Spiral gives your agent every tool with one account. Browse the tools →

Codex · LLMReleased 2026-08-12

How to Use Qwen3.8 2.4T A95B in Codex

Use Qwen3.8 2.4T A95B for coding, research, and document analysis that requires several steps. It accepts text only and always uses reasoning before producing its answer.

Prompts to try with Qwen3.8 2.4T A95B in Codex

Copy an example into Codex, or ask in your own words.

Use Qwen3.8 2.4T A95B to investigate the failing tests in this project. Reproduce the failure, trace the cause, make a focused fix, and run the relevant checks. Summarize the evidence and changed behavior.

Qwen3.8 2.4T A95BCodex
Try asking
  • Use Qwen3.8 2.4T A95B with deeper reasoning to plan this project's migration to the next major version of its main framework. Inspect the dependency manifest and affected code, then propose ordered changes and acceptance checks.

  • Use Qwen3.8 2.4T A95B to compare the API specification with the request handlers in this repository. Identify concrete mismatches, cite the relevant files, and propose a patch for the highest-impact mismatch.

  • Use Qwen3.8 2.4T A95B to review the current diff for behavior changes and missed edge cases. Trace each finding through the surrounding code and give a reproducible example before recommending a fix.

  • Use Qwen3.8 2.4T A95B with temperature 1.0, top_p 0.95, and top_k 20 to implement pagination for this project's existing list endpoint. Follow the repository's conventions and verify empty results, page boundaries, and invalid input.

How to set up Qwen3.8 2.4T A95B in Codex

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the hosted server
    codex mcp add spiral --url https://api.spiral.ai/mcp
  2. 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

  1. Send Codex this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. Run Qwen3.8 2.4T A95B

    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/qwen3.8-2.4t-a95b",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: Codex finds Qwen3.8 2.4T A95B on Spiral, shows the price and runs it.

Qwen3.8 2.4T A95B providers and prices

Spiral runs Qwen3.8 2.4T A95B through OpenRouter. Open a card for today's price, with every fee included.

OpenRouterLLM
Qwen: Qwen3.8 2.4T A95B
qwen/qwen3.8-2.4t-a95b

Settings you can ask for

Ask Codex for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number
Top ka whole number from 0
Top p0 to 1
Logprobson or off
Max tokens1 to 131072

The most output tokens to generate.

Temperature0 to 2
Top logprobs0 to 20
Presence penalty-2 to 2
Reasoning effortlow, medium, or xhighxhigh

How much the model reasons.

Frequency penalty-2 to 2
Repetition penalty0 to 2

Every API field of Qwen: Qwen3.8 2.4T A95B is on its tool page: open its card above.

What can you do with Qwen3.8 2.4T A95B in Codex?

Turn repository investigation into a tested code change with Qwen3.8 2.4T A95B. Give the agent a concrete failure or specification and ask it to follow the dependencies through implementation and verification.

Investigate a failing test

Use Qwen3.8 2.4T A95B to trace a failure through source code and logs, propose a focused fix, and check the result against the original failure.

Plan a code migration

Ask Qwen3.8 2.4T A95B to map affected code, identify dependencies, and divide a migration into changes with explicit acceptance checks.

Compare document revisions

Give Qwen3.8 2.4T A95B the text of two specifications or policies and request changed requirements, contradictions, and supporting passages.

Build an evidence-based research brief

Use Qwen3.8 2.4T A95B to organize supplied research excerpts by question, identify disagreements, and separate findings from open questions.

Review an incident timeline

Ask Qwen3.8 2.4T A95B to reconcile timestamped logs and written updates into a timeline, with evidence for each proposed cause.

Prepare a decision memo

Give Qwen3.8 2.4T A95B written proposals and evaluation criteria, then request a comparison that makes assumptions and missing evidence explicit.

Track requirement changes

Use Qwen3.8 2.4T A95B to compare newly retrieved text with an earlier snapshot and draft a digest of changes that affect planned work.

Turn a specification into implementation tasks

Ask Qwen3.8 2.4T A95B to translate a written specification into ordered tasks, dependencies, edge cases, and completion criteria.

Questions about Qwen3.8 2.4T A95B in Codex

Can Codex use Qwen3.8 2.4T A95B?

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Qwen3.8 2.4T A95B like any built-in tool.

How much does Qwen3.8 2.4T A95B cost in Codex?

Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 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 Qwen3.8 2.4T A95B in Codex?

No. Spiral runs Qwen3.8 2.4T A95B on its own OpenRouter account. You sign in to Spiral once and never paste a key.

How long does it take to set up Qwen3.8 2.4T A95B in Codex?

About two minutes: add the hosted server, then sign in.

Does Codex wait while Qwen3.8 2.4T A95B runs?

Qwen3.8 2.4T A95B runs in the background. Codex starts the run, checks on it and gives you the text, json when it's ready.

What is Qwen3.8 2.4T A95B good at?

Qwen emphasizes coding, professional work, research, and tasks that require multiple steps. Suggested uses include debugging code, comparing lengthy documents, and building research briefs from supplied evidence.

Can Qwen3.8 2.4T A95B analyze images?

No. It is text-only, so provide extracted text or a written description when working from visual material.

How much context does Qwen3.8 2.4T A95B support?

Its native context length is 262,144 tokens. Qwen documents extension to 1,010,000 tokens, so distinguish the native limit from the extended capability when planning long-document work.

Can I turn off thinking in Qwen3.8 2.4T A95B?

No. Thinking is required for every interaction, although Qwen documents adjustable reasoning depth.

How long can a Qwen3.8 2.4T A95B response be?

NVIDIA describes output up to 128K tokens. Treat that as a documented upper capability, and specify the length you actually need in the prompt.

Get started

Start using Qwen3.8 2.4T A95B in Codex

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Codex:

Set up Codex

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options