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.

Qwen3 ASR 0.6BQwen Remove
Aura-2Deepgram Remove
Grok 4.7SpaceXAI Remove
Voxtral Mini 3B 2507Mistral AI Remove

4 is the maximum. Remove one to add another.

qwen3-asr-0.6b vs aura-2 vs grok-4.7 vs voxtral-mini-3b-2507
Attribute	Qwen3 ASR 0.6Bqwen3-asr-0.6b	Aura-2aura-2	Grok 4.7grok-4.7	Voxtral Mini 3B 2507voxtral-mini-3b-2507
Pricing
Input	$0 / 1M	$0 / 1M	$1.60 / 1M	$0 / 1M
Output	$0 / 1M	$0 / 1M	$4.80 / 1M	$0 / 1M
Cache Write (5m)	Not applicable	Not applicable	$1.60 / 1M	Not applicable
Cache Write (1h)	Not applicable	Not applicable	$1.60 / 1M	Not applicable
Cache Read	Not applicable	Not applicable	$1.60 / 1M	Not applicable
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	N/A	N/A	500K	N/A
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	No
Catalogue
Provider	Qwen	Deepgram	SpaceXAI	Mistral AI
Category	voice	voice	chat	voice
Charge type	Pay As You Go	Pay As You Go	Pay As You Go	Pay As You Go
Released	2026-08-13	2026-07-16	—	2026-08-13
Description
Summary	Qwen3-ASR 0.6B speech-to-text. Billed per second of audio.	Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.	Grok 4.7 is SpaceXAI's flagship model for coding, agentic workflows, and professional knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering, self-verification, and long-context execution, while improving capabilities in document drafting, presentations, and other professional tasks. Trained with extended reinforcement learning focused on multi-hour problems, Grok 4.7 is optimized for sustained, complex task execution and natively supports the Grok Bot harness for conversational workflows. It also introduces an enhanced safeguard stack designed to combine strong jailbreak resistance with low refusal rates for legitimate technical work. Reported benchmark results use xhigh reasoning effort.	Mistral AI Voxtral Mini (3B) speech-to-text. Billed per second of audio.