HAIL.SO / DISPATCH · 2026-07-26 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

2 models
DeepSeek
DeepSeek R1
×
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 R1Sonar
Knowledge cutoff
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
02

Speech to text

1 model
Google
Chirp 3
×
$/min$0.016000
$/min batch
Streaming
Realtime
Languages98+
Diarizationincluded
TTFW
Verified2026-07-19
Sourceprovider page ↗
03

Text to speech

3 models
Cartesia
Sonic Turbo
×
Cartesia
Sonic 2
×
Deepgram
Deepgram Aura 2
×
$/1M chars$50.00$50.00$30.00
Voice qualityneuralneuralneural
Voice cloning✓ included✓ included
Voice count
Languagesen, fr, de, es, pt, zh, ja, hi, koen, fr, de, es, pt, zh, ja, koen, es, de, fr, nl, it, ja
SSML support
TTFB40ms90ms
Output formatswav, mp3, linear16, mulaw, alaw, opus
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗