LongCat 2.5 Preview is Meituan's multimodal model for long-context analysis, coding, and agent workflows. It supports image input, tool calling, optional extended thinking, a 1M-token context window, and up to 128K output tokens.
Added Sep 27, 2026
Context Window
1M
Max Output
131.1K
Input Price (Auto)
$0.75/1M
Output Price (Auto)
$2.95/1M
Cache Read (Auto)
$0.015/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
No benchmark data is available yet for this model.
Providers
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare LongCat 2.5 Preview with similar models from the same provider or model family.
LongCat 2.0 Thinking
longcat-2.0:thinkingMeituan's LongCat 2.0 Thinking is the reasoning-enabled variant for harder coding, tool use, multi-step reasoning, and long-context agent workflows.
LongCat 2.0
longcat-2.0Meituan's LongCat 2.0 is an open-weight agentic model for coding, tool use, and long-context workflow automation, with reasoning disabled for faster direct answers.
MiMo V2.6 Flash Uncensored Thinking
xiaomi/mimo-v2.6-flash-uncensored:thinkingMiMo V2.6 Flash Uncensored with maximum thinking enabled. Supports a 1M-token context window and tool calling.
GLM 5.3 Uncensored
z-ai/glm-5.3-uncensoredAn experimental uncensored version of the full GLM 5.3 reasoning model for chat, creative writing, coding, and tool use. It may show unusual behavior or inconsistent response quality.
Perceptron Mk1.5
perceptron/perceptron-mk1.5Perceptron Mk1.5 is a multimodal reasoning model for visual analysis and physical agents. It accepts text, images, video, and audio, supports tool calling and structured output, and can return spatial annotations such as points, boxes, polygons, and tracks.
Qwen3.8 27B Uncensored TEE
TEE/qwen3.8-27b-uncensoredHauhauCS's Aggressive finetune of Qwen3.8 27B reduces refusal behavior for creative writing, coding, and image analysis. It supports reasoning, tool calling, and structured output with a 262K-token context. Runs inside a TEE (Trusted Execution Environment), with provider attestation support.