OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Tiny GPT-4.1 option for classification, routing, and very high-volume tasks
22 providers
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| OpenAI: o4 Mini (batch)openai/o4-mini:batch | OpenAI |
991.0 | 200K | $0.55 | $2.2 | — | ||
| Meta: Llama 4 Scoutmeta-llama/llama-4-scout | Meta |
896.0 | 327.68K | $0.1 | $0.3 | — | ||
| GPT-4.1 nanoopenai/gpt-4.1-nano | OpenAI |
891.0 | 1.04758M | $0.1 | $0.4 | 2025-04-14 | ||
| OpenAI: GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batch | OpenAI |
891.0 | 1.04758M | $0.05 | $0.2 | — |