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.

Perceptron Mk1.5Perceptron Remove
Gemini 3.5 TranscribeGoogle Remove
MiniMax M2MiniMax Remove
GPT-6 Sol ProOpenAI Remove

4 is the maximum. Remove one to add another.

perceptron-mk1.5 vs gemini-3.5-transcribe vs minimax-m2 vs gpt-6-sol-pro
Attribute	Perceptron Mk1.5perceptron-mk1.5	Gemini 3.5 Transcribegemini-3.5-transcribe	MiniMax M2minimax-m2	GPT-6 Sol Progpt-6-sol-pro
Pricing
Input	$0.15 / 1M	— Not priced per input token	$0.15 / 1M	$2.00 / 1M
Output	$1.50 / 1M	— Not priced per output token	$0.45 / 1M	$10.00 / 1M
Cache Write (5m)	$0.15 / 1M	Not applicable	$0.15 / 1M	$2.00 / 1M
Cache Write (1h)	$0.15 / 1M	Not applicable	$0.15 / 1M	$2.00 / 1M
Cache Read	$0.15 / 1M	Not applicable	$0.15 / 1M	$2.00 / 1M
Web Search	$0 / 1M	$0 / 1M	$0 / 1M	$0 / 1M
Context
Max context	36.9K	98.3K	196.6K	1.1M
Max output	N/A	N/A	N/A	N/A
Capabilities
Vision	No	Yes	Yes	Yes
Function Calling	No	Yes	Yes	Yes
JSON Mode	No	No	Yes	Yes
Streaming	Yes	No	Yes	Yes
Catalogue
Provider	Perceptron	Google	MiniMax	OpenAI
Category	chat	voice	chat	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	—	—
Description
Summary	Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.	Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.	MiniMax-M2 is a compact, high-efficiency model with 10B active (230B total) parameters, optimized for coding and agentic workflows. It delivers near-frontier reasoning and tool use, excels at multi-file coding tasks and compile-run-fix loops, and performs strongly on benchmarks like SWE-Bench and Terminal-Bench. It also handles long-horizon planning and recovery in agent evaluations, ranking among the top open models across reasoning domains. With fast inference and low cost, it’s ideal for large-scale agents and developer assistants — and works best when reasoning is preserved across turns.	GPT-6 Sol Pro uses the same underlying model as GPT-6 Sol, but runs with reasoning.mode set to pro for higher-quality responses on complex and demanding tasks. Optimized for deeper reasoning, greater accuracy, and more reliable multi-step execution, it is particularly well suited for agentic coding, long-horizon software engineering, professional analysis, and complex automated workflows where solution quality takes priority over latency and cost.