Model Capabilities & Pricing

Compare speed, intelligence, and cost to build your perfect workflow.

⚠️ Exact API Names Required

Copy the API Name exactly as shown into your settings.

1. Text Formatting & Intelligence Models

Provider Model Name & Status API Name (Copy This) Pricing (Input / Output) Speed (Est. TPM) Action
Groq
Llama 3.3 70B Versatile
Latest 		llama-3.3-70b-versatile $0.59 / $0.79 per 1M tokens ~16,800
Groq
Llama 3.1 8B Instant
Fast / Lite 		llama-3.1-8b-instant $0.05 / $0.08 per 1M tokens ~33,600
Groq
OpenAI GPT-OSS 20B
Speed King 		openai/gpt-oss-20b $0.075 / $0.30 per 1M tokens ~60,000
OpenAI
GPT-5 Mini
Latest 		gpt-5-mini-2025-08-07 $0.25 / $2.00 per 1M tokens ~5,640
OpenAI
GPT-4.1
Older 		gpt-4.1 $2.00 / $8.00 per 1M tokens ~4,800
OpenAI
o4 Mini
Reasoning 		o4-mini $1.10 / $4.40 per 1M tokens ~5,400
Google
Gemini 3.0 Flash
Latest 		gemini-3.0-flash $0.50 / $3.00 per 1M tokens ~13,080
Google
Gemini 2.5 Flash
Older 		gemini-2.5-flash $0.10 / $0.40 per 1M tokens ~16,800
Google
Gemini 2.5 Flash-Lite
Lite 		gemini-2.5-flash-lite $0.10 / $0.40 per 1M tokens ~53,220

2. Text-to-Speech (Transcription) Models

Provider Model Name & Status API Name (Copy This) Rate (Unit) Speed (Factor / Latency) Action
Groq
Whisper v3 Turbo
Fastest 		whisper-large-v3-turbo $0.040 / hour ~228x
Groq
Whisper Large v3
Latest 		whisper-large-v3 $0.111 / hour ~217x
OpenAI
GPT-4o Mini Transcribe
Latest 		gpt-4o-mini-transcribe $0.003 / min ~57x
OpenAI
GPT-4o Transcribe
Older 		gpt-4o-transcribe $0.006 / min ~38x
Google
Gemini 3.0 Flash
Latest 		gemini-3.0-flash $1.00 / 1M Audio Tokens Native (Low Latency)
Google
Gemini 2.5 Flash
Older 		gemini-2.5-flash $1.00 / 1M Audio Tokens Native (Low Latency)