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.

Transcribe 1 ProFish Audio Remove
MAI-Transcribe 2Microsoft Remove
DeepSeek V4.1 FlashDeepSeek Remove
Perceptron Mk1.5Perceptron Remove

4 is the maximum. Remove one to add another.

transcribe-1-pro vs mai-transcribe-2 vs deepseek-v4.1-flash vs perceptron-mk1.5
Attribute	Transcribe 1 Protranscribe-1-pro	MAI-Transcribe 2mai-transcribe-2	DeepSeek V4.1 Flashdeepseek-v4.1-flash	Perceptron Mk1.5perceptron-mk1.5
Pricing
Input	$0 / 1M	$0 / 1M	$0.30 / 1M	$0.15 / 1M
Output	$0 / 1M	$0 / 1M	$1.20 / 1M	$1.50 / 1M
Cache Write (5m)	Not applicable	Not applicable	$0.30 / 1M	$0.15 / 1M
Cache Write (1h)	Not applicable	Not applicable	$0.30 / 1M	$0.15 / 1M
Cache Read	Not applicable	Not applicable	$0.30 / 1M	$0.15 / 1M
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	N/A	N/A	1M	36.9K
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	No	No	Yes	No
Function Calling	No	No	Yes	No
JSON Mode	No	No	Yes	No
Streaming	No	No	Yes	Yes
Catalogue
Provider	Fish Audio	Microsoft	DeepSeek	Perceptron
Category	voice	voice	chat	chat
Charge type	Pay As You Go	Pay As You Go	Pay As You Go	Pay As You Go
Released	2026-09-24	2026-09-03	—	2026-09-25
Description
Summary	Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <\|speaker:0\|>. Billed per second of audio.	Microsoft MAI-Transcribe-2 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.	Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.