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.
longcat-2.0Released 20 Jul 2026 (Jul 2026)Pricing
List prices at AIHubMix, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.775 | $3.10 | |
| Cached input 98% off input | $0.0155 | 98% off input |
What it costs a month
At AIHubMix list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$396
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$301
- Coding agent1,000 requests a day, 40K in / 2K out, cached$478
- Overnight batch20,000 requests a day, 4K in / 0.4K out$2,603
Where to run it
2 hosts serve Longcat 2.0. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenCode GoCloud longcat-2.0 | $0.30 / $1.20 −61% vs headline | longcat-2.0 | |
AIHubMixGateway longcat-2.0 | $0.775 / $3.10 | longcat-2.0 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: MITRuns in about 4261.3 GB of GPU memory
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
- OpenCode Go61% lesslongcat-2.0$0.30 / $1.20
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 8% less
- 37% less
- 66% less
- 85% less
Open-weight picks
- 35% less
- 37% less
- 42% less
- 49% less
Call it
Using AIHubMix's API.
from litellm import completion
response = completion(
model="aihubmix/longcat-2.0",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Longcat 2.0 cost?
On AIHubMix, Longcat 2.0 costs $0.775 per million input tokens and $3.10 per million output tokens. Cached input costs $0.0155 per million tokens. The cheapest host is OpenCode Go, at $0.30 per million input tokens and $1.20 per million output tokens.
Which APIs offer Longcat 2.0?
Longcat 2.0 runs on 2 APIs: OpenCode Go and AIHubMix.
What is Longcat 2.0's context window?
1M tokens, with up to 131K tokens in one reply.
Is Longcat 2.0 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Longcat 2.0?
Models that cost less and keep most of what it can do: Grok Build 0.1 on xAI (8% less), Gemini 3.5 Flash Lite on Google AI Studio (37% less) and Motif 3 on ai& (35% less). Longcat 2.0 itself costs 61% less on OpenCode Go. Savings are on a mix of 3 input tokens to 1 output token.
When was Longcat 2.0 released?
Independent released it on 20 Jul 2026.
What is Longcat 2.0's API model id?
Use longcat-2.0 with AIHubMix.
Sources
Raw catalog entry for longcat-2.0 on AIHubMix
{
"cache_read_input_token_cost": 1.5492e-8,
"input_cost_per_token": 7.746e-7,
"litellm_provider": "aihubmix",
"max_input_tokens": 1000000,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.0000030984,
"source": "https://aihubmix.com/api/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
}