> For the complete documentation index, see [llms.txt](https://docs.meganova.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.meganova.ai/faq/models-and-providers.md).

# Models and Providers

### What models are supported on MegaNova, and how do I pick one?

MegaNova hosts 100+ models across text, multimodal, vision, image, video, audio, and embeddings — including Claude, GPT-5, Gemini, Grok, Qwen, DeepSeek, Mistral, Llama, MiMo, MiniMax, GLM, Kimi, and MegaNova's own Manta series. Browse the full catalog on the [Model List](/inference-models/model-list.md) page.

**A few starting points by use case:**

* **Character / dialogue apps** — Manta series (free), L3-70B-Euryale-v2.1 (free), L3.3-MS-Nevoria-70B (free), Claude Sonnet 4.6, Gemini 2.5 Flash
* **Coding / agents** — GPT-5.3-Codex, Claude Opus 4.7, DeepSeek-V3.2, GLM-5.1
* **Vision / multimodal** — Qwen3-VL-Plus, Gemini 2.5 Pro, GPT-5, Claude Opus 4.7
* **Cost-efficient general chat** — Mistral-Small-3.2-24B (free), DeepSeek-V3.2, GLM-4.7, MiMo-V2-Flash
* **Image generation** — Nano-Banana-Pro, Bytedance Seedream 5.0 Lite, Alibaba Z-Image-Turbo

Switch models at runtime via the `model` field in your API call — no config changes needed.

### What makes Manta models unique?

Manta is MegaNova's adaptive-routing model series: a pre-generation router picks the smallest sufficient tier (Mini / Flash / Pro) for each request, so simple turns stay fast and cheap while complex ones escalate when needed. It's optimized for dialogue depth and long-context memory, and includes a paid-fallback mode that keeps requests flowing after your free daily quota is exhausted.

### What are Manta model variants, and how do I use them?

**Manta Model Variants:**

* **`meganova-ai/manta-mini-1.0` (free)**: Lightweight, fast — ideal for quick responses and interactive chat
* **`meganova-ai/manta-flash-1.0` (free)**: Balanced performance with deeper context — the default choice for most apps
* **`meganova-ai/manta-pro-1.0` (free)**: Advanced memory and long context — for complex, long-running conversations

All three are free to call. With [paid auto-switch](/api-reference/platform-api/usage/paid-model-auto-switch.md) enabled, requests continue uninterrupted on a paid fallback once your daily quota runs out. Use the full model ID in API calls (e.g., `meganova-ai/manta-mini-1.0`).

> **Free Model Limits:** Free models have daily usage limits and are intended for evaluation and interactive use only, not production workloads.

### What tasks does MegaNova support?

Text generation, chat, vision (image understanding), image generation, image editing, video generation, text-to-speech, speech-to-text, embeddings, and reranking — all through OpenAI-compatible endpoints.

> **Usage Guidelines:** All usage must comply with our [Terms of Service](/legal-docs/terms-of-service.md) and [Privacy Policy](/legal-docs/privacy-policy.md). Ensure your use case aligns with our acceptable use policies.

### How frequently are new models added?

We're continuously working to add new models as quickly as possible. Thanks to our partnerships with the labs behind these models, we're often able to release them as soon as they become available. If there's a specific model you'd like to see supported on MegaNova, feel free to reach out to us on Discord!

### I am an inference provider, how can I get listed on MegaNova?

If you would like to contact us, the best place to reach us is over email (`contact@meganova.ai`)