GPT-3.5 Turbo
Pricing & Specs
OpenAI · $3 input / $6 output per 1M tokens · 16.385K context window
The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on GPT-3.5 Turbo costs about $0.0060 — roughly $6.00 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.
GPT-3.5 Turbo API Pricing
| Tokens | Price |
|---|---|
| Input | $3 / 1M tokens |
| Output | $6 / 1M tokens |
Cached tokens pricing is not available for this model.
What that means in practice
GPT-3.5 Turbo Specs
| Spec | Value |
|---|---|
| Context window | 16.385K tokens |
| Input modalities | text |
| Output modalities | text |
| Latency (measured by OpenMark) | ~340ms median response |
| Reasoning model | No |
| Tool / function calling | No |
| JSON mode | No |
| Streaming | No |
| Prompt caching | No |
Capabilities
FAQ
How much does GPT-3.5 Turbo cost?
GPT-3.5 Turbo costs $3 per 1M input tokens and $6 per 1M output tokens.
What is GPT-3.5 Turbo's context window?
GPT-3.5 Turbo has a 16.385K-token context window.
Can I test GPT-3.5 Turbo on my own task?
Yes. OpenMark lets you benchmark GPT-3.5 Turbo against 100+ models on your own task with real API calls — no API keys needed, free tier available.
Is GPT-3.5 Turbo the right model for YOUR task?
Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload — real API calls, real costs. Free tier available.