# Nebius

Nebius serves 6 text models on LLM API from Moonshot AI, Alibaba, Z.ai and 1 other lab.

Model ID prefix: `nebius/` · 6 models · 4 labs · [Nebius privacy policy](https://docs.nebius.com/legal/privacy)
Updated: 2026-11-13
Canonical: https://llmapi.ai/providers/nebius/

## Models and prices

Prices when Nebius serves the request.

### Text (6)

Prices per 1M tokens.

| Model | Model ID | Input | Output | Cache read | Context |
| --- | --- | --- | --- | --- | --- |
| [Kimi K3.1 Pro](https://llmapi.ai/models/kimi-k3-1-pro/) | `nebius/kimi-k3.1-pro` | $2 | $10 | $0.2 | 1.05M |
| [Kimi K3](https://llmapi.ai/models/moonshotai-kimi-k3/) | `nebius/kimi-k3` | $3 | $15 | $3 | 1.05M |
| [GLM 5.2](https://llmapi.ai/models/zhipu-zai-glm-5-2/) | `nebius/zai-glm-5.2` | $1.4 | $4.4 | $0.26 | 1M |
| [MiniMax M3](https://llmapi.ai/models/minimax-m3/) | `nebius/minimax-m3` | $0.3 | $1.2 | $0.06 | 1.05M |
| [Qwen3 30B A3B Instruct 2507](https://llmapi.ai/models/alibaba-qwen3-30b-a3b-instruct-2507/) | `nebius/qwen3-30b-a3b-instruct-2507` | $0.1 | $0.3 | — | 262K |
| [Qwen3 235B A22B Instruct 2507](https://llmapi.ai/models/alibaba-qwen3-235b-a22b-instruct-2507/) | `nebius/qwen3-235b-a22b-instruct-2507` | $0.2 | $0.6 | — | 262K |

**Volume pricing.** At higher monthly volume, models on Nebius 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 Nebius

Put `nebius/` before a model ID and the request goes to Nebius. If Nebius’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: Kimi K3.1 Pro, 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="nebius/kimi-k3.1-pro",
    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)