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. Qwen3 ASR 0.6BQwenRemove
  2. S1Fish AudioRemove
  3. GPT-6 Luna ProOpenAIRemove
  4. Claude Sonnet 5.5AnthropicRemove

4 is the maximum. Remove one to add another.

qwen3-asr-0.6b vs s1 vs gpt-6-luna-pro vs claude-sonnet-5.5
AttributeQwen3 ASR 0.6Bqwen3-asr-0.6bS1s1GPT-6 Luna Progpt-6-luna-proClaude Sonnet 5.5claude-sonnet-5.5
Pricing
Input$0 / 1M$0 / 1M$0.10 / 1M$2.00 / 1M
Output$0 / 1M$0 / 1M$0.50 / 1M$10.00 / 1M
Cache Write (5m)Not applicableNot applicable$0.10 / 1M$2.50 / 1M
Cache Write (1h)Not applicableNot applicable$0.10 / 1M$4.00 / 1M
Cache ReadNot applicableNot applicable$0.10 / 1M$0.20 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/A1.1M1M
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoYesYes
Function CallingNoNoYesYes
JSON ModeNoNoYesYes
StreamingNoNoYesYes
Catalogue
ProviderQwenFish AudioOpenAIAnthropic
Categoryvoicevoicechatchat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-08-132026-07-29——
Description
SummaryQwen3-ASR 0.6B speech-to-text. Billed per second of audio.Fish Audio S1 text-to-speech. Billed per UTF-8 byte of input text.GPT-6 Luna Pro uses the same underlying model as GPT-6 Luna, but runs with reasoning.mode set to pro for higher-quality responses on complex tasks. It combines Luna's speed and cost efficiency with deeper reasoning and more reliable multi-step execution, making it well suited for advanced coding, computer use, and agentic workflows where higher solution quality is needed without moving to a larger GPT-6 tier.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.