meituan Open weights Reasoning

LongCat 2.0 pricing & benchmarks

Released Jul 20, 2026 · served by 1 provider

Input / 1M tokens$0.300
Output / 1M tokens$1.20
Context window1.0M
Cached input$0.0060
1M in + 300K out$0.66

What LongCat 2.0 is

LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...

Providers and prices for LongCat 2.0

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
AtlasCloudcheapest $0.300 $1.20 1.0M fp8 100.0%

FAQ

How much does the LongCat 2.0 API cost?

$0.300 per 1M input tokens and $1.20 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.66.

Is LongCat 2.0 free?

No. It is a paid model starting at $0.300 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for LongCat 2.0?

AtlasCloud at $0.300 input / $1.20 output per 1M tokens (fp8 quantization).

Can I self-host LongCat 2.0?

Yes — weights are published as meituan-longcat/LongCat-2.0 on Hugging Face, so you can run it on your own hardware.