How to Use LongCat 2.0 in Hermes
LongCat 2.0 is built for understanding code, editing repositories, and completing tasks across multiple steps. Its 1M-token context supports work that combines a large codebase with migration docs.
Prompts to try with LongCat 2.0 in Hermes
Copy an example into Hermes, or ask in your own words.
Every weekday, use LongCat 2.0 to review new issue descriptions available through your connected tools. Identify likely duplicates, summarize reproduction steps, and rank issues by documented user impact.
Each morning, use LongCat 2.0 to compare the latest service report with the previous seven reports. Highlight changes that warrant investigation, cite the supporting figures, and separate observations from possible explanations.
Every Friday, use LongCat 2.0 to review the published release notes for our tracked dependencies. Summarize breaking changes and draft a migration checklist with links to the relevant documentation.
Each week, use LongCat 2.0 to research updates on the technical topics in our watchlist. Produce a brief with source links, conflicting claims, and questions that remain unanswered.
Every evening, use LongCat 2.0 to review today's failed automation runs through your connected tools. Compare error messages, identify recurring patterns, and prepare a short investigation queue with evidence for each item.
How to set up LongCat 2.0 in Hermes
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Hermes this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Add the server and sign in
Hermes opens your browser: sign in to Spiral and click Authorize. No API key. When Hermes asks Enable all tools? \[Y/n/select], answer Y: n cancels without saving the server, and select hides the tools you leave out.
hermes mcp add spiral \ --url https://api.spiral.ai/mcp \ --auth oauth \ --connect-timeout 300
- Check it
In a chat that was already open, run /reload-mcp.
hermes mcp list hermes mcp test spiral
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run LongCat 2.0
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "openrouter", "model": "meituan/longcat-2.0", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Hermes finds LongCat 2.0 on Spiral, shows the price and runs it.
LongCat 2.0 providers and prices
Spiral runs LongCat 2.0 through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.006404 per run at the default inputs. $0.39 per 1M input tokens, $1.56 per 1M output tokens.
Settings you can ask for
Ask Hermes for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 262144 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Meituan: LongCat 2.0 is on its tool page: open its card above.
What can you do with LongCat 2.0 in Hermes?
LongCat 2.0 can support recurring reviews that compare new information with earlier results and identify follow-up work. Define the evidence to inspect, the reporting threshold, and the format of each report.
Migrate a plugin to a new SDK
Provide the current implementation and migration documentation. Ask for an architecture map, required changes, and checks that existing behavior still works.
Fix a bug across several modules
Trace a reported failure through the relevant code, identify the cause, and request a focused patch with a regression test.
Explain an unfamiliar codebase
Map entry points, dependencies, and the path a request takes through the code. Ask for references to the implementation behind each explanation.
Build a small web prototype
Turn a written specification into application code. Define the screens, interactions, and acceptance checks before requesting implementation.
Produce a research brief
Have an agent gather evidence across several sources, reconcile conflicting claims, and produce a brief with citations and unresolved questions.
Work through a technical analysis
Supply assumptions, equations, and constraints. Request a solution with units, intermediate results, and a check against the original requirements.
Review recurring operational reports
Compare the current report with earlier results, identify changes that deserve investigation, and prepare a short evidence-based review.
More on LongCat 2.0 and Hermes
Overview
LongCat 2.0 in other agents
Questions about LongCat 2.0 in Hermes
Can Hermes use LongCat 2.0?
Yes. Add Spiral to Hermes as an MCP server, and Hermes can find and run LongCat 2.0 like any built-in tool.
How much does LongCat 2.0 cost in Hermes?
Up to $0.006404 per run at the default inputs. $0.39 per 1M input tokens, $1.56 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Hermes plan is separate.
Do I need an OpenRouter account to use LongCat 2.0 in Hermes?
No. Spiral runs LongCat 2.0 on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up LongCat 2.0 in Hermes?
About two minutes: add the server and sign in, then check it.
Does Hermes wait while LongCat 2.0 runs?
LongCat 2.0 runs in the background. Hermes starts the run, checks on it and gives you the text, json when it's ready.
What is LongCat 2.0 best suited for?
Code understanding, repository edits, and tasks that require several steps. Give it a concrete result to produce, such as a tested patch or a migration plan.
How much context can LongCat 2.0 handle?
Meituan documents a 1M-token context. That makes it useful for tasks that draw on substantial reference material, such as code and migration documentation together.
How long can a LongCat 2.0 response be?
Meituan's API documentation specifies a maximum generation length of 131,072 tokens. The 1M-token context should not be read as a promise of a million-token response.
When should I use thinking with LongCat 2.0?
Use thinking for difficult debugging or analytical tasks. The maker describes turning thinking off as more token efficient and recommends retaining reasoning content when using its thinking template.
Does LongCat 2.0 perform equally well in every language?
The model card explicitly warns that performance varies across languages. Check representative examples in the language you plan to use before assigning recurring work.
Start using LongCat 2.0 in Hermes
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Hermes:
set up https://spiral.ai/SKILL.md


