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 | Transcribe 1 Protranscribe-1-pro | Qwen3.8 2.4T A95Bqwen3.8-2.4t-a95b |
|---|---|---|---|
| Pricing | |||
| Input | $0.10 / 1M | — Not priced per input token | $1.80 / 1M |
| Output | $0.50 / 1M | — Not priced per output token | $5.40 / 1M |
| Cache Write (5m) | $0.10 / 1M | Not applicable | $1.80 / 1M |
| Cache Write (1h) | $0.10 / 1M | Not applicable | $1.80 / 1M |
| Cache Read | $0.10 / 1M | Not applicable | $1.80 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 1M | N/A | 262K |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | Yes | No | Yes |
| Function Calling | Yes | No | Yes |
| JSON Mode | Yes | No | Yes |
| Streaming | Yes | No | Yes |
| Catalogue | |||
| Provider | DeepSeek | Fish Audio | Alibaba |
| Category | chat | voice | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | 2026-09-24 | — |
| 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. | Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <|speaker:0|>. Billed per second of audio. | Qwen3.8 2.4T A95B is Qwen's open-weight sparse Mixture-of-Experts (MoE) model and the open-weight counterpart to Qwen3.8 Max. It features 2.4T total parameters with 95B activated per token, combining frontier-scale capacity with efficient sparse inference. Designed for coding, research, complex reasoning, and agentic workflows, the model is well suited for demanding long-horizon tasks and advanced autonomous systems while providing the flexibility and customization benefits of open weights. |