How to Use Qwen3.5 Plus in Codex
Qwen3.5 Plus handles coding, long document analysis, and multilingual text. This February 15, 2026 snapshot offers a 1 million token context for working across extensive source material.
Prompts to try with Qwen3.5 Plus in Codex
Copy an example into Codex, or ask in your own words.
Use Qwen3.5 Plus with thinking enabled to investigate the failing tests in this project. Trace each failure to the relevant code, make a focused fix, and run the affected tests.
Use Qwen3.5 Plus to compare this project's implementation with its specification. List mismatches with file and section references, then propose an ordered correction plan.
Use Qwen3.5 Plus with thinking enabled to review the authentication code for incorrect state transitions. Give a reproducible example for each finding and add a regression test for any fix.
Use Qwen3.5 Plus to translate this project's English interface strings into Spanish for Mexico. Preserve interpolation tokens and keys, and flag strings that need more context.
Use Qwen3.5 Plus to draft a contributor guide from the README, build configuration, and tests. Include commands verified against the project and list any unresolved gaps.
How to set up Qwen3.5 Plus in Codex
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
codex mcp add spiral --url https://api.spiral.ai/mcp
- Sign in
Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.
codex mcp login spiral
Use the Spiral skill
- Send Codex 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 Qwen3.5 Plus
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": "qwen/qwen3.5-plus-02-15", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Codex finds Qwen3.5 Plus on Spiral, shows the price and runs it.
Qwen3.5 Plus providers and prices
Spiral runs Qwen3.5 Plus through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.008319 per run at the default inputs. $0.338 per 1M input tokens, $2.028 per 1M output tokens.
Settings you can ask for
Ask Codex for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 65536 | 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 |
Every API field of Qwen: Qwen3.5 Plus 2026-02-15 is on its tool page: open its card above.
What can you do with Qwen3.5 Plus in Codex?
Use Qwen3.5 Plus to trace behavior across project files, draft fixes, and turn technical notes into documentation. Give it the relevant code, constraints, and acceptance criteria, then ask for verification tied to the requested change.
Trace a bug across project files
Ask Qwen3.5 Plus to connect an error report with the relevant implementation and tests, propose a focused patch, and explain how to verify it.
Compare lengthy specifications
Give Qwen3.5 Plus labeled specification texts and request a table of changed requirements, conflicts, and unanswered questions with section references.
Turn reports into a decision brief
Use Qwen3.5 Plus to summarize supplied reports into findings, supporting evidence, and open questions. Require a source reference for each finding.
Translate support content
Ask Qwen3.5 Plus to translate support articles for a named region while preserving product terms, examples, and formatting.
Extract records from messages
Use Qwen3.5 Plus to turn supplied messages into JSON records with explicit keys and missing-value rules. Validate the resulting keys and types.
Work through technical calculations
Give Qwen3.5 Plus a mathematical or engineering problem with its assumptions and units. Request the result, a concise derivation, and a check against the stated constraints.
Prepare recurring operations briefs
Have Qwen3.5 Plus summarize each supplied batch of status updates into changes, blockers, owners, and decisions needed, using a consistent format.
Draft documentation from technical notes
Ask Qwen3.5 Plus to turn implementation notes into a user guide with worked examples. Have it list missing information before drafting unsupported instructions.
More on Qwen3.5 Plus and Codex
Overview
Qwen3.5 Plus in other agents
Questions about Qwen3.5 Plus in Codex
Can Codex use Qwen3.5 Plus?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Qwen3.5 Plus like any built-in tool.
How much does Qwen3.5 Plus cost in Codex?
Up to $0.008319 per run at the default inputs. $0.338 per 1M input tokens, $2.028 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.
Do I need an OpenRouter account to use Qwen3.5 Plus in Codex?
No. Spiral runs Qwen3.5 Plus on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Qwen3.5 Plus in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while Qwen3.5 Plus runs?
Qwen3.5 Plus runs in the background. Codex starts the run, checks on it and gives you the text, json when it's ready.
What is Qwen3.5 Plus useful for?
Use it for coding tasks, comparing long source texts, summarizing reports, and multilingual writing. Give it the relevant material and a concrete deliverable, such as a patch, comparison table, or brief with source references.
How much text can Qwen3.5 Plus handle?
Qwen3.5 Plus has a 1 million token context and a maximum output length of 65,536 tokens. For a lengthy deliverable, request an outline first and draft sections separately to stay within the output limit.
When should I use thinking mode?
Use thinking for logical reasoning, mathematical problems, and code generation. Direct responses suit straightforward questions and routine text tasks; thinking adds latency and token consumption.
Which languages does Qwen3.5 Plus support?
Qwen reports support for 201 languages and dialects. For translation, specify the target language, regional usage, audience, and terms that must remain unchanged.
Which settings should I try for coding and reasoning?
Qwen recommends starting thinking mode with temperature 0.6, top-p 0.95, and top-k 20. Treat these as a starting point and compare results on representative tasks before changing them.
Start using Qwen3.5 Plus in Codex
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Codex:
set up https://spiral.ai/SKILL.md


