[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [Qwen3.8 Max Prime](https://spiral.ai/integrations/codex/qwen3-8-max-prime)

# How to Use Qwen3.8 Max Prime in Codex

Qwen3.8 Max Prime suits coding, document analysis, and tasks that take several steps. It retains Qwen3.8 Max's capabilities while generating output faster.

|  |  |
| --- | --- |
| Model | Qwen3.8 Max Prime |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.06408 per run at the default inputs. $5.20 per 1M input tokens, $15.60 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen3.8 Max Prime in Codex

- Use Qwen3.8 Max Prime to trace the failing test in this project, identify the cause, make a focused fix, and report the verification result.
- Use Qwen3.8 Max Prime to compare this project's migration guide with its current dependencies. Draft an ordered migration plan with a check for each stage.
- Use Qwen3.8 Max Prime to review the authentication code across this repository. Explain the request flow and identify inconsistent behavior with file references.
- Use Qwen3.8 Max Prime to implement the acceptance criteria in the project brief. Work in small steps, run relevant checks, and report any unmet criteria.
- Use Qwen3.8 Max Prime to compare the supplied screenshot with this project's rendered page. List visible differences, fix them, and verify the result.

## How to set up Qwen3.8 Max Prime in Codex

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

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
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.

```bash
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.

```bash
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 Max Prime**: One request; the result comes back by polling or a webhook.

```bash
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-max-prime",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

Setup guide in the docs: https://spiral.ai/docs/quickstarts/codex

## Qwen3.8 Max Prime tools and prices

- [Qwen: Qwen3.8 Max Prime](https://spiral.ai/tools/openrouter/qwen/qwen3.8-max-prime) (OpenRouter): Up to $0.06408 per run at the default inputs. $5.20 per 1M input tokens, $15.60 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| logprobs |  | — |  |

## What can you do with Qwen3.8 Max Prime in Codex?

Qwen3.8 Max Prime can carry a software task from codebase investigation through implementation and verification. Define the expected behavior and require test evidence with the final patch.

### Fix bugs across a codebase

Trace a failure through related code, propose a focused patch, and check the result against a reproducible test.

### Plan software migrations

Compare current behavior with migration requirements, identify dependencies, and draft an implementation order with checks for each stage.

### Compare long documents

Find conflicting requirements across supplied documents and build an evidence table with section references.

### Turn research into a decision brief

Compare supplied studies, separate findings from assumptions, and explain which evidence supports each recommendation.

### Explain charts and screenshots

Analyze supplied visuals and write a concise explanation that distinguishes visible evidence from interpretation.

### Review product demonstration videos

Turn a supplied demonstration into a written account of the workflow, confusing steps, and questions for the product team.

### Prepare recurring operations briefs

Compare incoming updates with the previous report, identify unresolved dependencies, and draft the next actions with supporting evidence.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Codex guides](https://spiral.ai/integrations/codex)

## Qwen3.8 Max Prime in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen3-8-max-prime)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen3-8-max-prime)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen3-8-max-prime)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen3-8-max-prime)
- [Cline](https://spiral.ai/integrations/cline/qwen3-8-max-prime)
- [Cursor](https://spiral.ai/integrations/cursor/qwen3-8-max-prime)
- [Devin](https://spiral.ai/integrations/devin/qwen3-8-max-prime)
- [dots](https://spiral.ai/integrations/dots/qwen3-8-max-prime)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen3-8-max-prime)
- [Gemini](https://spiral.ai/integrations/gemini/qwen3-8-max-prime)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen3-8-max-prime)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen3-8-max-prime)
- [goose](https://spiral.ai/integrations/goose/qwen3-8-max-prime)
- [Grok](https://spiral.ai/integrations/grok/qwen3-8-max-prime)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen3-8-max-prime)
- [Hermes](https://spiral.ai/integrations/hermes/qwen3-8-max-prime)
- [Instinct](https://spiral.ai/integrations/instinct/qwen3-8-max-prime)
- [Manus](https://spiral.ai/integrations/manus/qwen3-8-max-prime)
- [Muse](https://spiral.ai/integrations/muse/qwen3-8-max-prime)
- [Muse Code](https://spiral.ai/integrations/muse-code/qwen3-8-max-prime)
- [n8n](https://spiral.ai/integrations/n8n/qwen3-8-max-prime)
- [Notion](https://spiral.ai/integrations/notion/qwen3-8-max-prime)
- [OpenClaw](https://spiral.ai/integrations/openclaw/qwen3-8-max-prime)
- [opencode](https://spiral.ai/integrations/opencode/qwen3-8-max-prime)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen3-8-max-prime)
- [Raycast](https://spiral.ai/integrations/raycast/qwen3-8-max-prime)
- [VS Code](https://spiral.ai/integrations/vscode/qwen3-8-max-prime)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen3-8-max-prime)
- [Zapier](https://spiral.ai/integrations/zapier/qwen3-8-max-prime)

## More Codex guides

- [Qwen3.8 Max (0902) (batch)](https://spiral.ai/integrations/codex/qwen3-8-max-0902-batch)
- [Qwen3.8 Omni Flash](https://spiral.ai/integrations/codex/qwen3-8-omni-flash)
- [Qwen3.8 Max (0902)](https://spiral.ai/integrations/codex/qwen3-8-max-0902)
- [Qwen4 Max](https://spiral.ai/integrations/codex/qwen4-max)
- [Qwen3.8 Flash](https://spiral.ai/integrations/codex/qwen3-8-flash)
- [ReMM SLERP 13B](https://spiral.ai/integrations/codex/remm-slerp-13b)

## Questions about Qwen3.8 Max Prime in Codex

**Can Codex use Qwen3.8 Max Prime?**

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

**How much does Qwen3.8 Max Prime cost in Codex?**

Up to $0.06408 per run at the default inputs. $5.20 per 1M input tokens, $15.60 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 Max Prime in Codex?**

No. Spiral runs Qwen3.8 Max Prime 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 Max Prime in Codex?**

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

**Does Codex wait while Qwen3.8 Max Prime runs?**

Qwen3.8 Max Prime 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 Max Prime good at?**

Use it for software changes, research synthesis, document analysis, and work that requires several connected steps. Give it a concrete deliverable, the source material, and a way to check the result.

**How does Qwen3.8 Max Prime differ from Qwen3.8 Max?**

Prime retains Qwen3.8 Max's capabilities and generates output faster. Choose it when output speed matters during coding or repeated analysis.

**How much can Qwen3.8 Max Prime read and write?**

It has a one-million-token context window and supports up to 131,072 completion tokens. Keep the requested deliverable bounded; split material that exceeds the context limit into focused sections.

**Does Qwen3.8 Max Prime create images or videos?**

Its output is text. Use it to analyze supplied images or video and produce explanations, comparisons, or written briefs.

**When should I ask for deeper reasoning?**

Reserve deeper reasoning for difficult debugging, competing explanations, and plans with several dependencies. Qwen recommends medium effort for a balance of accuracy and speed and xhigh for complex analysis.

