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 | Gemini 4 Argongemini-4-argon | Llama 3.2 1b Instructllama-3.2-1b-instruct |
|---|---|---|
| Pricing | ||
| Input | $2.00 / 1M | $0.0025 / 1M |
| Output | $10.00 / 1M | $0.005 / 1M |
| Cache Write (5m) | $2.00 / 1M | $0.0025 / 1M |
| Cache Write (1h) | $2.00 / 1M | $0.0025 / 1M |
| Cache Read | $2.00 / 1M | $0.0025 / 1M |
| Web Search | $0 / 1M | $0 / 1M |
| Context | ||
| Max context | 1M | N/A |
| Max output | N/A | N/A |
| Capabilities | ||
| Vision | Yes | No |
| Function Calling | Yes | Yes |
| JSON Mode | Yes | Yes |
| Streaming | Yes | Yes |
| Catalogue | ||
| Provider | Meta | |
| Category | chat | chat |
| Charge type | Pay As You Go | Pay As You Go |
| Released | — | — |
| Description | ||
| Summary | 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. | Llama 3.2 1B is a lightweight 1-billion-parameter model built for efficient NLP tasks like summarization, conversation, and multilingual analysis. It runs well in low-resource environments, supports eight core languages (and can be fine-tuned for more), making it a good fit for developers who need capable, multilingual AI without heavy compute costs. |