LongCat 2.5 Preview

meituan/longcat-2.5-preview

A chat model with a 1M-token context window, at $0.315 per million input tokens and $1.26 per million output tokens.

Details

Maker: meituan
Kind: Chat
Context window: 1,048,576 tokens
Max output: 131,072 tokens
Input: $0.315 per million tokens
Cached input: $0.0063 per million tokens, 98% off
Cache write: Same as input
Output: $1.26 per million tokens
Capabilities: Reasoning, tool use, vision
Takes: Text, image
Returns: Text
Zero data retention: Not on every provider
No training on requests: Not on every provider
Released: 2026-09-26

Description

LongCat-2.5-Preview is Meituan’s multimodal reasoning model for coding and agentic workflows, with a 1M-token context window and support for text and image inputs. It combines image understanding, visual question answering, and content summarization with code generation, code understanding, and automated programming, and supports tool calling and optional thinking for complex tasks.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meituan/longcat-2.5-preview",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model