GPT-4.1 Mini
OpenAI released 2025-04-14
GPT-5.6 Luna is both better and cheaper.
It scores +37.5 higher and costs 36% less ($0.450/M against $0.700/M) on this workload — and it does everything this model does.
DeepSeek V4 Flash 0731 is cheaper still (85% less) but drops no image, file input.
The same model via batch is 50% cheaper ($0.350/M) — same weights, different latency.
Every price dimension
| Input | $0.400/M |
|---|---|
| Output | $1.60/M |
| Cached input | $0.100/M |
| Web search | $0.01/call |
Independent scores
| Intelligence | 14.8 |
|---|---|
| Coding | 20.2 |
| Agentic | 1.8 |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Capability
| Context window | 1.0M |
|---|---|
| Max output | 33K |
| Input modes | image, text, file |
| Tool use | yes |
| Reasoning | no |
| Knowledge cutoff | 2024-06-30 |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
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...