How to Use GPT-4o mini (2024-07-18) in Claude Code
GPT-4o mini (2024-07-18) fixes the model version for extraction, reply drafting, and coding tasks. It has the same capabilities and limits as the snapshot currently selected by GPT-4o mini.
Prompts to try with GPT-4o mini (2024-07-18) in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use GPT-4o mini (2024-07-18) to draft tests for the date parser in this project. Cover valid dates, invalid dates, and boundary values using the existing test framework, then run the tests.
Use GPT-4o mini (2024-07-18) to propose a small fix for the failing test in this project. Read the failure and relevant function, explain the cause, and change only what the test requires.
Ask GPT-4o mini (2024-07-18) through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
Get a second opinion from GPT-4o mini (2024-07-18) on this function, then tell me what the call cost.
Summarize these release notes with GPT-4o mini (2024-07-18) in five bullet points.
How to set up GPT-4o mini (2024-07-18) in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.
Use the Spiral skill
- Send Claude Code 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 GPT-4o mini (2024-07-18)
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-4o-mini-2024-07-18", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude Code finds GPT-4o mini (2024-07-18) on Spiral, shows the price and runs it.
GPT-4o mini (2024-07-18) providers and prices
Spiral runs GPT-4o mini (2024-07-18) through OpenAI. Open a card for today's price, with every fee included.
Up to $0.003202 per run at the default inputs. $0.195 per 1M input tokens, $0.0975 per 1M cached input tokens, $0.78 per 1M output tokens.
Settings you can ask for
Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | a whole number from 16 | 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 | ||
| Parallel tool calls | on or off |
Every API field of GPT-4o-mini (2024-07-18) is on its tool page: open its card above.
What can you do with GPT-4o mini (2024-07-18) in Claude Code?
Turn project code into small patches, test drafts, and explanations with GPT-4o mini. Scope each request to a function or a focused diff and specify the expected behavior.
Extract receipt details from text
Give GPT-4o mini receipt text and request merchant, date, total, and currency in a defined record. Require missing values to remain empty.
Label support requests
Ask GPT-4o mini to assign a defined intent label to each message. Supply examples for ambiguous requests and require a supporting phrase.
Draft email replies
Provide the conversation history and ask GPT-4o mini for a concise reply that addresses open questions without inventing commitments.
Extract meeting follow-ups
Turn meeting notes into tasks, owners, and stated due dates with GPT-4o mini. Keep tentative suggestions separate from confirmed assignments.
Draft tests for a function
Give GPT-4o mini a function and its expected behavior. Request tests for ordinary inputs, boundary conditions, and invalid inputs, then run them.
Explain a small code change
Ask GPT-4o mini to explain a focused diff, identify changed behavior, and point to the relevant lines for review.
Translate customer messages
Ask GPT-4o mini to translate a message into the requested language while preserving product names, identifiers, and stated dates.
Prepare records for validation
Have GPT-4o mini extract named attributes from incoming text into a supplied schema. Validate the structure and compare important values with the source.
More on GPT-4o mini (2024-07-18) and Claude Code
Overview
GPT-4o mini (2024-07-18) in other agents
More Claude Code guides
Questions about GPT-4o mini (2024-07-18) in Claude Code
Can Claude Code use GPT-4o mini (2024-07-18)?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run GPT-4o mini (2024-07-18) like any built-in tool.
How much does GPT-4o mini (2024-07-18) cost in Claude Code?
Up to $0.003202 per run at the default inputs. $0.195 per 1M input tokens, $0.0975 per 1M cached input tokens, $0.78 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.
Do I need an OpenAI account to use GPT-4o mini (2024-07-18) in Claude Code?
No. Spiral runs GPT-4o mini (2024-07-18) 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-4o mini (2024-07-18) in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while GPT-4o mini (2024-07-18) runs?
GPT-4o mini (2024-07-18) runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.
What is GPT-4o mini useful for?
Start with extraction, short email replies grounded in conversation history, and small coding tasks. Give each request a clear scope and a checkable result.
How much text can GPT-4o mini handle?
The context window is 128,000 tokens, and a response can contain up to 16,384 tokens. Tokens are the units behind these limits, so avoid treating them as word counts.
How does GPT-4o mini differ from GPT-4o mini (2024-07-18)?
GPT-4o mini currently selects the July 18, 2024 snapshot. The dated name explicitly selects that version; it does not add capabilities.
Does valid JSON mean GPT-4o mini extracted the right information?
No. Structured Outputs can enforce a supported schema, but the values can still be wrong. Check names, dates, amounts, and supporting text against the original.
Can GPT-4o mini work in languages besides English?
Yes. OpenAI says it supports the same range of languages as GPT-4o. State the target language and identify any names or terms that should stay unchanged.
Start using GPT-4o mini (2024-07-18) in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


