> ## Documentation Index
> Fetch the complete documentation index at: https://lava.so/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Together

> Together AI offers the widest open-source model selection in the market, providing access to DeepSeek V4, GLM 5.2, Qwen3, Kimi, and 100+ other models through a single OpenAI-compatible API.

Together offers 56 models through Lava's AI Gateway, supporting Chat Completions, Embeddings. Authentication uses `Authorization: Bearer`. See the [Together API docs](https://docs.together.ai/reference) for provider-specific parameters.

<Info>Supports both **managed** (Lava's API keys) and **unmanaged** (bring your own credentials) mode.</Info>

## Quick Start

```typescript theme={null}
const response = await fetch('https://api.lava.so/v1/forward?u=https%3A%2F%2Fapi.together.xyz%2Fv1%2Fchat%2Fcompletions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: `Bearer ${forwardToken}`,
  },
  body: JSON.stringify({
    model: 'deepcogito/cogito-v2-1-671b',
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
```

## Chat Completions

**Target URL:** `https://api.together.xyz/v1/chat/completions`

| | |
| - | - |
| **Content Type** | `application/json` |
| **Streaming** | Yes (set `stream: true` in request body) |

| Model | Input / 1M tokens | Output / 1M tokens |
| - | - | - |
| deepseek-ai/DeepSeek-R1-0528 | \$3.00 | \$7.00 |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | \$2.00 | \$2.00 |
| deepseek-ai/DeepSeek-R1-Distill-Llama-70B | \$2.00 | \$2.00 |
| Qwen/Qwen2.5-VL-72B-Instruct | \$1.95 | \$8.00 |
| deepseek-ai/DeepSeek-V4-Pro | \$1.74 | \$3.48 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | \$1.60 | \$1.60 |
| zai-org/GLM-5.2 | \$1.40 | \$4.40 |
| deepcogito/cogito-v2-1-671b | \$1.25 | \$1.25 |
| Qwen/Qwen3.7-Max | \$1.25 | \$3.75 |
| moonshotai/Kimi-K2.6 | \$1.20 | \$4.50 |
| Qwen/QwQ-32B | \$1.20 | \$1.20 |
| Qwen/Qwen2-VL-72B-Instruct | \$1.20 | \$1.20 |
| Qwen/Qwen2.5-72B-Instruct-Turbo | \$1.20 | \$1.20 |
| moonshotai/Kimi-K2.7-Code | \$0.95 | \$4.00 |
| Qwen/Qwen2-72B-Instruct | \$0.90 | \$0.90 |
| meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | \$0.88 | \$0.88 |
| nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | \$0.88 | \$0.88 |
| meta-llama/Meta-Llama-3-70B-Instruct-Turbo | \$0.88 | \$0.88 |
| deepseek-ai/deepseek-coder-33b-instruct | \$0.80 | \$0.80 |
| Qwen/Qwen2.5-Coder-32B-Instruct | \$0.80 | \$0.80 |
| google/gemma-2-27b-it | \$0.80 | \$0.80 |
| nvidia/nemotron-3-ultra-550b-a55b | \$0.60 | \$3.60 |
| NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO | \$0.60 | \$0.60 |
| Qwen/Qwen3-VL-32B-Instruct | \$0.50 | \$1.50 |
| Qwen/Qwen3.6-Plus | \$0.50 | \$3.00 |
| Qwen/Qwen3-Coder-Next-FP8 | \$0.50 | \$1.20 |
| google/gemma-4-31B-it | \$0.39 | \$0.97 |
| Qwen/Qwen3.7-Plus | \$0.32 | \$1.28 |
| MiniMaxAI/MiniMax-M3 | \$0.30 | \$1.20 |
| MiniMaxAI/MiniMax-M2.7 | \$0.30 | \$1.20 |
| Qwen/Qwen2.5-7B-Instruct-Turbo | \$0.30 | \$0.30 |
| pearl-ai/gemma-4-31b-it | \$0.28 | \$0.86 |
| meta-llama/Meta-Llama-3-8B-Instruct | \$0.20 | \$0.20 |
| mistralai/Ministral-3-14B-Instruct-2512 | \$0.20 | \$0.20 |
| Qwen/Qwen3-235B-A22B-Instruct-2507-tput | \$0.20 | \$0.60 |
| meta-llama/Llama-3-8b-chat-hf | \$0.20 | \$0.20 |
| mistralai/Mistral-7B-Instruct-v0.1 | \$0.20 | \$0.20 |
| Qwen/Qwen3-VL-8B-Instruct | \$0.18 | \$0.68 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | \$0.18 | \$0.18 |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | \$0.18 | \$0.18 |
| Qwen/Qwen3.5-9B | \$0.17 | \$0.25 |
| openai/gpt-oss-120b | \$0.15 | \$0.60 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | \$0.15 | \$1.50 |
| Qwen/Qwen3-Next-80B-A3B-Thinking | \$0.15 | \$1.50 |
| meta-llama/Meta-Llama-3-8B-Instruct-Lite | \$0.14 | \$0.14 |
| mistralai/Mistral-Small-24B-Instruct-2501 | \$0.10 | \$0.30 |
| nvidia/NVIDIA-Nemotron-Nano-9B-v2 | \$0.06 | \$0.25 |
| google/gemma-3n-E4B-it | \$0.06 | \$0.12 |
| openai/gpt-oss-20b | \$0.05 | \$0.20 |
| LiquidAI/LFM2-24B-A2B | \$0.03 | \$0.12 |

## Embeddings

**Target URL:** `https://api.together.xyz/v1/embeddings`

| | |
| - | - |
| **Content Type** | `application/json` |
| **Streaming** | No |

| Model | Input / 1M tokens | Output / 1M tokens |
| - | - | - |
| Alibaba-NLP/gte-modernbert-base | \$0.08 | Free |
| intfloat/multilingual-e5-large-instruct | \$0.02 | Free |
| BAAI/bge-large-en-v1.5 | \$0.02 | Free |
| togethercomputer/m2-bert-80M-32k-retrieval | \$0.01 | Free |
| BAAI/bge-base-en-v1.5-vllm | \$0.01 | Free |
| BAAI/bge-base-en-v1.5 | \$0.01 | Free |

## Next Steps

<CardGroup cols={2}>
  <Card title="All Providers" icon="grid" href="/docs/gateway/supported-providers">
    Browse all supported AI providers
  </Card>

  <Card title="Forward Proxy" icon="route" href="/docs/gateway/forward-proxy">
    Learn how to construct proxy URLs and authenticate requests
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.