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.
- mai-ds-r1:freeNot in the catalogueRemove
- Gemini 4 ArgonGoogleRemove
- DeepSeek V4.1 FlashDeepSeekRemove
- Perceptron Mk1.5PerceptronRemove
4 is the maximum. Remove one to add another.
| Attribute | mai-ds-r1:freeNot in the catalogue | Gemini 4 Argongemini-4-argon | DeepSeek V4.1 Flashdeepseek-v4.1-flash | Perceptron Mk1.5perceptron-mk1.5 |
|---|---|---|---|---|
| Pricing | ||||
| Input | — | $2.00 / 1M | $0.30 / 1M | $0.15 / 1M |
| Output | — | $10.00 / 1M | $1.20 / 1M | $1.50 / 1M |
| Cache Write (5m) | — | $2.00 / 1M | $0.30 / 1M | $0.15 / 1M |
| Cache Write (1h) | — | $2.00 / 1M | $0.30 / 1M | $0.15 / 1M |
| Cache Read | — | $2.00 / 1M | $0.30 / 1M | $0.15 / 1M |
| Web Search | — | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | — | 1M | 1M | 36.9K |
| Max output | — | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | — | Yes | Yes | No |
| Function Calling | — | Yes | Yes | No |
| JSON Mode | — | Yes | Yes | No |
| Streaming | — | Yes | Yes | Yes |
| Catalogue | ||||
| Provider | — | DeepSeek | Perceptron | |
| Category | — | chat | chat | chat |
| Charge type | — | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | — | — | 2026-09-25 |
| 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. | DeepSeek V4.1 Flash is a cost-efficient sparse Mixture-of-Experts (MoE) model in DeepSeek's V4.1 family, optimized for coding, reasoning, and agentic workflows. Despite its efficiency-focused positioning, DeepSeek reports that it surpasses the previous V4 Pro in performance, inference speed, and overall task completion time. The model is particularly strong at long-horizon, multi-step execution, making it well suited for coding agents, complex problem solving, and autonomous workflows that must reliably carry tasks through to completion. | Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token. |