Compact GPT model for low-latency assistance and high-volume workloads
GPT-3.5-turbo by openai is offered by 12 providers on this page. Its official list price is $0.50 per 1M input tokens and $1.50 per 1M output tokens.
Artificial Analysis rates it 5.5 on the Intelligence Index, with 10.7 for coding. Against its lowest blended price of $0.688 per 1M, that is roughly 8 index points per dollar, which is the value ratio the leaderboards rank on.
The context window is 16,385 tokens at the reference host, but hosts report different limits, from 16,384 to 16,385, so the usable window depends on the provider you pick. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2021-09-01.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Poe | Gateway | $0.45 | $1.40 | — | — | 16,384 ⚠ | 2,048 | |
| NanoGPT | Gateway | $0.50 | $1.50 | — | — | 16,385 | 4,096 | |
| Kilo Gateway | Gateway | $0.50 | $1.50 | — | — | 16,385 | 4,096 | |
| OpenRouter | Gateway | $0.50 | $1.50 | — | — | 16,385 | 4,096 | |
| Impossibl | Gateway | $0.50 | $1.50 | — | — | 16,385 | 4,096 | |
| Vercel AI Gateway | Cloud | $0.50 | $1.50 | — | — | 16,385 | 4,096 | |
| OrcaRouter | Gateway | $0.50 | $1.50 | $0 | — | 16,385 | 4,096 | |
| Merge Gateway | Gateway | $0.50 | $1.50 | — | — | 16,385 | 4,096 | |
| Eden AI | Gateway | $0.50 | $1.50 | — | — | 16,385 | 4,096 | |
| DevPass (LLM Gateway) | Gateway | $0.50 | $1.50 | $0 | — | 16,385 | 4,096 | |
| OpenAIOfficial | First-party | $0.50 | $1.50 | $0 | — | 16,385 | 4,096 | deprecated |
| LLM Gateway | Gateway | $0.50 | $1.50 | — | — | 16,385 | 4,096 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 10.7 | index | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.