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 3.5 Super VL (Free)nemotron-3.5-super-vl:free | Kimi K3kimi-k3 | Gemini 3.1 Flash Image (Google Vertex AI)gemini-3.1-flash-image-vertex |
|---|---|---|---|
| Pricing | |||
| Input | $0 / 1M | $3.00 / 1M | — |
| Output | $0 / 1M | $15.00 / 1M | — |
| Cache Write | $0 / 1M | — | — |
| Cache Read | $0 / 1M | $3.00 / 1M | Not applicable |
| Cache Write (5m) | — | $3.00 / 1M | Not applicable |
| Cache Write (1h) | — | $3.00 / 1M | Not applicable |
| Web Search | — | $0 / 1M | — |
| Request | — | — | $0.067 / request |
| Billing | — | — | Pay Per Request |
| Context | |||
| Max context | 1M | 1M | N/A |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | Yes | Yes | Yes |
| Function Calling | Yes | Yes | No |
| JSON Mode | Yes | Yes | No |
| Streaming | Yes | Yes | No |
| Catalogue | |||
| Provider | NVIDIA | MoonShot AI | |
| Category | chat | chat | image |
| Charge type | Free | Pay As You Go | Pay Per Request |
| Released | — | — | — |
| Description | |||
| Summary | 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. | Kimi K3 is Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model, designed for complex coding, knowledge work, and long-horizon agentic workflows. It excels at repository-scale development, tool use, debugging, and iterative problem solving across text, images, logs, tests, and runtime feedback. Built with KDA and Attention Residuals for improved computational efficiency, Kimi K3 delivers strong performance on advanced engineering and multimodal reasoning tasks, making it well suited for autonomous coding agents and large-scale production workflows. | Gemini 3.1 Flash Image served from Google Vertex AI. Billed per image at US$0.067. Call it through /v1/chat/completions with stream set to false; the image is returned in the message content as a base64 data URI. Maximum output resolution is 2K. A request for a larger size, such as 4K or 4096x4096, returns a 2K image with the same aspect ratio at the same price. When a size is reduced, the response carries an X-Image-Resolution-Capped header with the requested and delivered size, for example 4096x4096->2048x2048. |