Context
16K
Max output
4K
Serving providers
4
Cheapest input
$0.50 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.50 to $1.50 per 1M tokens across 4 providers, so the dearest route costs 200% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
AzureCheapest$0.50$1.501
ComponentUnitStandardBatchCached
Text input/1M tok$0.5000
Text output/1M tok$1.50
OpenAICheapest$0.50$1.501
Vercel AI GatewayCheapest$0.50$1.501
OpenRouter$1.50$2.001

Price history

input + output $/1M since we started tracking
Input Output
Input down 67% since first tracked
$0.000$0.500$1.00$1.50$2.00Sep 20Jul 30Sep 24Jun 22$1.50$0.500

Cost calculator

estimate your monthly spend on this model
$220
estimated / month

Model IDs

copy the exact identifier for your platform
azure/gpt-3.5-turbogpt-3.5-turbovercel_ai_gateway/openai/gpt-3.5-turboopenrouter/openai/gpt-3.5-turbo

Frequently asked questions

GPT-3.5 Turbo pricing, context and availability

How much does GPT-3.5 Turbo cost?

GPT-3.5 Turbo costs $0.50 per 1M input tokens and $1.50 per 1M output tokens at its cheapest provider via Azure. Across 4 serving providers, input prices range from $0.50 to $1.50 per 1M tokens.

What is the context window of GPT-3.5 Turbo?

GPT-3.5 Turbo accepts up to 16K tokens of context and can return up to 4K output tokens.

Which providers serve GPT-3.5 Turbo?

GPT-3.5 Turbo is available from 4 serving providers, each with its own pricing and model ID. Azure is currently the cheapest.

What can GPT-3.5 Turbo do?

GPT-3.5 Turbo supports tool use and prompt caching.

Other OpenAI models

compare pricing across the OpenAI lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI