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 3.5 TranscribeGoogleRemove
- Perceptron Mk1.5PerceptronRemove
- Qwen3 ASR 0.6BQwenRemove
- DeepSeek V4.1 FlashDeepSeekRemove
4 is the maximum. Remove one to add another.
| Attribute | Gemini 3.5 Transcribegemini-3.5-transcribe | Perceptron Mk1.5perceptron-mk1.5 | Qwen3 ASR 0.6Bqwen3-asr-0.6b | DeepSeek V4.1 Flashdeepseek-v4.1-flash |
|---|---|---|---|---|
| Pricing | ||||
| Input | $0 / 1M | $0.15 / 1M | $0 / 1M | $0.30 / 1M |
| Output | $0 / 1M | $1.50 / 1M | $0 / 1M | $1.20 / 1M |
| Cache Write (5m) | Not applicable | $0.15 / 1M | Not applicable | $0.30 / 1M |
| Cache Write (1h) | Not applicable | $0.15 / 1M | Not applicable | $0.30 / 1M |
| Cache Read | Not applicable | $0.15 / 1M | Not applicable | $0.30 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | 98.3K | 36.9K | N/A | 1M |
| Max output | N/A | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | Yes | No | No | Yes |
| Function Calling | Yes | No | No | Yes |
| JSON Mode | No | No | No | Yes |
| Streaming | No | Yes | No | Yes |
| Catalogue | ||||
| Provider | Perceptron | Qwen | DeepSeek | |
| Category | voice | chat | voice | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | 2026-09-25 | 2026-09-25 | 2026-08-13 | — |
| Description | ||||
| Summary | Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token. | Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token. | Qwen3-ASR 0.6B 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. |