# Together AI

Together AI serves 13 models on LLM API: 9 text models and 4 image models from Alibaba, DeepSeek, Moonshot AI and 5 other labs.

Model ID prefix: `togetherai/` · 13 models · 8 labs · [Together AI privacy policy](https://www.together.ai/privacy)
Updated: 2026-11-13
Canonical: https://llmapi.ai/providers/together-ai/

## Models and prices

Prices when Together AI serves the request.

### Text (9)

Prices per 1M tokens.

| Model | Model ID | Input | Output | Cache read | Context |
| --- | --- | --- | --- | --- | --- |
| [DeepSeek V4.1 Flash 1017](https://llmapi.ai/models/deepseek-v4-1-flash-1017/) | `togetherai/deepseek-v4.1-flash-1017` | $0.3 | $1.2 | $0.006 | 1M |
| [Kimi K3.1 Pro](https://llmapi.ai/models/kimi-k3-1-pro/) | `togetherai/kimi-k3.1-pro` | $2 | $10 | $0.2 | 1.05M |
| [Kimi K3](https://llmapi.ai/models/moonshotai-kimi-k3/) | `togetherai/kimi-k3` | $3 | $15 | $0.3 | 1.05M |
| [GLM-5.3](https://llmapi.ai/models/zhipu-glm-5-3/) | `togetherai/glm-5.3` | $1.4 | $4.4 | $0.26 | 1.05M |
| [MiniMax-M3.1-Flash](https://llmapi.ai/models/minimax-m3-1-flash/) | `togetherai/MiniMax-M3.1-Flash` | $0.15 | $0.6 | $0.015 | 1M |
| [Inkling 2 Small](https://llmapi.ai/models/inkling-2-small/) | `togetherai/inkling-2-small` | $0.3 | $1 | $0.03 | 262K |
| [DeepSeek V4.1 Flash](https://llmapi.ai/models/deepseek-deepseek-v4-1-flash/) | `togetherai/deepseek/deepseek-v4.1-flash` | $0.3 | $1.2 | $0.006 | 1M |
| [Qwen 3.5 9B](https://llmapi.ai/models/qwen-qwen3-5-9b/) | `togetherai/qwen3.5-9b` | $0.1 | $0.15 | — | 262K |
| [GPT OSS 120B](https://llmapi.ai/models/openai-gpt-oss-120b/) | `togetherai/gpt-oss-120b` | $0.15 | $0.6 | $0.15 | 131K |

### Image (4)

Price per image.

| Model | Model ID | Price | Modes |
| --- | --- | --- | --- |
| [Qwen Image 2.0](https://llmapi.ai/models/alibaba-qwen-image-2-0/) | `togetherai/qwen-image-2.0` | $0.04 / image | Generate |
| [Qwen Image 2.0 Pro](https://llmapi.ai/models/alibaba-qwen-image-2-0-pro/) | `togetherai/qwen-image-2.0-pro` | $0.08 / image | Generate |
| [Gemini 3 Pro Image](https://llmapi.ai/models/google-gemini-3-pro-image/) | `togetherai/gemini-3-pro-image` | $0.134 / image | Generate, Edit |
| [Gemini 2.5 Flash Image](https://llmapi.ai/models/google-gemini-2-5-flash-image/) | `togetherai/gemini-2.5-flash-image` | $0.039 / image | Generate, Edit |

**Volume pricing.** At higher monthly volume, models on Together AI may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Send requests to Together AI

Put `togetherai/` before a model ID and the request goes to Together AI. If Together AI’s uptime over the last 5 minutes is below 90%, it goes to another provider of the model, unless it sends `X-No-Fallback: true`. [Routing docs](https://docs.llmapi.ai/features/routing)

Example: DeepSeek V4.1 Flash 1017, Chat Completions (`POST /v1/chat/completions`). Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="togetherai/deepseek-v4.1-flash-1017",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

Prices synced 2026-11-13.

Next step: [Get API key](https://app.llmapi.ai/signup)