LongCat 2.0 pricing, context and benchmark
LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total.
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | LongCat 2.0 |
| Model ID | meituan/longcat-2.0 |
| Provider | Meituan |
| Release date | 20 July 2026 |
| Status | Generally available |
| Input context | 1,048,756 tokens |
| Output context | 262,144 tokens |
| Official input pricing | $0.3 per 1M tokens |
| Official output pricing | $1.2 per 1M tokens |
| Cache read pricing | $0.015 per 1M tokens (98% off input) |
| Market input pricing | $0.3 per 1M (cheapest route) |
| Market output pricing | $1.2 per 1M (cheapest route) |
| Input modalities | text |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Other |
| Provider routes | 1 endpoint |
| Artificial Analysis index | Not published |
| Speed | 56 tokens/s, 31.32s to first token |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.3 in |
| Image | no | no | not supported |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
What is LongCat 2.0?
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...
LongCat 2.0 carries a 1.05M token window, uses the Other tokenizer and is served by Meituan. On Hoodgen it sits in the Coding tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
Release and what changed from the previous version
This is the only release of LongCat 2.0 on OpenRouter, released 20 July 2026. The provider has not published a knowledge cutoff, so treat training data as recent but unconfirmed for very new events.
Features and capabilities
What can you do with LongCat 2.0?
Prompt caching and how to cut the bill
Cached input bills at $0.015 per million instead of $0.3, a 98% discount. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
LongCat 2.0 pricing
Official pricing
- $0.015 cached input
- 1.05M context
- text input
- 1 route on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| AtlasCloud | standard | $0.3 | $1.2 | $0.006 | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0043 | $2.14 | 2030 |
| List price | $0.0044 | $2.19 | 2081 |
API and developer information
| Model ID | meituan/longcat-2.0 |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text->text |
| Max prompt tokens | 1,048,756 |
| Max completion tokens | 262,144 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meituan/longcat-2.0",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 262,144 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
LongCat 2.0 vs other Meituan models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| LongCat 2.0 | 1.05M | $0.3 | $1.2 | n/a | 2026 |
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Meituan and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
LongCat 2.0 questions, answered
Start chatting with LongCat 2.0
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.