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

Codex · LLMReleased 2026-03-17

How to Use GPT Mini Latest in Codex

Use GPT Mini Latest for focused code edits, debugging, and structured text tasks. It currently points to GPT-5.4 mini, but the alias can change as newer GPT Mini models become available.

Prompts to try with GPT Mini Latest in Codex

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

Use GPT Mini Latest to trace the checkout total from the page component to its calculation function. Read the relevant project files and report the call path with file references.

GPT Mini LatestCodex
Try asking
  • Use GPT Mini Latest to fix the failing date-parser test. Reproduce the failure, make the smallest relevant change, run the test again, and report the result.

  • Use GPT Mini Latest to build a searchable table using the project's existing components. Include loading, empty, and error states, then verify keyboard navigation.

  • Use GPT Mini Latest to review the current diff for incorrect null handling. Report each finding with a file reference, triggering input, and suggested test; return an empty list if none are found.

  • Use GPT Mini Latest to convert the validation rules in this project into a JSON checklist. Preserve each rule's source location and mark conflicting rules for review.

How to set up GPT Mini Latest 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 GPT Mini Latest

    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": "openai",
        "model": "~openai/gpt-mini-latest",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: Codex finds GPT Mini Latest on Spiral, shows the price and runs it.

GPT Mini Latest providers and prices

Spiral runs GPT Mini Latest through OpenAI. Open a card for today's price, with every fee included.

OpenAILLM
GPT Mini Latest
~openai/gpt-mini-latest

Settings you can ask for

Ask Codex for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number
Top pa number up to 1

Taken only at reasoning effort "none", this model's default.

Logprobson or off

Taken only at reasoning effort "none", this model's default.

Max tokens16 to 128000

The most output tokens to generate.

Temperature0 to 2

Taken only at reasoning effort "none", this model's default.

Top logprobs0 to 20

Taken only at reasoning effort "none", this model's default.

Presence penalty-2 to 2

Taken only at reasoning effort "none", this model's default.

Reasoning effortnone, low, medium, high, or xhighnone

How much the model reasons.

Frequency penalty-2 to 2

Taken only at reasoning effort "none", this model's default.

Parallel tool callson or off

Every API field of GPT Mini Latest is on its tool page: open its card above.

What can you do with GPT Mini Latest in Codex?

Turn a specific bug or interface requirement into a focused code change with GPT Mini Latest. Give the agent relevant project files, acceptance criteria, and an explicit verification step.

Fix a reproducible bug

Give GPT Mini Latest the failing behavior and relevant code. Ask for a focused patch and a test that reproduces the failure.

Find the code behind a behavior

Have GPT Mini Latest trace a request from its entry point to the function that changes the result, with file references for each step.

Build a defined interface component

Ask GPT Mini Latest to implement a form or table with explicit loading, empty, error, and success states.

Review a bounded code change

Give GPT Mini Latest a diff and acceptance criteria. Request concrete defects with evidence and a suggested verification step.

Extract action items

Turn meeting text into structured actions with owners, deadlines, and supporting excerpts. Require missing details to remain unknown.

Sort support requests

Supply category definitions and examples, then ask GPT Mini Latest to label each request and flag ambiguous cases.

Explain an interface screenshot

Ask GPT Mini Latest to identify visible controls and explain a displayed error, separating observations from suggested fixes.

Compare policy excerpts

Give GPT Mini Latest two passages and a fixed comparison checklist. Request changed requirements with supporting text from both versions.

Questions about GPT Mini Latest in Codex

Can Codex use GPT Mini Latest?

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run GPT Mini Latest like any built-in tool.

How much does GPT Mini Latest cost in Codex?

Up to $0.023997 per run at the default inputs. $0.975 per 1M input tokens, $0.0975 per 1M cached input tokens, $5.85 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 OpenAI account to use GPT Mini Latest in Codex?

No. Spiral runs GPT Mini Latest on its own OpenAI account. You sign in to Spiral once and never paste a key.

How long does it take to set up GPT Mini Latest in Codex?

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

Does Codex wait while GPT Mini Latest runs?

GPT Mini Latest runs in the background. Codex starts the run, checks on it and gives you the text, json when it's ready.

Does GPT Mini Latest always use the same model?

No. It currently points to GPT-5.4 mini, but the alias follows the latest GPT Mini model, so behavior and limits can change.

How much text can GPT Mini Latest handle?

The current target has a 400,000-token context window and a maximum output of 128,000 tokens. Reasoning also consumes the generation allowance, so that maximum does not promise a visible answer of the same length.

What is GPT Mini Latest good at?

The current target suits focused code edits, codebase navigation, front-end generation, debugging, and interpreting interface screenshots. Give it a defined task and a clear deliverable.

Where does GPT Mini Latest need more guidance?

The current target is weaker at inferring missing steps and handling ambiguity. Specify the work order, what to do when information is missing, and the exact form of the answer.

Can I trust every value in its JSON?

Schema adherence does not establish factual accuracy. Define how missing evidence should appear and check extracted values against the source text.

Get started

Start using GPT Mini Latest 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