API pricing per million tokens
- Input
- $0.5
- per 1M, list
- Output
- $1.5
- per 1M tokens
- Cached input
- n/a
- batch $0.25 / $0.75
- Context
- 16K
- 4K max output
Price history
List price since Mar 26, 2024, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
| Seen | Model | Old price | New price | Change |
|---|---|---|---|---|
| Apr 18, 2024 |  GPT-3.5 TurboInput $1 to $0.5, Output $2 to $1.5 | Input $1Output $2 | Input $0.5Output $1.5 | -50% |
Through a gateway
Your own numbers100M input and 20M output tokens a month: $80.00 direct.
Helicone$80.00+0%
Kong AI Gateway$80.00+0%
LiteLLM$80.00+0%
Vercel AI Gateway$80.00+0%
AWS Bedrock$80.00+0%
Azure AI Foundry$80.00+0%
Google Vertex AI$80.00+0%
Databricks Mosaic AI$80.00+0%
Hugging Face Inference$80.00+0%
Cloudflare AI Gateway$84.00+5%
Requesty$84.00+5%
Eden AI$84.40+5.5%
OpenRouter$84.40+5.5%
Snowflake Cortex AI$96.00+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
Gemini 3.8 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MSep 2, 2026
GLM 5.3Z.ai · via DeepInfra (fp4) · 1.31M$0.563 / $2.5in / out per 1M$0.563$2.5$0.1251.31MAug 18, 2026
About GPT-3.5 Turbo
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.
Takes text in and returns text. First listed Mar 26, 2024. Blended price $0.75 per 1M tokens at 3 input to 1 output.
Questions
How much does GPT-3.5 Turbo cost?
$0.5 per million input tokens and $1.5 per million output tokens, or $0.25 and $0.75 through the Batch API.
What is the context window of GPT-3.5 Turbo?
16K tokens, with up to 4K tokens of output.
Has GPT-3.5 Turbo's price changed?
Yes. The output price went from $2 to $1.5, first seen Apr 18, 2024.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.