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 | MiniMax M2minimax-m2 | Kimi K3.1 Prokimi-k3.1-pro | Gemini 4 Argongemini-4-argon |
|---|---|---|---|
| Pricing | |||
| Input | $0.15 / 1M | $2.00 / 1M | $2.00 / 1M |
| Output | $0.45 / 1M | $10.00 / 1M | $10.00 / 1M |
| Cache Write (5m) | $0.15 / 1M | $2.00 / 1M | $2.00 / 1M |
| Cache Write (1h) | $0.15 / 1M | $2.00 / 1M | $2.00 / 1M |
| Cache Read | $0.15 / 1M | $2.00 / 1M | $2.00 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 196.6K | 1M | 1M |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | Yes | Yes | Yes |
| Function Calling | Yes | Yes | Yes |
| JSON Mode | Yes | Yes | Yes |
| Streaming | Yes | Yes | Yes |
| Catalogue | |||
| Provider | MiniMax | MoonShot AI | |
| Category | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | MiniMax-M2 is a compact, high-efficiency model with 10B active (230B total) parameters, optimized for coding and agentic workflows. It delivers near-frontier reasoning and tool use, excels at multi-file coding tasks and compile-run-fix loops, and performs strongly on benchmarks like SWE-Bench and Terminal-Bench. It also handles long-horizon planning and recovery in agent evaluations, ranking among the top open models across reasoning domains. With fast inference and low cost, it’s ideal for large-scale agents and developer assistants — and works best when reasoning is preserved across turns. | Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model, building on Kimi K3 with enhanced post-training for advanced reasoning and autonomous task execution. It features a 1M-token context window and native image and video understanding, enabling complex, long-context multimodal workflows. Optimized for long-horizon coding, 3D creation, financial research, and end-to-end agentic knowledge work, Kimi K3.1 Pro is well suited for autonomous software engineering, multimodal analysis, and complex professional workflows that require sustained reasoning and reliable execution. | 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. |