# Available Models

The MaaS API provides full-accuracy access to model families such as Gemini, Anthropic, OpenAI, and others listed below.

### Danh sách mô hình

MaaS hỗ trợ nhiều loại mô hình khác nhau:

#### ***Chat***

| Model Name                     | Provider  | Rate Limit        |
| ------------------------------ | --------- | ----------------- |
| Claude Sonnet 4.0              | Anthropic | 50 requests / day |
| Claude 3.7 Sonnet              | Anthropic | 50 requests / day |
| Claude 3.5 Haiku               | Anthropic | 50 requests / day |
| Claude 3 Opus                  | Anthropic | 50 requests / day |
| Gemini 3.1 Pro Preview         | Google    | 50 requests / day |
| Gemini 2.5 Pro                 | Google    | 50 requests / day |
| Gemini 2.5 Flash               | Google    | 50 requests / day |
| Gemini 2.5 Flash Lite          | Google    | 50 requests / day |
| Gemini 2.0 Flash               | Google    | 50 requests / day |
| Gemini 2.0 Flash Lite          | Google    | 50 requests / day |
| gpt-5                          | OpenAI    | 50 requests / day |
| gpt-5-mini                     | OpenAI    | 50 requests / day |
| gpt-5-nano                     | OpenAI    | 50 requests / day |
| gpt-oss-120b                   | OpenAI    | 50 requests / day |
| gpt-oss-20b                    | OpenAI    | 50 requests / day |
| ChatGPT 4o                     | OpenAI    | 50 requests / day |
| ChatGPT 4o mini                | OpenAI    | 50 requests / day |
| ChatGPT 3.5 Turbo              | OpenAI    | 50 requests / day |
| DeepSeek Reasoner              | DeepSeek  | 50 requests / day |
| DeepSeek Chat                  | DeepSeek  | 50 requests / day |
| deepseek-r1-qwen3-8b           | DeepSeek  | 50 requests / day |
| Qwen3-235B-A22B-Thinking-2507  | Qwen      | 50 requests / day |
| Qwen3-235B-A22B-Instruct-2507  | Qwen      | 50 requests / day |
| Qwen3-VL-235B-A22B-Instruct    | Qwen      | 50 requests / day |
| qwen3-30b-a3b-thinking-2507    | Qwen      | 50 requests / day |
| qwen3-coder-plus-2025-07-22    | Qwen      | 50 requests / day |
| qwen3-coder-plus               | Qwen      | 50 requests / day |
| qwen3-coder-480b-a35b-instruct | Qwen      | 50 requests / day |
| qwen3-5-27b                    | Qwen      | 50 requests / day |
| ByteDance-Seed-1.6             | ByteDance | 50 requests / day |
| ByteDance-Seed-1.6-flash       | ByteDance | 50 requests / day |
| Skylark-pro                    | ByteDance | 50 requests / day |
| Skylark-vision                 | ByteDance | 50 requests / day |
| meta-llama-4-maverick          | Meta      | 50 requests / day |
| meta-llama-4-scout             | Meta      | 50 requests / day |
| meta-llama-3-8b                | Meta      | 50 requests / day |
| gemma-3-27b-it                 | Google    | 50 requests / day |
| nemotron-3-nano-30b-a3b        | NVIDIA    | 50 requests / day |
| GreenMind Medium 14B R1 Chat   | GreenNode | 50 requests / day |

#### *Generate Content*

| Model Name                     | Provider | Rate Limit        |
| ------------------------------ | -------- | ----------------- |
| Gemini 2.5 Pro (Native)        | Google   | 50 requests / day |
| Gemini 2.5 Flash (Native)      | Google   | 50 requests / day |
| Gemini 2.5 Flash Lite (Native) | Google   | 50 requests / day |

#### *Image Generation*

| Model Name  | Provider | Rate Limit      |
| ----------- | -------- | --------------- |
| GPT-image-1 | OpenAI   | 5 request / day |
| Dall-e-3    | OpenAI   | 5 request / day |
| Dall-e-2    | OpenAI   | 5 request / day |

#### *Completion*

| Model Name                 | Provider | Rate Limit        |
| -------------------------- | -------- | ----------------- |
| ChatGPT 3.5 Turbo Instruct | OpenAI   | 50 requests / day |

#### *Embedding*

| Model Name                     | Provider  | Rate Limit        |
| ------------------------------ | --------- | ----------------- |
| openai-text-embedding-3-large  | OpenAI    | 50 requests / day |
| openai-text-embedding-3-small  | OpenAI    | 50 requests / day |
| openai-text-embedding-ada-002  | OpenAI    | 50 requests / day |
| gemini-embedding-001           | Google    | 50 requests / day |
| qwen3-embedding-8b             | Qwen      | 50 requests / day |
| BGE-M3                         | BAAI      | 50 requests / day |
| GreenNode Embedding Large 1007 | GreenNode | 50 requests / day |

#### *Rerank*

| Model Name        | Provider | Rate Limit |
| ----------------- | -------- | ---------- |
| qwen3-reranker-8b | Qwen     |            |

#### *Text to Speech*

| Model Name                   | Provider | Rate Limit |
| ---------------------------- | -------- | ---------- |
| Gemini 2.5 Flash Preview TTS | Google   |            |

#### *Speech to Text*

| Model Name       | Provider | Rate Limit |
| ---------------- | -------- | ---------- |
| Whisper Large V3 | OpenAI   |            |

#### *OCR*

| Model Name    | Provider  | Rate Limit |
| ------------- | --------- | ---------- |
| GreenNode IDP | GreenNode |            |

Note:

* You can create [ticket](https://helpdesk.vngcloud.vn/portal/vi/newticket) for request new model


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.vngcloud.vn/vng-cloud-document/ai-stack/ai-platform/model-as-a-service/available-models.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.