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

side by side.

← all costsclear
01

Large language models

4 models
Alibaba
Qwen3-Max
×
Alibaba
Qwen3.6-Flash
×
Perplexity
Sonar
×
OpenAI
OpenAI o1
×
Output $/MTok$6.00$1.50$1.00$60.00
Input $/MTok$1.20$0.25$1.00$15.00
Cached input $/MTok$7.5000
Context window262,1441,048,576128,000200,000
Output cap32,76865,5368,000100,000
Modalitiesin: text / out: textin: text, image, video / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyQwen 3 MaxQwen 3.6 FlashSonaro-series
Knowledge cutoff2025-06-302023-10-01
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Cartesia
Ink Whisper
×
$/min$0.003000
$/min batch$0.001500
Streaming
Realtime
Languages99+
Diarizationunsupported
TTFW
Verified2026-07-19
Sourceprovider page ↗
03

Text to speech

1 model
Microsoft Azure
Azure AI Speech — Neural HD (DragonHD)
×
$/1M chars$22.00
Voice qualityneural
Voice cloning
Voice count30
Languagesen-US, zh-CN, de-DE, es-ES, fr-FR, ja-JP
SSML support
TTFB
Output formats
Verified2026-07-19
Sourceprovider page ↗