OpenAI · Released Sep 28, 2023
GPT-3.5 Turbo Instruct
This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.
- Released
- Sep 28 2023
- Context window
- 4K 4K out
- Input / 1M tokens
- $1.50 from $1.40
- Output / 1M tokens
- $2.00 from $1.80
Where to run it
5 providers compared
Cheapest: Poe at $1.40 / $1.80 per 1M input / output tokens — 8% less than the priciest option.
| Provider | Input | Output | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|
| Poe | $1.40 | $1.80 | 4K | 1K | — | Cheapest |
| OpenAIno tool calling | $1.50 | $2.00 | 4K | 4K | 0%24h | +8% |
| Kilo Gatewayno tool calling | $1.50 | $2.00 | 4K | 4K | — | +8% |
| Azureno tool calling | $1.50 | $2.00 | 4K | 4K | — | +8% |
| Azure Cognitive Servicesno tool calling | $1.50 | $2.00 | 4K | 4K | — | +8% |
Value
Price vs. performance
GPT-3.5 Turbo Instruct Other OpenAI Other labs Value frontier · METR time horizon vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
1 benchmark score
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| METR time horizonSoftware engineering · Length of software task solved more often than not | 1 min | #23of 23 | Claude Opus 4.612 h |
Specs
Details
- Model ID
openai/gpt-3.5-turbo-instruct- Developer
- OpenAI
- Release date
- Sep 28, 2023 ·
- Context window
- 4,095 tokens
- Max output
- 3,685 tokens
- API price
- $1.50 / $2.00 per 1M input / output tokens
- Providers
- 5
- Input types
- text
- Reasoning
- No
- Tool calling
- No
- Open weights
- No
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.