OpenAI: GPT-4o-mini
GPT-4o mini is a previous OpenAI cheap omni snapshot, not the 2026 latest model. The still-listed GPT-4o mini card prints $0.15 input / $0.60 output per 1M tokens (cached input $0.075), aliases gpt-4o-mini and gpt-4o-mini-2024-07-18.
Compare GPT-4o if you wanted the leftover full 4o row at $2.50 / $10, GPT-5.6 Sol if you wanted the live frontier, and OpenAI if you wanted the company page.
Key Features
- Still listed, not the start-here model: Docs still describe GPT-4o mini as a cheap multimodal GPT. The models index now starts at GPT-5.6 Sol / Terra / Luna.
- Printed dollar row: $0.15 / $0.60 per 1M on the GPT-4o mini card on the public page. Confirm before you reuse leftover GPT-3.5 math.
- Website is the model card: Point at the developers model page, not a generic openai.com homepage claim that it is newest.
- No leftover MMLU crown: Do not paste 82% MMLU or "ranks higher than GPT-4" as a 2026 census.
Use Cases
- People with a GPT-4o mini bookmark who need the catalog corrected.
- People who were about to call GPT-4o mini the 2026 latest cheap OpenAI model.
Limitation: We did not re-run leftover MMLU or chat-preference crowns.
Pricing
GPT-4o mini model card on 2026-08-18.
| Piece | Price | Notes |
|---|---|---|
| gpt-4o-mini | $0.15 / $0.60 per 1M | Cached input $0.075. Still listed. |
| gpt-4o-mini-2024-07-18 | Same dated alias | Confirm the same card. |
| Live start | GPT-5.6 Sol $5 / $30 | gpt-5.6. |
If a leftover blog still calls GPT-4o mini the newest OpenAI model after GPT-4 Omni, treat the models index as the correction.
Getting Started
- Open the GPT-4o mini card and note $0.15 / $0.60.
- Confirm GPT-4o if you wanted the leftover full 4o row.
- Confirm GPT-5.6 Sol if you wanted the live start-here model.
- Do not paste "newest after GPT-4 Omni" into a 2026 deck.
Frequently Asked Questions
Is GPT-4o mini still latest?
No. The live models index starts at GPT-5.6 Sol.
Is it gone?
No. The card is still listed at $0.15 / $0.60.
Same as GPT-4o?
No. GPT-4o is the leftover full omni snapshot at $2.50 / $10.
Alternatives
- GPT-5.6 Sol: Live OpenAI frontier.
- GPT-4o: Leftover full 4o snapshot.
- OpenAI: Company page.
Tips
- Quote $0.15 / $0.60 from the live card, not leftover GPT-3.5 math.
- Call GPT-4o mini previous, not newest.
- Confirm GPT-5.6 Sol if you wanted the 2026 start-here row.
Conclusion
GPT-4o mini is a still-listed previous cheap omni snapshot at $0.15 / $0.60, not the 2026 latest OpenAI model. Start at the GPT-4o mini card, then decide whether GPT-5.6 Sol already covers the path you need.
Comments
No comments yet. Be the first to comment!
Related Tools
Related Insights
Grok Bot and Hermes Bot: one person finally gets a think tank and a secretariat
Grok Bot now ships with Cursor Pro+. Hermes Bot runs on a VPS. They are not smarter chat boxes. The think tank advises, the secretariat executes, and you still make the call.
Hook OpenCode Go into Codex on Windows. Do Not Open a Second Toolkit.
A ChatGPT-signed Codex desktop app still shows mostly GPT in the picker. On Windows, enable only OpenCode Go and the Grok, GLM, Kimi, DeepSeek, and MiniMax models you already pay for appear in the same selector. Keys stay local. Native GPT stays put.
What Locks Codex Is the Picker, Not the Models
You already pay for OpenCode Go, Grok, and Z.ai, but the Codex picker still shows mostly GPT. The community project codex-router does not teach another install ritual. It puts subscriptions you already bought back into the selector, keeps keys on the machine, and leaves native GPT alone.