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 1.7BQwenRemove
  2. Nova-3DeepgramRemove
  3. Gemini 3.5 TranscribeGoogleRemove
  4. GPT-6 AstraOpenAIRemove

4 is the maximum. Remove one to add another.

qwen3-asr-1.7b vs nova-3 vs gemini-3.5-transcribe vs gpt-6-astra
AttributeQwen3 ASR 1.7Bqwen3-asr-1.7bNova-3nova-3Gemini 3.5 Transcribegemini-3.5-transcribeGPT-6 Astragpt-6-astra
Pricing
Input$0 / 1M$0 / 1M$0 / 1M$10.00 / 1M
Output$0 / 1M$0 / 1M$0 / 1M$50.00 / 1M
Cache Write (5m)Not applicableNot applicableNot applicable$10.00 / 1M
Cache Write (1h)Not applicableNot applicableNot applicable$10.00 / 1M
Cache ReadNot applicableNot applicableNot applicable$10.00 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/A98.3K1M
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoYesYes
Function CallingNoNoYesYes
JSON ModeNoNoNoYes
StreamingNoNoNoYes
Catalogue
ProviderQwenDeepgramGoogleOpenAI
Categoryvoicevoicevoicechat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-08-132026-07-152026-09-25—
Description
SummaryQwen3-ASR 1.7B speech-to-text. Billed per second of audio.Deepgram Nova-3 speech-to-text. Billed per second of audio.Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.GPT-6 Astra is OpenAI's flagship model for demanding end-to-end professional work, designed for advanced analysis, software engineering, deep research, scientific tasks, and document creation. It is particularly strong in long-horizon agentic workflows, including tasks that require sustained reasoning, tool orchestration, and computer and browser use, making it well suited for complex autonomous workflows and production-grade knowledge work.