api-docs

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.togetherDocs = void 0;
exports.togetherDocs = [
    {
        id: "together-chat",
        title: "Together AI Chat API",
        category: "chat",
        provider: "together",
        keywords: ["together", "chat", "completions", "open source", "llama"],
        content: `# Together AI Chat API

## Endpoint
POST https://api.together.xyz/v1/chat/completions

## Headers
- Authorization: Bearer YOUR_API_KEY
- Content-Type: application/json

## Request Body
\`\`\`json
{
  "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo" | "meta-llama/Llama-3.1-8B-Instruct-Turbo" | "mistralai/Mixtral-8x22B-Instruct-v0.1" | "Qwen/Qwen2.5-72B-Instruct-Turbo" | "deepseek-ai/DeepSeek-V3",
  "messages": [
    {
      "role": "system" | "user" | "assistant" | "tool",
      "content": "string"
    }
  ],
  "max_tokens": number,
  "temperature": number (0-2, default 1),
  "top_p": number (0-1),
  "top_k": number,
  "stream": boolean,
  "stop": string[],
  "repetition_penalty": number (1-2),
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "string",
        "description": "string",
        "parameters": {JSON Schema}
      }
    }
  ],
  "tool_choice": "auto" | "none" | "required",
  "response_format": {"type": "text" | "json_object"},
  "safety_model": "Meta-Llama/Llama-Guard-3-8B"
}
\`\`\`

## Response
OpenAI-compatible format:
\`\`\`json
{
  "id": "xxx",
  "object": "chat.completion",
  "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "string",
        "tool_calls": [...]
      },
      "finish_reason": "stop" | "length" | "tool_calls"
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}
\`\`\`

## Available Models
- meta-llama/Llama-3.3-70B-Instruct-Turbo: Latest 70B
- meta-llama/Llama-3.1-8B-Instruct-Turbo: Fast 8B
- mistralai/Mixtral-8x22B-Instruct-v0.1: MoE model
- Qwen/Qwen2.5-72B-Instruct-Turbo: Qwen 72B
- deepseek-ai/DeepSeek-V3: DeepSeek V3
- NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
- google/gemma-2-27b-it

## Python SDK Example
\`\`\`python
from together import Together

client = Together(api_key="YOUR_API_KEY")

response = client.chat.completions.create(
    model="meta-llama/Llama-3.3-70B-Instruct-Turbo",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
    max_tokens=1024,
    temperature=0.7
)

print(response.choices[0].message.content)
\`\`\`

## Node.js Example
\`\`\`javascript
import Together from "together-ai";

const client = new Together({ apiKey: "YOUR_API_KEY" });

const response = await client.chat.completions.create({
  model: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
  messages: [{ role: "user", content: "Hello!" }],
  max_tokens: 1024
});

console.log(response.choices[0].message.content);
\`\`\`

## cURL Example
\`\`\`bash
curl https://api.together.xyz/v1/chat/completions \\
  -H "Authorization: Bearer $TOGETHER_API_KEY" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 1024
  }'
\`\`\``
    },
    {
        id: "together-embeddings",
        title: "Together AI Embeddings API",
        category: "embeddings",
        provider: "together",
        keywords: ["together", "embeddings", "vector", "semantic", "similarity"],
        content: `# Together AI Embeddings API

## Endpoint
POST https://api.together.xyz/v1/embeddings

## Request
\`\`\`json
{
  "model": "togethercomputer/m2-bert-80M-8k-retrieval" | "WhereIsAI/UAE-Large-V1" | "BAAI/bge-large-en-v1.5",
  "input": "text" | ["text1", "text2"]
}
\`\`\`

## Response
\`\`\`json
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.1, 0.2, ...]
    }
  ],
  "model": "togethercomputer/m2-bert-80M-8k-retrieval",
  "usage": {"prompt_tokens": 10, "total_tokens": 10}
}
\`\`\`

## Available Embedding Models
- togethercomputer/m2-bert-80M-8k-retrieval: 768 dims, 8K context
- WhereIsAI/UAE-Large-V1: 1024 dims
- BAAI/bge-large-en-v1.5: 1024 dims

## Python Example
\`\`\`python
from together import Together

client = Together(api_key="YOUR_API_KEY")

response = client.embeddings.create(
    model="togethercomputer/m2-bert-80M-8k-retrieval",
    input="Hello world"
)

embedding = response.data[0].embedding
\`\`\``
    },
    {
        id: "together-rate-limits",
        title: "Together AI Rate Limits & Pricing",
        category: "limits",
        provider: "together",
        keywords: ["together", "rate limit", "pricing", "cost", "free"],
        content: `# Together AI Rate Limits & Pricing

## Free Tier
- $5 free credit on signup
- Rate limits vary by model

## Pricing (per 1M tokens)
- Llama-3.3-70B: Input $0.88, Output $0.88
- Llama-3.1-8B: Input $0.18, Output $0.18
- Mixtral-8x22B: Input $1.20, Output $1.20
- Qwen2.5-72B: Input $1.20, Output $1.20
- DeepSeek-V3: Input $1.25, Output $1.25
- Embedding models: ~$0.01 per 1K requests

## Context Windows
- Llama-3.3-70B: 128K tokens
- Llama-3.1-8B: 128K tokens
- Mixtral-8x22B: 64K tokens
- Qwen2.5-72B: 128K tokens

## Features
- Open-source models
- Fine-tuning support
- OpenAI-compatible API
- Multiple embedding models`
    }
];
//# sourceMappingURL=together.js.map