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
×
Mistral
Mistral Small 4
×
Output $/MTok$1.50$1.00$0.60
Input $/MTok$0.25$1.00$0.15
Cached input $/MTok
Context window1,048,576128,000262,144
Output cap65,5368,0008,192
Modalitiesin: text, image, video / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashSonarMistral Small
Knowledge cutoff
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Gladia
Gladia Solaria-1
×
AssemblyAI
Universal-2
×
$/min$0.012500$0.002500
$/min batch$0.010170
Streaming
Realtime
Languages100+99+
Diarizationincludedextra-cost
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
03

Text to speech

1 model
Rime
Rime Mist v3
×
$/1M chars$30.00
Voice qualityneural
Voice cloning
Voice count94
Languagesen
SSML support
TTFB37ms
Output formats
Verified2026-07-19
Sourceprovider page ↗