HAIL.SO / DISPATCH · 2026-07-22 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Perplexity
Sonar
×
OpenAI
OpenAI o1
×
Alibaba
Qwen3.7-Max
×
Mistral
Codestral 25.08
×
Output $/MTok$1.00$60.00$7.50$0.90
Input $/MTok$1.00$15.00$2.50$0.30
Cached input $/MTok$7.5000
Context window128,000200,0001,048,576131,072
Output cap8,000100,00065,5368,192
Modalitiesin: text / out: textin: text, image / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilySonaro-seriesQwen 3.7 MaxCodestral
Knowledge cutoff2023-10-01
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Cartesia
Ink 2
×
$/min$0.009000
$/min batch
Streaming
Realtime
Languagesen
Diarization
TTFW
Verified2026-07-19
Sourceprovider page ↗
03

Text to speech

1 model
Smallest.ai
Lightning v3.1 Pro
×
$/1M chars$19.50
Voice qualityneural
Voice cloning
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, pl
SSML support
TTFB200ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-19
Sourceprovider page ↗