API pricing per million tokens
- Input
- $2
- per 1M, list
- Output
- $8
- per 1M tokens
- Cached input
- $0.5
- batch $1 / $4
- Context
- 1.05M
- 33K max output
Where to buy it (4)
Azure AI Foundrydefault region$2 / $8cached $0.5
OpenAI (list)the lab's own API$2 / $8cached $0.5
Snowflake Cortex AI (AI_COMPLETE)default region, 1.2 AI Credits per 1M input tokens, 4.8 per 1M output tokens+20%$2.4 / $9.6$4.2 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $360.00 direct.
Helicone$360.00+0%
Kong AI Gateway$360.00+0%
LiteLLM$360.00+0%
Vercel AI Gateway$360.00+0%
AWS Bedrock$360.00+0%
Google Vertex AI$360.00+0%
Databricks Mosaic AI$360.00+0%
Hugging Face Inference$360.00+0%
Cloudflare AI Gateway$378.00+5%
Requesty$378.00+5%
Eden AI$379.80+5.5%
OpenRouter$379.80+5.5%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
Muse Spark 1.3Meta · 1M$1.25 / $4.25in / out per 1M$1.25$4.25$0.151MSep 2, 2026
Gemini 3.1 Pro PreviewGoogle Gemini API · 1M$2 / $12in / out per 1M$2$12$0.21MFeb 19, 2026
Qwen3.8 Max (0902)Qwen (Alibaba) · 1M$2 / $6in / out per 1M$2$6$0.251MSep 3, 2026
About GPT-4.1
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning.
Takes image, text, files in and returns text. First listed Apr 15, 2025. Blended price $3.5 per 1M tokens at 3 input to 1 output.
Questions
How much does GPT-4.1 cost?
$2 per million input tokens and $8 per million output tokens, with cached input at $0.5, or $1 and $4 through the Batch API.
What is the context window of GPT-4.1?
1.05M tokens, with up to 33K tokens of output.
Where is GPT-4.1 cheapest?
Of 4 routes tracked, Azure AI Foundry is cheapest at $2 input and $8 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.