# Novita AI

Novita AI serves 43 models on LLM API: 42 text models and 1 video model from Z.ai, OpenAI, Alibaba and 6 other labs.

Model ID prefix: `novita/` (for text and image requests) · 43 models · 9 labs · [Novita AI privacy policy](https://novita.ai/legal/privacy-policy)
Updated: 2026-11-13
Canonical: https://llmapi.ai/providers/novita/

## Models and prices

Prices when Novita AI serves the request. A value in brackets is the price before the discount.

### Text (42)

Prices per 1M tokens.

| Model | Model ID | Input | Output | Cache read | Context |
| --- | --- | --- | --- | --- | --- |
| [GPT-6.1 Sol](https://llmapi.ai/models/gpt-6-1-sol/) | `novita/gpt-6.1-sol` | $2 | $10 | $0.1 | 1.05M |
| [GPT-6 Luna](https://llmapi.ai/models/openai-gpt-6-luna/) | `novita/gpt-6-luna` | $0.085 | $0.425 | $0.0085 | 1.05M |
| [DeepSeek V4.1 Flash 1017](https://llmapi.ai/models/deepseek-v4-1-flash-1017/) | `novita/deepseek-v4.1-flash-1017` | $0.3 | $1.2 | $0.006 | 1M |
| [DeepSeek V4 Pro](https://llmapi.ai/models/deepseek-deepseek-v4-pro/) | `novita/deepseek-v4-pro` | $1.6 | $3.2 | $0.135 | 1.05M |
| [Kimi K3](https://llmapi.ai/models/moonshotai-kimi-k3/) (−10%) | `novita/kimi-k3` | $2.7 (list $3) | $13.5 (list $15) | $0.27 (list $0.3) | 1.05M |
| [Qwen 3.8 Max](https://llmapi.ai/models/alibaba-qwen3-8-max/) | `novita/qwen3.8-max` | $2 | $6 | $0.17 | 1M |
| [GLM-5.3](https://llmapi.ai/models/zhipu-glm-5-3/) (−10%) | `novita/glm-5.3` | $1.26 (list $1.4) | $3.96 (list $4.4) | $0.234 (list $0.26) | 1M |
| [MiniMax-M3.1-Flash](https://llmapi.ai/models/minimax-m3-1-flash/) | `novita/MiniMax-M3.1-Flash` | $0.15 | $0.6 | $0.015 | 1M |
| [GPT-6 Sol](https://llmapi.ai/models/openai-gpt-6-sol/) | `novita/gpt-6-sol` | $1.7 | $8.5 | $0.085 | 1.05M |
| [DeepSeek V4.1 Flash](https://llmapi.ai/models/deepseek-deepseek-v4-1-flash/) | `novita/deepseek/deepseek-v4.1-flash` | $0.3 | $1.2 | $0.006 | 1M |
| [Gemini 3.8 Flash](https://llmapi.ai/models/google-gemini-3-8-flash/) | `novita/gemini-3.8-flash` | $0.6375 | $3.1875 | $0.0638 | 1.05M |
| [Gemini 3.7 Flash](https://llmapi.ai/models/google-gemini-3-7-flash/) | `novita/gemini-3.7-flash` | $0.6375 | $3.1875 | $0.0638 | 1.05M |
| [DeepSeek V4 Flash 0731](https://llmapi.ai/models/deepseek-v4-flash-0731/) | `novita/deepseek-v4-flash-0731` | $0.44 | $1.32 | $0.028 | 1M |
| [Gemini 3.5 Flash Lite](https://llmapi.ai/models/google-gemini-3-5-flash-lite/) | `novita/gemini-3.5-flash-lite` | $0.255 | $2.125 | $0.0255 | 1.05M |
| [Gemini 3.6 Flash](https://llmapi.ai/models/google-gemini-3-6-flash/) | `novita/gemini-3.6-flash` | $0.6375 | $3.1875 | $0.0638 | 1.05M |
| [GPT-5.6 Luna](https://llmapi.ai/models/openai-gpt-5-6-luna/) | `novita/gpt-5.6-luna` | $0.17 | $1.02 | $0.017 | 1.05M |
| [GPT-5.6 Sol](https://llmapi.ai/models/openai-gpt-5-6-sol/) | `novita/gpt-5.6-sol` | $3 | $15 | $0.375 | 1.05M |
| [GPT-5.6 Terra](https://llmapi.ai/models/openai-gpt-5-6-terra/) | `novita/gpt-5.6-terra` | $1.5 | $9 | $0.15 | 1.05M |
| [GLM 5.2](https://llmapi.ai/models/zhipu-zai-glm-5-2/) (−40%) | `novita/zai-glm-5.2` | $0.84 (list $1.4) | $2.64 (list $4.4) | $0.156 (list $0.26) | 1M |
| [Kimi K2.7-Code](https://llmapi.ai/models/moonshotai-kimi-k2-7-code/) | `novita/kimi-k2.7-code` | $0.95 | $4 | $0.19 | 262K |
| [MiniMax M3](https://llmapi.ai/models/minimax-m3/) | `novita/minimax-m3` | $0.3 | $1.2 | $0.06 | 1M |
| [Kimi K2.6](https://llmapi.ai/models/moonshotai-kimi-k2-6/) | `novita/kimi-k2.6` | $0.95 | $4 | $0.16 | 262K |
| [Gemma 4 31B IT](https://llmapi.ai/models/google-gemma-4-31b-it/) | `novita/gemma-4-31b-it` | $0.14 | $0.4 | — | 262K |
| [Gemma 4 26B A4B IT](https://llmapi.ai/models/google-gemma-4-26b-a4b-it/) | `novita/gemma-4-26b-a4b-it` | $0.13 | $0.4 | — | 262K |
| [GLM-5](https://llmapi.ai/models/z-ai-glm-5/) | `novita/glm-5` | $1 | $3.2 | $0.2 | 203K |
| [MiniMax M2.1](https://llmapi.ai/models/minimax-minimax-m2-1/) | `novita/minimax-m2.1` | $0.3 | $1.2 | — | 205K |
| [GLM-4.7](https://llmapi.ai/models/z-ai-glm-4-7/) | `novita/glm-4.7` | $0.6 | $2.2 | $0.11 | 205K |
| [GLM-4.6V](https://llmapi.ai/models/z-ai-glm-4-6v/) | `novita/glm-4.6v` | $0.3 | $0.9 | $0.055 | 131K |
| [Qwen3 VL 30B A3B Instruct](https://llmapi.ai/models/qwen-qwen3-vl-30b-a3b-instruct/) | `novita/qwen3-vl-30b-a3b-instruct` | $0.2 | $0.7 | — | 131K |
| [GLM-4.6](https://llmapi.ai/models/z-ai-glm-4-6/) | `novita/glm-4.6` | $0.55 | $2.2 | $0.11 | 205K |
| [Qwen3 Max](https://llmapi.ai/models/qwen-qwen3-max/) | `novita/qwen3-max` | $0.845 | $3.38 | $0.6 | 262K |
| [GLM-4.5V](https://llmapi.ai/models/zhipu-glm-4-5v/) | `novita/glm-4.5v` | $0.6 | $1.8 | $0.11 | 128K |
| [MiniMax M2.7](https://llmapi.ai/models/minimax-minimax-m2-7/) | `novita/minimax-m2.7` | $0.3 | $1.2 | $0.06 | 205K |
| [Qwen3 235B A22B Instruct 2507](https://llmapi.ai/models/alibaba-qwen3-235b-a22b-instruct-2507/) | `novita/qwen3-235b-a22b-instruct-2507` | $0.09 | $0.58 | — | 262K |
| [Qwen3 Coder 30B A3B Instruct](https://llmapi.ai/models/alibaba-qwen3-coder-30b-a3b-instruct/) | `novita/qwen3-coder-30b-a3b-instruct` | $0.07 | $0.27 | — | 262K |
| [MiniMax M2.5](https://llmapi.ai/models/minimax-minimax-m2-5/) | `novita/minimax-m2.5` | $0.3 | $1.2 | $0.03 | 205K |
| [MiniMax M2.5 Highspeed](https://llmapi.ai/models/minimax-m2-5-highspeed/) | `novita/minimax-m2.5-highspeed` | $0.6 | $2.4 | $0.03 | 205K |
| [Qwen3 235B A22B FP8](https://llmapi.ai/models/alibaba-qwen3-235b-a22b-fp8/) | `novita/qwen3-235b-a22b-fp8` | $0.2 | $0.8 | — | 41K |
| [Llama 4 Maverick 17B Instruct](https://llmapi.ai/models/meta-llama-llama-4-maverick-17b-instruct/) | `novita/llama-4-maverick-17b-instruct` | $0.27 | $0.85 | — | 1.05M |
| [Llama 4 Scout 17B Instruct](https://llmapi.ai/models/meta-llama-llama-4-scout-17b-instruct/) | `novita/llama-4-scout-17b-instruct` | $0.18 | $0.59 | — | 131K |
| [Llama 3.3 70B Instruct](https://llmapi.ai/models/meta-llama-llama-3-3-70b-instruct/) | `novita/llama-3.3-70b-instruct` | $0.135 | $0.4 | — | 131K |
| [Llama 3.1 8B Instruct](https://llmapi.ai/models/meta-llama-llama-3-1-8b-instruct/) | `novita/llama-3.1-8b-instruct` | $0.02 | $0.05 | — | 128K |

### Video (1)

Price per second of video; a range covers its resolutions.

| Model | Model ID | Per second | Generates from | Resolution |
| --- | --- | --- | --- | --- |
| [Dreamina-Seedance-2.5](https://llmapi.ai/models/dreamina-seedance-2-5-260628/) | `dreamina-seedance-2-5-260628` | $0.112–0.625 / second | Text, Image, Reference | 480p–1080p |

**Volume pricing.** At higher monthly volume, models on Novita 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 Novita AI

Put `novita/` before a model ID and the request goes to Novita AI. If Novita 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: GPT-6.1 Sol, 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="novita/gpt-6.1-sol",
    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)