longcat-2.0

by Meituan

Designed for agent development scenarios, it natively supports tool invocation, multi-step reasoning, and long-context tasks; it excels at code generation, automated workflows, and executing complex instructions; and it is deeply adapted to productivity tools such as Claude Code, OpenClaw, OpenCode, and Kilo Code.

API Pricing

Input$0.77 / 1M tokens
Output$3.1 / 1M tokens
Cache read$0.02 / 1M tokens

Specifications

Modalitiestext
Featuresthinking, tool calling

FAQ

What is longcat-2.0?

Designed for agent development scenarios, it natively supports tool invocation, multi-step reasoning, and long-context tasks; it excels at code generation, automated workflows, and executing complex instructions; and it is deeply adapted to productivity tools such as Claude Code, OpenClaw, OpenCode, and Kilo Code.

How much does longcat-2.0 cost?

On AIHubMix, longcat-2.0 costs $0.77 per million input tokens and $3.1 per million output tokens. Cached input reads are billed at $0.02 per million tokens.

What modalities does longcat-2.0 support?

longcat-2.0 accepts text input.

What features does longcat-2.0 support?

longcat-2.0 supports thinking and tool calling. Per-protocol parameter support is listed in the capability table on this page.

How do I call longcat-2.0 via API?

longcat-2.0 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to longcat-2.0 — no other code changes needed.

Who develops longcat-2.0?

longcat-2.0 is developed by Meituan. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More from Meituan

LongCat-Flash-Chat

by Meituan

Meituan has officially released and open-sourced LongCat-Flash-Chat, which utilizes an…

$0.14/1M in · $0.7/1M out

Use longcat-2.0 via the AIHubMix unified API — one interface for every major LLM.