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

side by side.

← all costsclear
01

Large language models

3 models
Perplexity
Sonar
×
DeepSeek
DeepSeek V3
×
Alibaba
Qwen3.6-Flash
×
Output $/MTok$1.00$0.28$1.50
Input $/MTok$1.00$0.14$0.25
Cached input $/MTok$0.0028
Context window128,0001,048,5761,048,576
Output cap8,000384,00065,536
Modalitiesin: text / out: textin: text / out: textin: text, image, video / out: text
Tool use
Structured output
FamilySonarDeepSeek V3Qwen 3.6 Flash
Knowledge cutoff
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Rev.ai
Rev.ai Reverb
×
$/min$0.003300
$/min batch
Streaming
Realtime
Languagesen
Diarizationincluded
TTFW
Verified2026-07-19
Sourceprovider page ↗
03

Text to speech

2 models
Smallest.ai
Lightning v3.1 Pro
×
OpenAI
TTS-1
×
$/1M chars$19.50$15.00
Voice qualityneuralneural
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, plen
SSML support
TTFB200ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗