Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
| Attribute | Nemotron Nano 9B V2 (Free)nemotron-nano-9b-v2 | Nemotron 3.5 Super VL (Free)nemotron-3.5-super-vl:free | Gemini 4 Argongemini-4-argon |
|---|---|---|---|
| Pricing | |||
| Input | $0 / 1M | $0 / 1M | $2.00 / 1M |
| Output | $0 / 1M | $0 / 1M | $10.00 / 1M |
| Cache Write | $0 / 1M | $0 / 1M | — |
| Cache Read | $0 / 1M | $0 / 1M | $2.00 / 1M |
| Cache Write (5m) | — | — | $2.00 / 1M |
| Cache Write (1h) | — | — | $2.00 / 1M |
| Web Search | — | — | $0 / 1M |
| Context | |||
| Max context | 131.1K | 1M | 1M |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | No | Yes | Yes |
| Function Calling | Yes | Yes | Yes |
| JSON Mode | Yes | Yes | Yes |
| Streaming | Yes | Yes | Yes |
| Catalogue | |||
| Provider | NVIDIA | NVIDIA | |
| Category | chat | chat | chat |
| Charge type | Free | Free | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | NVIDIA Nemotron Nano 9B v2 is a 9B-parameter language model trained from scratch by NVIDIA, designed to handle both reasoning and non-reasoning tasks. It can generate an internal reasoning trace before producing a final answer, and this behavior is configurable via system prompts—allowing developers to enable or suppress visible reasoning as needed. | NVIDIA Nemotron 3.5 Super VL is an open multimodal Mixture-of-Experts (MoE) model featuring 120B total parameters with 12B activated per token. Built on a hybrid Mamba–Transformer architecture with multi-token prediction, it supports text, images, documents, GUI screenshots, and video inputs, along with a 1M-token context window for complex, long-horizon workflows. Optimized for multimodal reasoning, visual understanding, and agentic tool use, the model supports configurable reasoning modes and token budgets. It is well suited for document intelligence, web research, coding validation, customer service, GUI analysis, and video understanding, enabling efficient, long-running multimodal agent applications. | Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response. |