API pricing per million tokens
gpt-3-5-turbo-instructChecked 6h ago
- Input
- $1.5
- per 1M, list
- Output
- $2
- per 1M tokens
- Cached input
- n/a
- no batch tier listed
- Context
- 4K
- 4K max output
Where to buy it (1)
OpenAI (list)the lab's own API$1.5 / $2$1.63 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $190.00 direct.
Helicone$190.00+0%
Kong AI Gateway$190.00+0%
LiteLLM$190.00+0%
Vercel AI Gateway$190.00+0%
AWS Bedrock$190.00+0%
Azure AI Foundry$190.00+0%
Google Vertex AI$190.00+0%
Databricks Mosaic AI$190.00+0%
Hugging Face Inference$190.00+0%
Cloudflare AI Gateway$199.50+5%
Requesty$199.50+5%
Eden AI$200.45+5.5%
OpenRouter$200.45+5.5%
Snowflake Cortex AI$228.00+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
ModelInputOutputCachedContextReleased
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
Qwen3.8 Max (0902)Qwen (Alibaba) · 1M$2 / $6in / out per 1M$2$6$0.251MSep 3, 2026
About GPT-3.5 Turbo Instruct
This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations.
Takes text in and returns text. First listed Mar 26, 2024. Blended price $1.63 per 1M tokens at 3 input to 1 output.
Questions
How much does GPT-3.5 Turbo Instruct cost?
$1.5 per million input tokens and $2 per million output tokens.
What is the context window of GPT-3.5 Turbo Instruct?
4K tokens, with up to 4K tokens of output.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.