GPT-3.5 Turbo (older v0613)
OpenAI · released Jan 25, 2024
- Type
- Closed
- Input
- $3.00
- Output
- $4.00
- Cached
- None held
List price · per 1M tokens · OpenAI at 16K context · machine-readable source ↗
Our take
Written Sep 3, 2026GPT-3.5 Turbo is an older text-only model from OpenAI, released in early 2024 with a four-thousand-token request limit. It remains available through select providers at budget rates, though newer models outperform it on every measured dimension we track.
Use this as a fallback when newer models are unavailable on a specific integration, or for cost-sensitive batch jobs where a four-thousand-token limit suffices and speed is not critical. Skip it if you need image, audio or video input, a longer request limit, or the best throughput for your dollar.
The case for it
- Lowest price among its three tracked offers comes via third-party routing, not direct from the lab.
- Fastest measured deployment runs at nearly twice the tokens per second of the slowest one.
The case against it
- Smallest request limit in its own data, with no alternative configuration listed.
- Slowest measured deployment is also the highest-priced one, the direct-from-lab route.
- Text-to-text only; no image, audio or video handling listed.
How good is it?
An older general-purpose text model for chat, drafting and code, now behind newer options on all three.
- getting answers to everyday questionsArena Text (overall) · 165th of 168
- drafts, rewrites and editingArena Creative Writing · 164th of 168
- writing and completing codeArena Coding · 163rd of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)165th of 168 · 1226
CodingWriting and fixing code on its own
Arena Coding163rd of 168 · 1275
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing164th of 168 · 1191
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked 2 hours ago — each listing carries its own date.
OpenAI, direct
The lab is the cheapest at this context. The strip above and this offer are the same one, compared at 16K of context. 2 cheaper rows below are outside that comparison: a different context length.
- per 1M tokens
- $3.00 in / $4.00 out
- Context served
- 16K
- Throughput
- ~18 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $1.00 / $2.00checked 2 hours ago | 4K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIThrough OpenRouter | $1.00 / $2.00checked 2 hours ago | 4K4K max reply | 50 tok/s | No | No | Confirmed |
| OpenAIDirect | $3.00 / $4.00checked 2 hours ago | 16K4K max reply | 18 tok/s | No | Yesunknown period | Unknown |
OpenRouter
Microsoft Azure AIAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 1 appears 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 | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 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
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 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-older-v0613