GPT-3.5 Turbo Instruct
OpenAI · released Sep 28, 2023
- Type
- Closed
- Input
- $0.50
- Output
- $1.50
- Cached
- None held
List price · per 1M tokens · OpenAI at 16K context · machine-readable source ↗
Our take
Written Sep 3, 2026GPT-3.5 Turbo Instruct is a legacy text-only model from OpenAI that follows instructions rather than chatting. Its narrow four-thousand-token request limit and lack of published quality scores make it a dated choice for anything beyond light tasks.
Use this for simple instruction tasks where a short prompt is enough and you do not need chat formatting. It is the cheaper of the two tracked offers for this model. Skip it if you need long documents, multi-turn work, or any measured quality data to compare against alternatives.
The case for it
- Lower cost through OpenAI direct than through the reseller route we list.
- Text-only simplicity avoids paying for capabilities you do not need if your task is pure instruction following.
The case against it
- Very short request limit by current standards, which blocks document work and multi-turn tasks.
- No measured quality scores in our data, so there is no independent benchmark to judge it by.
- Slow on the only measured endpoint at six tokens per second.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Where to rent it
Prices checked 2 hours ago — each listing carries its own date.
OpenAI, direct
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
- ~20 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.50 / $1.50checked 2 hours ago | 16K | not measured | Unknown | Unknown | Unknown |
| OpenAIDirect | $0.50 / $1.50checked 2 hours ago | 16K4K max reply | 20 tok/s | No | Yesunknown period | Unknown |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- No independent board has scored it, 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 does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak 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
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text in, text out
- Catalogue slug
- openai-gpt-3-5-turbo-instruct