OpenAI · language model
GPT-3.5 Turbo Instruct: pricing, context and benchmarks
GPT-3.5 Turbo Instruct is OpenAI's model released on September 28, 2023. It costs $1.5 per million input tokens and $2 per million output tokens, with a 4.1K-token context window. No independent score has been published for it so far.
| Price | 10/30 | |
|---|---|---|
| Context | 0/15 | |
| Features | 3/15 |
What you need to know about GPT-3.5 Turbo Instruct
OpenAI, based in United States, put GPT-3.5 Turbo Instruct online on September 28, 2023. It accepts text as input and produces text. Its context window reaches 4,095 tokens, larger than 1 % of the models in the registry, and it can write up to 3,685 tokens in one go.
Released more than 3 years ago, it belongs to a generation most vendors have since superseded.
GPT-3.5 Turbo Instruct pricing
On OpenRouter, GPT-3.5 Turbo Instruct costs $1.5 per million input tokens and $2 per million output tokens. Counting three tokens read for every token written, its average price is $1.625 per million, more expensive than 68 % of paid models (2.1 times the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.004. At 1,000 tasks a day, budget $120 a month. The price calculator redoes this with your own volumes.
Performance and benchmarks
Epoch AI does not yet publish a capabilities index for GPT-3.5 Turbo Instruct. We therefore show no made-up performance rating: only price, context and features count towards its score.
Features, privacy and local use
- It does not support tool calling: it is not suited to driving an AI agent that has to act.
- It can answer in an enforced JSON format (structured outputs).
- Its knowledge stops at September 2021.
Its weights are not published: it can only be used through the OpenAI API or a broker such as OpenRouter, which means sending your data off your machines.
Other OpenAI models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| GPT-6.1 Sol | Sep 29, 2026 | $4 | 168.4 |
| GPT-6.1 Sol Pro | Sep 29, 2026 | $4 | — |
| GPT-6 Sol | Sep 22, 2026 | $4 | 163.7 |
| GPT-6 Luna | Sep 22, 2026 | $0.2 | 156.8 |
| GPT-6 Luna Pro | Sep 22, 2026 | $0.2 | — |
| GPT-6 Sol Pro | Sep 22, 2026 | $4 | — |
| GPT-6 Astra | Sep 4, 2026 | $20 | 168.8 |
| GPT-6 Astra Pro | Sep 4, 2026 | $20 | — |
Verdict
Computed score: 22/100, from public data (performance, price, context, features).
Limitations
- Short context (4.1K tokens): long documents must be split.
- No tool calling: unusable as an agent's brain.
- No independent score published: performance cannot be verified.
- Older generation, often replaced by a newer model from the same vendor.
- Text only: reads neither images nor files.
Avoid if…
- your data must not leave your servers;
- you are building an agent that must call tools;
- you analyse long documents in one go.
Alternatives
Comparisons and tools
Learn more
Frequently asked questions
How much does GPT-3.5 Turbo Instruct cost?
$1.5 per million input tokens and $2 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.004.
How big is GPT-3.5 Turbo Instruct's context window?
4,095 tokens, roughly 3,000 words, with a maximum of 3,685 output tokens.
Can GPT-3.5 Turbo Instruct run locally?
No, OpenAI does not publish its weights: it is API-only.
Is GPT-3.5 Turbo Instruct suitable for an AI agent?
No: without tool calling it cannot act, only answer.
What are the alternatives to GPT-3.5 Turbo Instruct?
The closest models on price and performance are Nano Banana 2 (Gemini 3.1 Flash Image Preview), Aion-RP 1.0 (8B), and Magnum v4 72B.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score