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.
- Gemini 4 ArgonGoogleRemove
- DeepSeek V4.1 Flash 1017DeepSeekRemove
- Perceptron Mk1.5PerceptronRemove
- GLM 5Z.AIRemove
4 is the maximum. Remove one to add another.
| Attribute | Gemini 4 Argongemini-4-argon | DeepSeek V4.1 Flash 1017deepseek-v4.1-flash-1017 | Perceptron Mk1.5perceptron-mk1.5 | GLM 5glm-5 |
|---|---|---|---|---|
| Pricing | ||||
| Input | $2.00 / 1M | $0.10 / 1M | $0.15 / 1M | $0.60 / 1M |
| Output | $10.00 / 1M | $0.50 / 1M | $1.50 / 1M | $2.20 / 1M |
| Cache Write (5m) | $2.00 / 1M | $0.10 / 1M | $0.15 / 1M | $0.60 / 1M |
| Cache Write (1h) | $2.00 / 1M | $0.10 / 1M | $0.15 / 1M | $0.60 / 1M |
| Cache Read | $2.00 / 1M | $0.10 / 1M | $0.15 / 1M | $0.60 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | 1M | 1M | 36.9K | 202.8K |
| Max output | N/A | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | Yes | Yes | No | Yes |
| Function Calling | Yes | Yes | No | Yes |
| JSON Mode | Yes | Yes | No | Yes |
| Streaming | Yes | Yes | Yes | Yes |
| Catalogue | ||||
| Provider | DeepSeek | Perceptron | Z.AI | |
| Category | chat | chat | chat | chat |
| Charge type | Pay As You Go | 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 1017 is the October 17, 2026 snapshot of DeepSeek’s cost-efficient Mixture-of-Experts (MoE) model, built on its innovative Causal Encoder-Decoder (CED) architecture. Featuring 552B total parameters with 8B activated for input and 16B for output, it combines efficient inference with native multimodal understanding through jointly trained text and visual representations. Optimized for coding, terminal and computer-use agents, and long-horizon workflows, the model introduces compressed KV caching that reduces cache memory usage to approximately one-quarter of the previous Flash generation. DeepSeek reports that it surpasses V4 Pro in performance, inference speed, and task completion time, making it well suited for cost-efficient autonomous agents, complex software engineering, and long-context analysis. | Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token. | GLM-5 is Z.AI's flagship open-source foundation model, engineered for complex systems design and long-horizon agent workflows. Built with expert developers in mind, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With strong agentic planning, deep backend reasoning, and iterative self-correction capabilities, GLM-5 extends beyond traditional code generation to support full-system construction and autonomous execution, making it well suited for advanced engineering and agent-driven development environments. |