Models/gpt-4.1-mini

gpt-4.1-miniActive · Inference

Replicate · Released Apr 2025 · Proprietary

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

Context
0
Max output
0
Input
$0.40
Output
$1.60
Cached in
-
Latency
-

Capabilities

Core
Streaming
Function calling
JSON mode
Structured outputs
Multimodal
Vision
Image input
Audio
Image generation
Video
Advanced
Reasoning
Tool calling
MCP
Prompt caching
Batch API
Embeddings

Benchmarks

Aider Polyglot32.4

Details

ProviderReplicate
ReleasedApr 2025
LicenseProprietary
InputText
OutputText
Throughput-
Availability100%

Related models