added
OpenAI's new o3, o4-mini, GPT-4.1 models
about 2 months ago by Cormick Marskamp
OpenAI's latest models can be found in the model garden.
When to use what model
- o-series models are purpose-built for reasoning and tool-use. Choose o3 when raw capability beats everything else; use o4-mini when you still need strong reasoning but want 10× cheaper tokens and snappier replies.
- GPT-4.1 family is the evolution of the “generalist” GPT line. The full model gives you 1 M-token context with strong instruction following; mini trims cost/latency for mainstream workloads; nano pushes pricing and speed to the floor for simple or massive-scale tasks.
| Feature | GPT-4.1 | GPT-4.1 mini | GPT-4.1 nano | o3 | o4 mini |
|---|---|---|---|---|---|
| Training cutoff date | May 2024 | May 2024 | May 2024 | May 2024 | May 2024 |
| Context window | 1M | 1M | 1M | 200k | 200k |
| Max output tokens | 32.768 | 32.768 | 32.768 | 100k | 100k |
| Input price | $2/M Tokens | $0.40/M Tokens | $0.10/M Tokens | $10/M tokens | $1.10/M tokens |
| Output price | $8/M Tokens | $1.60/M Tokens | $0.40/M Tokens | $40/M tokens | $4.40/M tokens |
| Latency | Moderate | Fast | Very fast | Slow | Moderate |
| When to use? | Long-context chat, knowledge-work, multimodal apps needing top GPT quality | Everyday product features, prototyping & chat where speed and price count | Real-time, latency-critical or large-scale batch jobs on a tight budget | Deep research, complex multi-step reasoning, high-stakes coding/science tasks | Reasoning workloads where cost & throughput matter; API agents, math & data-science |