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 | Qwen3 ASR 1.7Bqwen3-asr-1.7b | DeepSeek V4.1 Flashdeepseek-v4.1-flash | Universal-3.5 Prouniversal-3-5-pro |
|---|---|---|---|
| Pricing | |||
| Input | $0 / 1M | $0.30 / 1M | $0 / 1M |
| Output | $0 / 1M | $1.20 / 1M | $0 / 1M |
| Cache Write (5m) | Not applicable | $0.30 / 1M | Not applicable |
| Cache Write (1h) | Not applicable | $0.30 / 1M | Not applicable |
| Cache Read | Not applicable | $0.30 / 1M | Not applicable |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | N/A | 1M | N/A |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | No | Yes | No |
| Function Calling | No | Yes | No |
| JSON Mode | No | Yes | No |
| Streaming | No | Yes | No |
| Catalogue | |||
| Provider | Qwen | DeepSeek | AssemblyAI |
| Category | voice | chat | voice |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | 2026-08-13 | — | 2026-09-22 |
| Description | |||
| Summary | Qwen3-ASR 1.7B speech-to-text. Billed per second of audio. | 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. | AssemblyAI Universal-3.5 Pro speech-to-text. Billed per second of audio. |