GPT-3.5 Turbo Instruct
OpenAI · released Sep 28, 2023
- Type
- Proprietary
- Input
- $0.50
- Output
- $1.50
- Cached
- Not published
List price · per 1M tokens · OpenAI at 16K context · source ↗
Our take
Written Aug 3, 2026GPT-3.5 Turbo Instruct is a text-only instruction-following model from OpenAI with a four-thousand-token request limit and no published parameter count. It is positioned for simple completion tasks where cost matters, though no benchmark scores are available to verify its performance.
Pick this for simple instruction-following tasks where a four-thousand-token context suffices and you want the lowest-cost direct access. Use it for legacy integrations still requiring the Instruct API format. Skip it if you need image or audio input, a larger request limit, or measured quality data to compare against alternatives.
The case for it
- Lowest-cost direct access through OpenAI, noticeably cheaper than the alternative routed offer.
- Fits legacy integrations that still require the Instruct API format.
The case against it
- No benchmark scores in our data, so performance against contemporaries is unverified.
- Four-thousand-token request limit, with no larger variant offered.
- Text-to-text only; no image, audio or other multimodal input.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up GPT-3.5 Turbo Instruct — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts OpenAI on 16K of context.
- per 1M tokens
- $0.50 in / $1.50 out
- Context served
- 16K
- Throughput
- ~58 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenAI | $0.50 / $1.50 | 16K4K out | 58 tok/s | No | Yesunknown period | Unknown |
| OpenRouter | $1.50 / $2.00 | 4K | not measured | Unknown | Unknown | Unknown |
OpenRouterAcross the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenAI | ✓ | ✓ | ✓ |
| OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 1 of 2 listings says yes, 1 says no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- openai-gpt-3-5-turbo-instruct