Migrate off GPT-4 Turbo
RetiredGPT-4 Turbo has been retired and shut down on 23 Oct 2026. OpenAI's official replacement is GPT-5.6 Sol. The cheapest comparable model we track is Amazon Nova Lite (Amazon) at $0.105 per 1M tokens blended.
Last verified: 24 Oct 2026 · sourced from official provider documentation
◎ You're on the watch list. We'll ping you the moment a model launches, changes price, or gets deprecated.
✕ Couldn't subscribe right now — please try again in a moment.
Free forever · no spam · unsubscribe anytime.
GPT-4 Turbo → GPT-5.6 Sol
Moving to GPT-5.6 Sol means 1.9× cheaper ($15 → $8 /1M blended) and a larger context window (128K → 1.1M).
| Spec | GPT-4 Turbo | GPT-5.6 Sol |
|---|---|---|
| Status | Retired | GA |
| Blended price /1M | $15 | $8 |
| Input / output /1M | $10 / $30 | $4 / $20 |
| Context window | 128K | 1.1M |
| Max output | 4096 | 128.000 |
| Modality | text, image | text, image |
| Knowledge cutoff | 1 Dec 2023 | 16 Feb 2026 |
API string was gpt-4-turbo-2024-04-09 → switch to gpt-5.6-sol. See GPT-5.6 Sol's full spec sheet →
Budget-friendly replacements for GPT-4 Turbo
Generally-available models that match GPT-4 Turbo's capabilities (and at least half its 128K context), ranked by blended price. Every number is computed from official catalog prices.
| Model | Blended /1M | Input / output | Context |
|---|---|---|---|
| Amazon Nova Lite Amazon | $0.105 | $0.06 / $0.24 | 300K |
| Llama 4 Scout (17B-16E Instruct) Meta | $0.15 | $0.1 / $0.3 | 10M |
| Ministral 3 8B Mistral | $0.15 | $0.15 / $0.15 | 256K |
Migrating off GPT-4 Turbo
What replaces GPT-4 Turbo?
OpenAI's recommended migration for GPT-4 Turbo is GPT-5.6 Sol. The cheapest comparable model in our catalog is Amazon Nova Lite (Amazon) at $0.105/1M blended.
Is GPT-4 Turbo still available?
No — GPT-4 Turbo has been retired (shut down 23 Oct 2026) and is no longer available via OpenAI's API.
What is the cheapest alternative to GPT-4 Turbo?
Amazon Nova Lite (Amazon) is the cheapest generally-available alternative we track that matches GPT-4 Turbo's capabilities, at $0.06 per 1M input and $0.24 per 1M output tokens ($0.105/1M blended).
Browse the full deprecation watch → or see GPT-4 Turbo's full spec sheet →
Get a heads-up before your model is retired
New models, price cuts, and deprecations — a short email when something actually changes. No spam, unsubscribe anytime.
The last few changes we caught — this is what lands in your inbox:
- RetiringO4-mini is off - OpenAI shut it down on October 23, 2026, as scheduled; migrate to gpt-5.6-terra
- RetiringO3-mini is off - OpenAI shut it down on October 23, 2026, as scheduled; migrate to gpt-5.6-sol
- RetiringO1-pro is off - OpenAI shut it down on October 23, 2026, as scheduled; migrate to gpt-5.6-sol
◎ You're on the watch list. We'll ping you the moment a model launches, changes price, or gets deprecated.
✕ Couldn't subscribe right now — please try again in a moment.
Free forever · powered by the same data on this page.