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.

Grok 4.7SpaceXAI Remove
Voxtral Small 24B 2507 STTMistral AI Remove
Aura-2Deepgram Remove
Perceptron Mk1.5Perceptron Remove

4 is the maximum. Remove one to add another.

grok-4.7 vs voxtral-small-24b-2507-stt vs aura-2 vs perceptron-mk1.5
Attribute	Grok 4.7grok-4.7	Voxtral Small 24B 2507 STTvoxtral-small-24b-2507-stt	Aura-2aura-2	Perceptron Mk1.5perceptron-mk1.5
Pricing
Input	$1.60 / 1M	$0 / 1M	$0 / 1M	$0.15 / 1M
Output	$4.80 / 1M	$0 / 1M	$0 / 1M	$1.50 / 1M
Cache Write (5m)	$1.60 / 1M	Not applicable	Not applicable	$0.15 / 1M
Cache Write (1h)	$1.60 / 1M	Not applicable	Not applicable	$0.15 / 1M
Cache Read	$1.60 / 1M	Not applicable	Not applicable	$0.15 / 1M
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	500K	N/A	N/A	36.9K
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	Yes	No	No	No
Function Calling	Yes	No	No	No
JSON Mode	Yes	No	No	No
Streaming	Yes	No	No	Yes
Catalogue
Provider	SpaceXAI	Mistral AI	Deepgram	Perceptron
Category	chat	voice	voice	chat
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	2026-09-25
Description
Summary	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 Small (24B) speech-to-text. Billed per second of audio.	Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.	Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.