HAIL.SO / DISPATCH · 2026-07-25 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Perplexity
Sonar
×
Alibaba
Qwen3.7-Plus
×
Alibaba
Qwen3.7-Max
×
Output $/MTok$1.00$1.60$7.50
Input $/MTok$1.00$0.40$2.50
Cached input $/MTok
Context window128,0001,048,5761,048,576
Output cap8,00065,53665,536
Modalitiesin: text / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilySonarQwen 3.7 PlusQwen 3.7 Max
Knowledge cutoff
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
03

Text to speech

3 models
Deepgram
Deepgram Aura 2
×
Cartesia
Sonic 2
×
Cartesia
Sonic Turbo
×
$/1M chars$30.00$50.00$50.00
Voice qualityneuralneuralneural
Voice cloning✓ included✓ included
Voice count
Languagesen, es, de, fr, nl, it, jaen, fr, de, es, pt, zh, ja, koen, fr, de, es, pt, zh, ja, hi, ko
SSML support
TTFB90ms40ms
Output formatswav, mp3, linear16, mulaw, alaw, opus
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗