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 | DeepSeek V3.2 (Thinking)deepseek-v3.2-thinking | DeepSeek V4.1 Flashdeepseek-v4.1-flash |
|---|---|---|
| Pricing | ||
| Input | $0.19 / 1M | $0.30 / 1M |
| Output | $0.275 / 1M | $1.20 / 1M |
| Cache Write (5m) | $0.19 / 1M | $0.30 / 1M |
| Cache Write (1h) | $0.19 / 1M | $0.30 / 1M |
| Cache Read | $0.19 / 1M | $0.30 / 1M |
| Web Search | $0 / 1M | $0 / 1M |
| Context | ||
| Max context | 163.8K | 1M |
| Max output | N/A | N/A |
| Capabilities | ||
| Vision | Yes | Yes |
| Function Calling | Yes | Yes |
| JSON Mode | Yes | Yes |
| Streaming | Yes | Yes |
| Catalogue | ||
| Provider | DeepSeek | DeepSeek |
| Category | chat | chat |
| Charge type | Pay As You Go | Pay As You Go |
| Released | — | — |
| Description | ||
| Summary | DeepSeek-V3.2 is an efficiency-focused large model that combines strong reasoning with reliable tool use. It introduces DeepSeek Sparse Attention to lower compute costs for long contexts while preserving quality, and uses large-scale reinforcement learning to reach GPT-5-class reasoning (including top IMO/IOI results). An agentic task-synthesis pipeline improves how it reasons with tools in interactive settings — and developers can toggle reasoning on or off as needed. | 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. |