How to Use Ling 3.0 Flash in Claude
Ling 3.0 Flash is built for code changes, research, and reasoning over long text. Its 262,144-token context accommodates large inputs, while individual completions support up to 32,768 tokens.
Prompts to try with Ling 3.0 Flash in Claude
Copy an example into Claude, or ask in your own words.
Use Ling 3.0 Flash to compare the proposals in this conversation. Judge them on reliability, maintenance work, and failure recovery. Cite the relevant passages and mark any criterion the proposals leave unanswered.
Use Ling 3.0 Flash to explain the code pasted above. Trace one successful execution and one failure case, identify assumptions, and suggest three tests that would check the explanation.
Use Ling 3.0 Flash to turn the source excerpts above into a 600-word research brief. Answer the stated question, cite source labels, separate agreement from disagreement, and list missing evidence.
Use Ling 3.0 Flash to turn the requirements above into acceptance scenarios. For each scenario, give the starting conditions, action, and expected result. List ambiguities separately instead of inventing requirements.
Use Ling 3.0 Flash to analyze the technical decision described above. Compare three plausible approaches, state assumptions, and recommend one with explicit reasons. Keep the final answer under 800 words.
How to set up Ling 3.0 Flash in Claude
Pick the way that suits you. Each takes about two minutes.
Use the Claude connector
- Add Spiral to Claude
Click Add Spiral in Claude above. Claude opens Add custom connector with Spiral and its URL filled in; check them and click Continue. Without the link: in Claude open Customize › Connectors › Add › Add custom connector and paste this URL:
https://api.spiral.ai/mcp
- Keep the detected sign-in and click Add
Claude finds Spiral's sign-in by itself: leave Sign in now and Use Claude's published identity selected.
- Click Connect
The connector page opens. Connect takes you to Spiral in your browser.
Use the Spiral skill
- Send Claude 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 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 Ling 3.0 Flash
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": "inclusionai/ling-3.0-flash", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude finds Ling 3.0 Flash on Spiral, shows the price and runs it.
Ling 3.0 Flash providers and prices
Spiral runs Ling 3.0 Flash through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.000337 per run at the default inputs. $0.0273 per 1M input tokens, $0.0819 per 1M output tokens.
Settings you can ask for
Ask Claude 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 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 32768 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of inclusionAI: Ling 3.0 Flash is on its tool page: open its card above.
What can you do with Ling 3.0 Flash in Claude?
Turn lengthy technical text into comparisons, explanations, and research briefs with Ling 3.0 Flash. Give it a clear question and labeled source passages so the answer can be checked against the evidence.
Fix a reproducible bug
Give Ling 3.0 Flash the failing behavior, relevant code, and test output. Ask for a focused patch and a regression test.
Plan a code refactor
Ask Ling 3.0 Flash to trace dependencies, identify behavior that must stay intact, and propose small changes with verification checks.
Explain an unfamiliar codebase
Have Ling 3.0 Flash trace a request through the relevant modules and explain where validation, state changes, and error handling happen.
Compare technical proposals
Supply proposal text and decision criteria. Ask Ling 3.0 Flash to compare tradeoffs, cite supporting passages, and list unanswered questions.
Prepare a research brief
Give Ling 3.0 Flash source excerpts and a specific question. Request a brief that separates supported findings, conflicting evidence, and gaps.
Track changes in recurring reports
Compare current and previous report text with Ling 3.0 Flash. Ask for meaningful changes, supporting passages, and questions for follow-up.
Turn requirements into acceptance checks
Ask Ling 3.0 Flash to translate written requirements into concrete scenarios, expected outcomes, and ambiguities that need a decision.
More on Ling 3.0 Flash and Claude
Overview
Ling 3.0 Flash in other agents
Questions about Ling 3.0 Flash in Claude
Can Claude use Ling 3.0 Flash?
Yes. Add Spiral to Claude as an MCP server, and Claude can find and run Ling 3.0 Flash like any built-in tool.
How much does Ling 3.0 Flash cost in Claude?
Up to $0.000337 per run at the default inputs. $0.0273 per 1M input tokens, $0.0819 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude plan is separate.
Do I need an OpenRouter account to use Ling 3.0 Flash in Claude?
No. Spiral runs Ling 3.0 Flash on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Ling 3.0 Flash in Claude?
About two minutes: add Spiral to Claude, then keep the detected sign-in and click Add, then click Connect.
Does Claude wait while Ling 3.0 Flash runs?
Ling 3.0 Flash runs in the background. Claude starts the run, checks on it and gives you the text, json when it's ready.
What is Ling 3.0 Flash useful for?
The maker trains it for coding, general agent work, and deep research. Practical starting points include debugging, comparing source material, and turning lengthy text into an evidence-based brief.
How much text can Ling 3.0 Flash work with?
Its context window is 262,144 tokens. Use that capacity for relevant source material, and specify which questions the answer must resolve.
How long can a Ling 3.0 Flash answer be?
It supports up to 32,768 completion tokens. For lengthy deliverables, ask for an outline first and draft one section at a time.
Which sampling settings should I start with?
The maker recommends temperature 0.6, top_p 0.95, and top_k 20. Start there when assessing results on your own tasks.
Does Ling 3.0 Flash use a thinking mode?
Thinking is enabled by default in its native chat template and reasoning parser. For difficult tasks, ask for a concise final explanation with assumptions and verification checks.
Start using Ling 3.0 Flash in Claude
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude:
set up https://spiral.ai/SKILL.md


