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

Codex · LLMReleased 2026-09-21

How to Use Qwen3.8 Omni Flash in Codex

Qwen3.8 Omni Flash turns recordings, videos, images, and text into summaries and written analysis. Its 1 million-token context supports long source material, while its output is text only.

Prompts to try with Qwen3.8 Omni Flash in Codex

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

Use Qwen3.8 Omni Flash to compare the screenshots in this project with the relevant UI components. List visible discrepancies, likely source locations, and a proposed fix for each; separate observations from hypotheses.

Qwen3.8 Omni FlashCodex
Try asking
  • Use Qwen3.8 Omni Flash to analyze the 10-minute bug reproduction video in this project. Draft reproduction steps and expected versus observed behavior, then inspect the code for a likely cause.

  • Use Qwen3.8 Omni Flash to turn the project's 30-minute feature walkthrough into a documentation draft. Check terminology against the README and flag behavior that the recording does not explain.

  • Use Qwen3.8 Omni Flash to compare the recorded design review with the current implementation. Produce a change list tied to project files, with unresolved decisions listed separately.

  • Use Qwen3.8 Omni Flash to review the architecture notes and relevant source files. Request more reasoning effort to identify contradictions, then propose a small implementation plan with evidence for each recommendation.

How to set up Qwen3.8 Omni Flash 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 Omni 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": "qwen/qwen3.8-omni-flash",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

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

Qwen3.8 Omni Flash providers and prices

Spiral runs Qwen3.8 Omni Flash through OpenRouter. Open a card for today's price, with every fee included.

OpenRouterLLM
Qwen: Qwen3.8 Omni Flash
qwen/qwen3.8-omni-flash

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
Frequency penalty-2 to 2

Every API field of Qwen: Qwen3.8 Omni Flash is on its tool page: open its card above.

What can you do with Qwen3.8 Omni Flash in Codex?

Turn screenshots and recorded demonstrations into issue reports, implementation plans, and documentation with Qwen3.8 Omni Flash. Your coding agent can connect the observations to project files and check proposed changes against the code.

Meeting notes with clear ownership

Turn a meeting recording into decisions, unresolved questions, and action items. Request an owner and deadline only when the recording supplies them.

Interview research summaries

Analyze recorded interviews for recurring needs and objections. Ask for supporting excerpts and keep interpretations separate from what participants actually said.

Video editing briefs

Review footage and draft a scene outline, suggested cuts, and narration notes for an editor. Request written editing instructions as the deliverable.

Translated recording summaries

Create a written translation or summary of spoken source material. Specify the target language and ask it to preserve names and flag unclear passages.

Training video notes

Convert a recorded demonstration into instructions and a review checklist. Ask it to distinguish visible actions from spoken explanations.

Media archive tagging

Generate consistent topic labels and short descriptions for recordings and videos. Supply a fixed taxonomy and request evidence for each assigned label.

Screenshot-based issue reports

Use screenshots to draft descriptions of visible interface problems. In a coding agent, connect those observations to the relevant project code.

Knowledge work across source formats

Combine written material, screenshots, and recorded explanations into a brief. Ask for source references beside conclusions and a separate list of unanswered questions.

Questions about Qwen3.8 Omni Flash in Codex

Can Codex use Qwen3.8 Omni Flash?

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

How much does Qwen3.8 Omni Flash cost in Codex?

Up to $0.002511 per run at the default inputs. $0.195 per 1M input tokens, $0.611 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 Omni Flash in Codex?

No. Spiral runs Qwen3.8 Omni 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 Qwen3.8 Omni Flash in Codex?

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

Does Codex wait while Qwen3.8 Omni Flash runs?

Qwen3.8 Omni Flash 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 Omni Flash useful for?

Use it to turn recordings and videos into meeting notes, content tags, translations, and written analysis. It also handles text and image inputs.

Can Qwen3.8 Omni Flash generate speech or finished videos?

Its output is text only. Ask for narration scripts, edit instructions, or written analysis; use separate tools to produce audio or render video.

How long can recordings and videos be?

Qwen documents support for audio up to 3 hours and video up to 2 hours. Keep requests within those duration limits and the model's context limit.

How much material can Qwen3.8 Omni Flash handle?

Its context window reaches 1 million tokens. The documented maximum output is 131,072 tokens, and thinking mode allows up to 983,616 input tokens.

Does Qwen3.8 Omni Flash understand multilingual audio?

Qwen lists 113 supported audio input languages and dialects. Specify whether you want the original wording preserved or a translation into a named language.

Get started

Start using Qwen3.8 Omni Flash 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