Skip to content
Apertis

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.

  1. Gemini 3.5 TranscribeGoogleRemove
  2. Claude Sonnet 5.5AnthropicRemove
  3. Transcribe 1 ProFish AudioRemove
  4. MiniMax M2MiniMaxRemove

4 is the maximum. Remove one to add another.

gemini-3.5-transcribe vs claude-sonnet-5.5 vs transcribe-1-pro vs minimax-m2
AttributeGemini 3.5 Transcribegemini-3.5-transcribeClaude Sonnet 5.5claude-sonnet-5.5Transcribe 1 Protranscribe-1-proMiniMax M2minimax-m2
Pricing
Input— Not priced per input token$2.00 / 1M— Not priced per input token$0.15 / 1M
Output— Not priced per output token$10.00 / 1M— Not priced per output token$0.45 / 1M
Cache Write (5m)Not applicable$2.50 / 1MNot applicable$0.15 / 1M
Cache Write (1h)Not applicable$4.00 / 1MNot applicable$0.15 / 1M
Cache ReadNot applicable$0.20 / 1MNot applicable$0.15 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max context98.3K1MN/A196.6K
Max outputN/AN/AN/AN/A
Capabilities
VisionYesYesNoYes
Function CallingYesYesNoYes
JSON ModeNoYesNoYes
StreamingNoYesNoYes
Catalogue
ProviderGoogleAnthropicFish AudioMiniMax
Categoryvoicechatvoicechat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-09-25—2026-09-24—
Description
SummaryGoogle Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, serving as a direct upgrade to Sonnet 5. It excels at feature development, bug fixing, and creating polished documents, presentations, and spreadsheets, while offering clearer writing and communication than its predecessor.Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <|speaker:0|>. Billed per second of audio.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.