HAIL.SO / DISPATCH · 2026-07-24 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

2 models
Anthropic
Claude Fable 5
×
Alibaba
Qwen3-Max
×
Output $/MTok$50.00$6.00
Input $/MTok$10.00$1.20
Cached input $/MTok$1.0000
Context window1,000,000262,144
Output cap128,00032,768
Modalitiesin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilyClaude 5Qwen 3 Max
Knowledge cutoff2026-01-312025-06-30
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
03

Text to speech

4 models
Deepgram
Deepgram Aura 2
×
Rime
Rime Mist v3
×
LMNT
LMNT Blizzard
×
Cartesia
Sonic 2
×
$/1M chars$30.00$30.00$50.00$50.00
Voice qualityneuralneuralneuralneural
Voice cloning✓ included✓ included
Voice count94
Languagesen, es, de, fr, nl, it, jaen31+en, fr, de, es, pt, zh, ja, ko
SSML support
TTFB37ms90ms
Output formatswav, mp3, linear16, mulaw, alaw, opus
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗