HAIL.SO / DISPATCH · 2026-07-12 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

2 models
Perplexity
Sonar
×
Alibaba
Qwen3-Max
×
Output $/MTok$1.00$6.00
Input $/MTok$1.00$1.20
Cached input $/MTok
Context window128,000262,144
Output cap8,00032,768
Modalitiesin: text / out: textin: text / out: text
Tool use
Structured output
FamilySonarQwen 3 Max
Knowledge cutoff2025-06-30
Verified2026-07-022026-07-02
Sourceprovider page ↗provider page ↗
02

Speech to text

1 model
Soniox
Soniox STT Async v4
×
$/min$0.001670
$/min batch
Streaming
Realtime
Languages60+
Diarizationincluded
TTFW
Verified2026-07-02
Sourceprovider page ↗
03

Text to speech

3 models
Cartesia
Sonic 2
×
Rime
Rime Mist v3
×
Smallest.ai
Lightning v3.1
×
$/1M chars$50.00$30.00$17.50
Voice qualityneuralneuralneural
Voice cloning✓ included✓ included
Voice count94217
Languagesen, fr, de, es, pt, zh, ja, koenen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or
SSML support
TTFB90ms37ms200ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-022026-07-022026-07-02
Sourceprovider page ↗provider page ↗provider page ↗