HAIL.SO / DISPATCH · 2026-07-27 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Perplexity
Sonar
×
Alibaba
Qwen3.7-Plus
×
Mistral
Codestral 25.08
×
Output $/MTok$1.00$1.60$0.90
Input $/MTok$1.00$0.40$0.30
Cached input $/MTok
Context window128,0001,048,576131,072
Output cap8,00065,5368,192
Modalitiesin: text / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilySonarQwen 3.7 PlusCodestral
Knowledge cutoff
Verified2026-07-192026-07-272026-07-27
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
OpenAI
Whisper
×
$/min$0.006000
$/min batch
Streaming
Realtime
Languages99+
Diarizationunsupported
TTFW
Verified2026-07-19
Sourceprovider page ↗
03

Text to speech

2 models
Smallest.ai
Lightning v3.1 Pro
×
LMNT
LMNT Blizzard
×
$/1M chars$19.50$50.00
Voice qualityneuralneural
Voice cloning✓ included
Voice count
Languagesen, hi, mr, ta, ml, te, kn, pa, bn, or, gu, ar, zh, id, ja, ko, ms, tr, vi, de, es, fr, it, pt, ru, el, fi, no, pl31+
SSML support
TTFB200ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗