# Together AI API

**Provider:** Together AI
**Category:** ai
**Base URL:** `https://api.together.xyz/v1`
**Auth:** bearer — `Authorization: Bearer YOUR_TOGETHER_API_KEY`
**Rate Limit:** 60 requests/min (default) · Scales with plan
**Free Tier:** No
**Pricing:** from $0.10/mo (pay-as-you-go)
**Docs:** https://docs.together.ai

## Description

Together AI provides cloud infrastructure for running open-source AI models at scale. The API is fully OpenAI-compatible and supports 200+ models including Llama 3.1 405B, Qwen 2.5, Mistral, DeepSeek, Stable Diffusion, and more. Features include serverless inference (pay per token), dedicated GPU clusters, fine-tuning with LORA, vision models, and function calling. Popular for research, enterprise AI, and teams migrating from proprietary models.

## Endpoints

| Method | Endpoint | Description |
|--------|----------|-------------|
| POST | `https://api.together.xyz/v1/chat/completions` | Chat completions (OpenAI-compatible) |
| POST | `https://api.together.xyz/v1/completions` | Text completions |
| POST | `https://api.together.xyz/v1/embeddings` | Generate text embeddings |
| POST | `https://api.together.xyz/v1/images/generations` | Image generation (Stable Diffusion, FLUX) |
| GET | `https://api.together.xyz/v1/models` | List all available models with pricing |
| POST | `https://api.together.xyz/v1/fine-tunes` | Start a fine-tuning job with LoRA |

## Authentication

Create an API key at api.together.ai. The endpoint is OpenAI-compatible — pass your key as a Bearer token in the Authorization header.

```
Authorization: Bearer YOUR_TOGETHER_API_KEY
```

## Sample Request

```bash
curl "https://api.together.xyz/v1/chat/completions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","messages":[{"role":"user","content":"Write a Python function to parse JSON safely"}],"max_tokens":200}'
```

## Sample Response

```json
{
  "id": "890ab123",
  "model": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
  "choices": [{
    "message": { "role": "assistant", "content": "Here's a Python function to safely parse JSON:

```python
import json

def safe_json_parse(data):
    try:
        return json.loads(data)
    except json.JSONDecodeError:
        return None
```" },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 20, "completion_tokens": 68 }
}
```

## Pricing Details

Llama 3.1 8B: $0.18/M · $0.18/M. Llama 3.1 70B: $0.88/M · $0.88/M. Llama 4 Scout: available. DeepSeek R1: $1.25/M · $1.25/M. Image gen: $0.008 per image. No free tier; minimum $5 credit purchase.

---

*Source: [API Map](https://apimap.dev/apis/together-ai/) — CC BY 4.0*