The AI arena is free today

Open Superagent
MeituanReleased on Sep 22, 2025

LongCat-Flash-Thinking: API Pricing, Context Window & Benchmarks

LongCat-Flash-Thinking is a language model from Meituan, released in September 2025.

LongCat-Flash-Thinking is Meituan's reasoning model built on the LongCat-Flash foundation with 560B total parameters (MoE, ~27B activated). It introduces a training pipeline specifically tuned for advanced reasoning, featuring Re-thinking

Input
Text
Output
Text
Speed
Latency p953.00s
Throughput P95100char/s
Cost
$0.40/ 1M · 8:1 in:out
$0.30 in · $1.20 out

LongCat-Flash-Thinking benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

How LongCat-Flash-Thinking performs across real-world prompt categories.

Performance by conversation depth

How LongCat-Flash-Thinking holds up as conversations get longer.

Quality Tracker

LongCat-Flash-Thinking Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Mon Aug 24 2026
Notice missing or incorrect data?

LongCat-Flash-Thinking pricing

Providers

LongCat-Flash-Thinking starts at $0.300 per million input tokens and $1.20 per million output tokens via Meituan.

ProviderInput $/MCached input $/MOutput $/MContext in / outTTFT p95 sOutput p5 c/sModalities in / out
Meituan logoMeituan
$0.300—$1.20128.0K/128.0K
3.00
—
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

LongCat-Flash-Thinking model size

LongCat-Flash-Thinking has 560 billion parameters. See how it compares to other models in the same parameter range.

Parameters
560BMoE
Frontier (200B+)
560B
1B7B70B405B

LongCat-Flash-Thinking context window

Input and output token limits for LongCat-Flash-Thinking, plus how it ranks on long-context understanding.

InputOutput
128Ktokens
128Ktokens
≈ 192 pages of text
128K
8K128K1M

LongCat-Flash-Thinking API

Available from the model provider

LongCat-Flash-Thinking has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

LongCat-Flash-Thinking latency

LongCat-Flash-Thinking time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

LongCat-Flash-Thinking examples

Recent arena outputs from LongCat-Flash-Thinking, picked from the highest-ranked matchups.

LongCat-Flash-Thinking license

LongCat-Flash-Thinking is released under the MIT license, which permits commercial use, has 560.0B parameters.

License
MIT
Commercial use allowed
Parameters
560.0B

MIT License - allows commercial use

LongCat-Flash-Thinking resources

Official sources for LongCat-Flash-Thinking: api documentation, official playground, paper or system card, source repository, model weights.

LongCat-Flash-Thinking vs other models

The most-compared alternatives to LongCat-Flash-Thinking are Grok-3 Mini, Nova 2 Pro, LongCat-Flash-Chat. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like LongCat-Flash-Thinking

Models ranked just above and below LongCat-Flash-Thinking by LLM Stats score.

 

Grok-3 Mini

Score pending
DetailsCompare
 

Nova 2 Pro

Score pending
DetailsCompare
 

LongCat-Flash-Chat

Score pending
DetailsCompare
 

Gemma 4 26B-A4B

Score pending
DetailsCompare
 

Qwen3.5-9B

Score pending
DetailsCompare
 

Nova 2 Lite

Score pending
DetailsCompare

FAQ

Common questions about LongCat-Flash-Thinking.

When was LongCat-Flash-Thinking released?

LongCat-Flash-Thinking was released on September 22, 2025 by Meituan. This is the official LongCat-Flash-Thinking release date tracked on LLM Stats.

How much does LongCat-Flash-Thinking cost?

LongCat-Flash-Thinking pricing starts at $0.30 per million input tokens and $1.20 per million output tokens via Meituan, the lowest price among tracked providers.

Is LongCat-Flash-Thinking available via API?

Yes, LongCat-Flash-Thinking is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

How big is LongCat-Flash-Thinking?

LongCat-Flash-Thinking has 560 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created LongCat-Flash-Thinking?

LongCat-Flash-Thinking was created by Meituan.

What is the license for LongCat-Flash-Thinking?

LongCat-Flash-Thinking is released under the MIT license. This is an open-source / open-weight license that permits self-hosting.

What is LongCat-Flash-Thinking latency?

LongCat-Flash-Thinking p95 time to first token is 3.00 seconds via Meituan over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and API workloads.

Where can I use LongCat-Flash-Thinking?

LongCat-Flash-Thinking is available through 1 provider including Meituan.

Where is the LongCat-Flash-Thinking paper or technical report?

LongCat-Flash-Thinking has a paper or technical report available at https://arxiv.org/abs/2509.18883. Use that source for architecture, training, release and evaluation details.

What models should I compare LongCat-Flash-Thinking against?

Common LongCat-Flash-Thinking comparisons include LongCat-Flash-Thinking vs Grok-3 Mini, LongCat-Flash-Thinking vs Nova 2 Pro, LongCat-Flash-Thinking vs LongCat-Flash-Chat. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.