Nemotron middle tier for collaborative agents and high-volume reasoning workloads
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Google's proven reasoning model for coding, math, and multimodal analysis
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Tiny GPT-4.1 option for classification, routing, and very high-volume tasks
Open GPT reasoning model for self-hosted agents and controllable deployments
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
Small omni GPT for cheap multimodal assistance and production-scale traffic
Open multimodal Gemma instruction model for multilingual text generation and image understanding
Largest open Gemma 3 instruction model for multilingual text generation and visual understanding
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super-120b-a12b | 1.7 | 262.144K | $0.05 | $0.25 | 2026-03-11 | |||
| Gemini 2.5 Progoogle/gemini-2.5-pro | 1.6 | 1.04858M | $1.25 | $10 | 2025-06-17 | |||
| Mercury 2inception/mercury-2 | 1.6 | 128K | $0.25 | $0.75 | 2026-02-24 | |||
| GPT-4.1 nanoopenai/gpt-4.1-nano | 1.2 | 1.04758M | $0.1 | $0.4 | 2025-04-14 | |||
| GPT OSS 20Bopenai/gpt-oss-20b | 1.2 | 131.072K | $0.018 | $0.09 | 2025-08-05 | |||
| Trinity Large Thinkingarcee-ai/trinity-large-thinking | 1.0 | 524.288K | $0.25 | $0.9 | 2026-04-01 | |||
| Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | 1.0 | 262.144K | $0.05 | $0.2 | 2025-12-15 | |||
| GPT-4o miniopenai/gpt-4o-mini | 1.0 | 128K | $0.15 | $0.6 | 2024-07-18 | |||
| Gemma 3 12B ITgoogle/gemma-3-12b-it | 0.1 | 131.072K | $0.04 | $0.12 | 2025-03-12 | |||
| Gemma 3 27B ITgoogle/gemma-3-27b-it | 0.1 | 131.072K | $0.08 | $0.16 | 2025-03-12 |