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. Qwen Plus 2025-07-28 ThinkingAlibabaRemove
  2. Transcribe 1 ProFish AudioRemove
  3. GPT-6 LunaOpenAIRemove
qwen-plus-2025-07-28:thinking vs transcribe-1-pro vs gpt-6-luna
AttributeQwen Plus 2025-07-28 Thinkingqwen-plus-2025-07-28:thinkingTranscribe 1 Protranscribe-1-proGPT-6 Lunagpt-6-luna
Pricing
Input$0.40 / 1M— Not priced per input token$0.10 / 1M
Output$4.00 / 1M— Not priced per output token$0.50 / 1M
Cache Write (5m)$0.40 / 1MNot applicable$0.10 / 1M
Cache Write (1h)$0.40 / 1MNot applicable$0.10 / 1M
Cache Read$0.40 / 1MNot applicable$0.10 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max context1MN/A1.1M
Max outputN/AN/AN/A
Capabilities
VisionNoNoYes
Function CallingYesNoYes
JSON ModeYesNoYes
StreamingYesNoYes
Catalogue
ProviderAlibabaFish AudioOpenAI
Categorychatvoicechat
Charge typePay As You GoPay As You GoPay As You Go
Released—2026-09-24—
Description
SummaryQwen Plus 0728 is a hybrid reasoning model built on the Qwen3 foundation, featuring a 1M-token context window and a balanced trade-off between performance, speed, and cost.Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <|speaker:0|>. Billed per second of audio.GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, optimized for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks. It combines low-cost, responsive inference with the GPT-6 family’s improvements in factual reliability and clear, concise communication. At higher reasoning effort, GPT-6 Luna can also handle complex software engineering and computer-use workflows that previously required a Sol-tier model, making it a versatile choice for scalable production applications that need to balance speed, cost, and capability.