HAIL.SO / DISPATCH · 2026-07-12 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

2 models
DeepSeek
DeepSeek V3
×
Perplexity
Sonar
×
Output $/MTok$0.28$1.00
Input $/MTok$0.14$1.00
Cached input $/MTok$0.0028
Context window1,048,576128,000
Output cap384,0008,000
Modalitiesin: text / out: textin: text / out: text
Tool use
Structured output
FamilyDeepSeek V3Sonar
Knowledge cutoff
Verified2026-07-022026-07-02
Sourceprovider page ↗provider page ↗
02

Speech to text

1 model
AssemblyAI
Universal-Streaming
×
$/min$0.002500
$/min batch
Streaming
Realtime
Languagesen
Diarizationextra-cost
TTFW
Verified2026-07-02
Sourceprovider page ↗
03

Text to speech

3 models
Cartesia
Sonic Turbo
×
Deepgram
Deepgram Aura 2
×
Cartesia
Sonic 2
×
$/1M chars$50.00$30.00$50.00
Voice qualityneuralneuralneural
Voice cloning✓ included✓ included
Voice count
Languagesen, fr, de, es, pt, zh, ja, hi, koen, es, de, fr, nl, it, jaen, fr, de, es, pt, zh, ja, ko
SSML support
TTFB40ms90ms
Output formatswav, mp3, linear16, mulaw, alaw, opus
Verified2026-07-022026-07-022026-07-02
Sourceprovider page ↗provider page ↗provider page ↗