prices synced 2026-09-21

GPT-4.1 Mini (batch)

OpenAI · Multimodal · Released Apr 2025

Compare

OpenAI's GPT-4.1 Mini optimized for batch processing, with 1 million token context window for asynchronous workloads.

Strengths
Runs fast and efficient inference on large document batches without token usage or latency constraints.
Best for
High-volume classification, extraction, and summarization tasks submitted as batch jobs over hours or days.
Limitations
Limited to batch API with asynchronous processing; slower real-time performance than the standard GPT-4.1 Mini, and does not support reasoning or chain-of-thought modes.

Input / 1M

$0.2

Output / 1M

$0.8

Cached input / 1M

$0.05

Context window

1.05M

Price history

Price per 1M tokens over timeOutput $0.8; Input $0.2 as of Aug 2026.$0$0.2$0.4$0.6$0.8Output on 6 Aug 2026: $0.8Out $0.8Input on 6 Aug 2026: $0.2In $0.2Aug 2026

Snapshots

Effective Input Output Cached in Note Source
6 Aug 2026 $0.2 $0.8 $0.05 Imported from OpenRouter openrouter.ai

More from OpenAI

Report a problem