GPT-3.5 Turbo

Fast and cost-effective model for simple tasks and conversational applications.

gpt-3.5-turbo
STABLEGet StartedView uptime
16,385 context
Released November 30, 2022
Starting at $0.45/M (10% off) input tokens
Starting at $1.35/M (10% off) output tokens
Streaming
Tools
JSON Output
No ratings yetSign in to rate
10% offthis model via OpenAI

Select Provider

All Providers for GPT-3.5 Turbo

OffRail routes requests to the best providers that are able to handle your prompt size and parameters.

OpenAI
Context: 16.4k10% off
Input
$0.5$0.45
10% off
/M tokens
Cache Read
/M tokens
Output
$1.5$1.35
10% off
/M tokens
Get Started
Azure
Context: 16.4k
Input
$0.5
/M tokens
Cache Read
/M tokens
Output
$1.5
/M tokens
Get Started

Frequently asked questions

What is GPT-3.5 Turbo?

Fast and cost-effective model for simple tasks and conversational applications. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does GPT-3.5 Turbo cost?

Pricing for GPT-3.5 Turbo on OffRail starts at $0.50 per million input tokens and $1.50 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of GPT-3.5 Turbo?

GPT-3.5 Turbo supports a context window of up to 16,385 tokens on its largest provider deployment.

Which providers serve GPT-3.5 Turbo?

GPT-3.5 Turbo is served by OpenAI, Azure through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does GPT-3.5 Turbo support tool calling and structured outputs?

GPT-3.5 Turbo supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).

When was GPT-3.5 Turbo released?

GPT-3.5 Turbo was released on November 30, 2022.