<table><thead><tr><th width="200">模型</th><th width="226">Gemini价格</th><th width="224">TTAPI价格</th><th>折扣</th></tr></thead><tbody><tr><td>gemini-1.5-pro</td><td>$1.25 / 1M input tokens<br>$5.00 / 1M output tokens</td><td>$0.75 / 1M input tokens<br>$3.00 / 1M output tokens</td><td>60%</td></tr><tr><td>gemini-1.5-flash-8B</td><td>$0.0375 / 1M input tokens<br>$0.15 / 1M output tokens</td><td>$0.0225 / 1M input tokens<br>$0.09 / 1M output tokens</td><td>60%</td></tr><tr><td>gemini-1.5-flash<br>gemini-2.0-flash-lite</td><td>$0.75 / 1M input tokens<br>$0.3 / 1M output tokens</td><td>$0.45 / 1M input tokens<br>$0.18 / 1M output tokens</td><td>60%</td></tr><tr><td>gemini-2.0-flash<br>gemini-2.5-flash-lite</td><td>$0.1 / 1M input tokens<br>$0.4 / 1M output tokens</td><td>$0.06 / 1M input tokens<br>$0.24 / 1M output tokens</td><td>60%</td></tr><tr><td>gemini-2.5-flash</td><td>$0.3 / 1M input tokens<br>$2.50 / 1M output token</td><td>$0.18 / 1M input tokens<br>$1.50 / 1M output token</td><td>60%</td></tr><tr><td>gemini-2.5-pro</td><td>$1.25 / 1M input tokens<br>$2.50 / 1M output token</td><td>$0.75 / 1M input tokens<br>$1.50 / 1M output tokens</td><td>60%</td></tr></tbody></table>