HAIL.SO / DISPATCH · 2026-07-22 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Alibaba
Qwen3.6-Flash
×
Perplexity
Sonar
×
OpenAI
GPT-5.4
×
Output $/MTok$1.50$1.00$15.00
Input $/MTok$0.25$1.00$2.50
Cached input $/MTok$0.2500
Context window1,048,576128,0001,050,000
Output cap65,5368,000128,000
Modalitiesin: text, image, video / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashSonarGPT-5.4
Knowledge cutoff2025-08-31
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

3 models
Cartesia
Ink Whisper
×
Speechmatics
Speechmatics Enhanced
×
Deepgram
Nova-3 Multilingual
×
$/min$0.003000$0.002150$0.005800
$/min batch$0.001500$0.009200
Streaming
Realtime
Languages99+56+61+
Diarizationunsupportedincludedextra-cost
TTFW
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗