Which models does LMU AI support?

The full Claude line (claude-opus-5, claude-fable-5, claude-sonnet-5, claude-haiku-4-5, and more), the OpenAI GPT-5.6 series (gpt-5.6-sol / terra / luna), and Chinese LLMs such as Qwen, DeepSeek, MiniMax, Zhipu GLM, Moonshot Kimi, and Xiaomi MiMo, plus GPT / Gemini / Grok image models. One API key calls them all.

Where do I find a model ID and how do I use it?

Click any model card on this page to copy its model ID, or use the plain-text list at the bottom for bulk copying. Then paste it into your tool's config: the model field in Claude Code's settings.json, the model in Codex CLI's ~/.codex/config.toml, or the model box of a GUI tool like Cursor or Chatbox.

Which are the current flagship models?

On the Claude side, claude-opus-5 (flagship) and claude-sonnet-5 (balanced); on the OpenAI side, gpt-5.6-sol; among Chinese LLMs, qwen3.8-max-preview, deepseek-v4-pro, glm-5.2, and kimi-k3. Newly launched models are marked New on their card.

Why can't my account call a certain model?

The actual available range is whatever the Available Models page in the LMU AI console shows; it differs by plan and billing group. For example, the GPT series requires a GPT subscription, or selecting a GPT group under pay-as-you-go billing.

Model Gallery

The full list of models available on the LMU AI API (Chinese LLMs / Claude / OpenAI). Click a model name to copy its ID and paste it into your tool config.

Below are all the model names the LMU AI API currently supports. Click any card to copy its model ID, then paste it straight into settings.json, config.toml, or a tool's model selector.

How to use a model name

Paste the copied model ID into your tool's config:

Claude Code → the "model" field in settings.json
Codex CLI → model = "..." in ~/.codex/config.toml
Cherry Studio / VS Code extension → paste into the model dropdown

Pick a model by use case

Not sure which model to use? Locate it in the table below, then copy the model ID from the matching section.

Use case	Recommended models	Why
Complex refactors, large cross-file changes	`claude-opus-5`	Claude's flagship tier, outstanding at code and long text, the default for Claude Code
Everyday coding, bug fixing	`claude-sonnet-5` · `claude-sonnet-4-6`	Balanced tier, a trade-off between capability and speed, ideal for frequent daily use
Frequent lightweight tasks (completion, formatting, bulk small edits)	`claude-haiku-4-5` · `deepseek-v4-flash` · `qwen3.6-flash`	High-speed tier, for simple single tasks called many times
Codex CLI / Codex App toolchain	`gpt-5.6-sol` · `gpt-5.4`	The latest flagship on the OpenAI side and the default in the Codex CLI config template
Chinese writing, documentation, conversation	`qwen3.8-max-preview` · `glm-5.2` · `kimi-k3`	Chinese LLMs with excellent Chinese comprehension at a lower price
Coding in Chinese contexts	`qwen3.6-plus` · `deepseek-v4-pro`	Code-oriented Chinese models, callable directly with the account balance
Multimodal (mixed image + text input)	`mimo-v2-omni`	The only conversational model marked multimodal here; for pure image generation see the image APIs below

Confirm two things before choosing

Model availability depends on the group: which models you can actually call is whatever the Available Models page in the console shows. For example, the GPT series requires a GPT subscription, or selecting a GPT group under pay-as-you-go billing. This is independent of which protocol you call with.
The Base URL must match the protocol: the protocol is decided by your client and SDK — the Anthropic protocol Base URL is without /v1, the OpenAI protocol must include /v1, and Gemini native uses /v1beta/models/.... Getting it wrong gives an outright 404; see API Protocols.

Chinese models

Excellent Chinese comprehension at a lower price, ideal for everyday coding, documentation, and conversation. Like Claude and GPT, Chinese models can all be called using the account balance.

Protocol: defaults to the Anthropic protocol · Base URL https://api.lmuai.com (without /v1). See API Protocols →

Alibaba · Qwen

DeepSeek

MiniMax

Zhipu · GLM

Moonshot · Kimi

Xiaomi · MiMo

Claude models

Anthropic's official models, outstanding at code and long text, the default for Claude Code.

Protocol: the Anthropic protocol is recommended · Base URL https://api.lmuai.com (without /v1). The OpenAI protocol also works; the backend translates the protocol.

OpenAI models

The OpenAI GPT-5 series, for Codex CLI, Codex App, and any tool that supports the OpenAI protocol.

Protocol: the OpenAI protocol · Base URL https://api.lmuai.com/v1 (must include /v1).

All model IDs (plain text)

For on-site search and bulk copying

Claude series: claude-opus-5, claude-fable-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-opus-4-5, claude-sonnet-5, claude-sonnet-4-6, claude-sonnet-4-5, claude-haiku-4-5

OpenAI series: gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.5, gpt-5.4, gpt-5.2

Qwen: qwen3.8-max-preview, qwen3.7-max, qwen3.6-plus, qwen3.6-flash, qwen3.5-plus, qwen3-max-2026-01-23

DeepSeek: deepseek-v4-pro, deepseek-v4-flash, deepseek-v3.2

MiniMax: MiniMax-M2.7, MiniMax-M2.7-highspeed, MiniMax-M2.5, MiniMax-M2.5-highspeed

Zhipu GLM: glm-5.2, glm-5.1, glm-5

Moonshot Kimi: kimi-k3, kimi-k2.6, kimi-k2.5

Xiaomi MiMo: mimo-v2.5-pro, mimo-v2.5, mimo-v2-pro, mimo-v2-omni

For image models see GPT Image, Gemini Image, and Grok Image.

Note

The actual available models are whatever the Available Models page in the LMU AI console shows; the range may differ by plan.
If you have questions about model selection, see the FAQ.

Last updated: 2026-08-26