Migrate off GPT-3.5 Turbo
DeprecatedGPT-3.5 Turbo is deprecated and shuts down on 23 Oct 2026. OpenAI's official replacement is GPT-5.6 Terra. The cheapest comparable model we track is Llama 3.1 8B Instruct (Meta) at $0.022 per 1M tokens blended.
Last verified: 26 Sep 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-3.5 Turbo → GPT-5.6 Terra
Moving to GPT-5.6 Terra means 6.0× more expensive ($0.75 → $4.50 /1M blended) and a larger context window (16K → 1.1M).
| Spec | GPT-3.5 Turbo | GPT-5.6 Terra |
|---|---|---|
| Status | Deprecated | GA |
| Blended price /1M | $0.75 | $4.50 |
| Input / output /1M | $0.5 / $1.50 | $2 / $12 |
| Context window | 16K | 1.1M |
| Max output | 4096 | 128.000 |
| Modality | text | text, image |
| Knowledge cutoff | 1 Sep 2021 | 16 Feb 2026 |
API string was gpt-3.5-turbo-0125 → switch to gpt-5.6-terra. See GPT-5.6 Terra's full spec sheet →
Budget-friendly replacements for GPT-3.5 Turbo
Generally-available models that match GPT-3.5 Turbo's capabilities (and at least half its 16K context), ranked by blended price. Every number is computed from official catalog prices.
| Model | Blended /1M | Input / output | Context |
|---|---|---|---|
| Llama 3.1 8B Instruct Meta | $0.022 | $0.02 / $0.03 | 128K |
| Amazon Nova Micro Amazon | $0.061 | $0.035 / $0.14 | 128K |
| Command R7B Cohere | $0.066 | $0.037 / $0.15 | 128K |
Migrating off GPT-3.5 Turbo
What replaces GPT-3.5 Turbo?
OpenAI's recommended migration for GPT-3.5 Turbo is GPT-5.6 Terra. The cheapest comparable model in our catalog is Llama 3.1 8B Instruct (Meta) at $0.022/1M blended.
When is GPT-3.5 Turbo shut down?
GPT-3.5 Turbo is deprecated and scheduled to shut down on 23 Oct 2026 (deprecated 22 Apr 2026). Migrate before that date to avoid a 404.
What is the cheapest alternative to GPT-3.5 Turbo?
Llama 3.1 8B Instruct (Meta) is the cheapest generally-available alternative we track that matches GPT-3.5 Turbo's capabilities, at $0.02 per 1M input and $0.03 per 1M output tokens ($0.022/1M blended).
Browse the full deprecation watch → or see GPT-3.5 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:
- DeprecatingGoogle re-pointed the Gemini 2.5 TTS migration path past the 3.1 preview and onto the new GA 3.8 TTS models
- New modelGemini 3.8 Flash TTS is GA - a flagship text-to-speech model at under half the audio rate of the preview it replaces, on a two-column price schedule
- New modelGemini 3.8 Flash-Lite TTS is GA - Google's cost-efficient TTS, which Google says was built to replace Gemini 3.1 Flash TTS
◎ 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.