LLM Reference

Using LongCat-2.0 on LongCat API Platform

Implementation guide · LongCat · Meituan

ServerlessOpen Source

Quick Start

  1. 1
    Create an account at LongCat API Platform and generate an API key.
  2. 2
    Use the LongCat API Platform SDK or REST API to call LongCat-2.0 — see the documentation for request format.
  3. 3
    You'll be billed $0.75/1M input, $2.95/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See LongCat API Platform documentation for integration details.

About LongCat API Platform

LongCat API Platform provides public API access to LongCat-2.0 with OpenAI and Anthropic API formats, including a 1M token context window and up to 128K output tokens for LongCat-2.0. The platform supports pay-as-you-go billing and token packs for LongCat-2.0.

LongCat API Platform is Meituan's public model API service. It serves LongCat-2.0 through OpenAI-compatible chat completions and Anthropic-compatible messages endpoints.

View all models on LongCat API Platform →

Pricing on LongCat API Platform

TypePrice (per 1M)
Input tokens$0.75
Output tokens$2.95

Capabilities

ReasoningFunction CallingTool UsePrompt Caching

About LongCat-2.0

LongCat-2.0 is Meituan's large-scale MoE language model for coding, long-context, and agentic tasks. The model has 1.6T total parameters, roughly 48B activated per token, native 1M context support, and API access through OpenAI- and Anthropic-compatible LongCat endpoints. Public MIT-licensed safetensors weights are downloadable from Hugging Face, with Transformers, vLLM, and SGLang deployment support.

Full model details →

Model Specs

Released2026-06-30
Parameters1.6T total; ~48B active
Context1m
ArchitectureMixture of Experts

Provider

LongCat API Platform

Meituan

Beijing, China