API pricing per million tokens
gpt-4-turboChecked 8h ago
- Input
- $10
- per 1M, list
- Output
- $30
- per 1M tokens
- Cached input
- n/a
- batch $5 / $15
- Context
- 128K
- 4K max output
Where to buy it (1)
OpenAI (list)the lab's own API$10 / $30$15 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $1,600 direct.
Helicone$1,600+0%
Kong AI Gateway$1,600+0%
LiteLLM$1,600+0%
Vercel AI Gateway$1,600+0%
AWS Bedrock$1,600+0%
Azure AI Foundry$1,600+0%
Google Vertex AI$1,600+0%
Databricks Mosaic AI$1,600+0%
Hugging Face Inference$1,600+0%
Cloudflare AI Gateway$1,680+5%
Requesty$1,680+5%
Eden AI$1,688+5.5%
OpenRouter$1,688+5.5%
Snowflake Cortex AI$1,920+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
ModelInputOutputCachedContextReleased
Claude Fable 5.1Anthropic · 1M$10 / $50in / out per 1M$10$50$0.251MSep 1, 2026
About GPT-4 Turbo
The latest GPT-4 Turbo model with vision capabilities.
Takes text, image in and returns text. First listed Apr 18, 2024. Blended price $15 per 1M tokens at 3 input to 1 output.
Questions
How much does GPT-4 Turbo cost?
$10 per million input tokens and $30 per million output tokens, or $5 and $15 through the Batch API.
What is the context window of GPT-4 Turbo?
128K 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.