HAIL.SO / DISPATCH · 2026-07-26 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Alibaba
Qwen3-Max
×
Perplexity
Sonar
×
DeepSeek
DeepSeek R1
×
Output $/MTok$6.00$1.00$0.28
Input $/MTok$1.20$1.00$0.14
Cached input $/MTok$0.0028
Context window262,144128,0001,048,576
Output cap32,7688,000384,000
Modalitiesin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3 MaxSonarDeepSeek R1
Knowledge cutoff2025-06-30
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 Turbo
×
Cartesia
Sonic 2
×
$/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, hi, koen, fr, de, es, pt, zh, ja, ko
SSML support
TTFB40ms90ms
Output formatswav, mp3, linear16, mulaw, alaw, opus
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗