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 V4.1 Flash 1017deepseek-v4.1-flash-1017 | Qwen3 Reranker 8BQwen/Qwen3-Reranker-8B |
|---|---|---|
| Pricing | ||
| Input | $0.10 / 1M | $0.56 / 1M |
| Output | $0.50 / 1M | $0.56 / 1M |
| Cache Write (5m) | $0.10 / 1M | Not applicable |
| Cache Write (1h) | $0.10 / 1M | Not applicable |
| Cache Read | $0.10 / 1M | Not applicable |
| Web Search | $0 / 1M | $0 / 1M |
| Context | ||
| Max context | 1M | 8.2K |
| Max output | N/A | N/A |
| Capabilities | ||
| Vision | Yes | No |
| Function Calling | Yes | No |
| JSON Mode | Yes | No |
| Streaming | Yes | No |
| Catalogue | ||
| Provider | DeepSeek | Reranker |
| Category | chat | chat |
| Charge type | Pay As You Go | Pay As You Go |
| Released | — | — |
| Description | ||
| Summary | 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. | — |