API pricing per million tokens
- Input
- $3
- per 1M, list
- Output
- $4
- per 1M tokens
- Cached input
- n/a
- no batch tier listed
- Context
- 16K
- 4K max output
Where to buy it (2)
Azure AI Foundrydefault region$3 / $4$3.25 blended
OpenAI (list)the lab's own API$3 / $4$3.25 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $380.00 direct.
Helicone$380.00+0%
Kong AI Gateway$380.00+0%
LiteLLM$380.00+0%
Vercel AI Gateway$380.00+0%
AWS Bedrock$380.00+0%
Azure AI Foundry$380.00+0%
Google Vertex AI$380.00+0%
Databricks Mosaic AI$380.00+0%
Hugging Face Inference$380.00+0%
Cloudflare AI Gateway$399.00+5%
Requesty$399.00+5%
Eden AI$400.90+5.5%
OpenRouter$400.90+5.5%
Snowflake Cortex AI$456.00+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
BigQuery MLn/a
Cloudflare Workers AIn/a
NVIDIA NIMn/a
Related models
GPT-6 LunaOpenAI · 1.05M$0.1 / $0.5in / out per 1M$0.1$0.5$0.011.05MSep 22, 2026
GPT-6 Luna ProOpenAI · 1.05M$0.1 / $0.5in / out per 1M$0.1$0.5$0.011.05MSep 22, 2026
GPT-6 SolOpenAI · 1.05M$2 / $10in / out per 1M$2$10$0.21.05MSep 22, 2026
GPT-6 Sol ProOpenAI · 1.05M$2 / $10in / out per 1M$2$10$0.21.05MSep 22, 2026
Muse Spark 1.3Meta · 1M$1.25 / $4.25in / out per 1M$1.25$4.25$0.151MSep 2, 2026
Gemini 3.8 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MSep 2, 2026
Gemini 3.1 Pro PreviewGoogle Gemini API · 1M$2 / $12in / out per 1M$2$12$0.21MFeb 19, 2026
Muse Spark 1.1Meta · 1M$1.25 / $4.25in / out per 1M$1.25$4.25$0.151MJul 16, 2026
About GPT-3.5 Turbo 16k
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost.
Takes text in and returns text. First listed Mar 26, 2024. Blended price $3.25 per 1M tokens at 3 input to 1 output.
Questions
How much does GPT-3.5 Turbo 16k cost?
$3 per million input tokens and $4 per million output tokens.
What is the context window of GPT-3.5 Turbo 16k?
16K tokens, with up to 4K tokens of output.
Where is GPT-3.5 Turbo 16k cheapest?
Of 2 routes tracked, Azure AI Foundry is cheapest at $3 input and $4 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.