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

side by side.

← all costsclear
01

Large language models

4 models
Alibaba
Qwen3.7-Plus
×
Perplexity
Sonar
×
DeepSeek
DeepSeek V3
×
xAI
Grok 4.5
×
Output $/MTok$1.60$1.00$0.28$6.00
Input $/MTok$0.40$1.00$0.14$2.00
Cached input $/MTok$0.0028$0.3000
Context window1,048,576128,0001,048,576500,000
Output cap65,5368,000384,000500,000
Modalitiesin: text, image / out: textin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyQwen 3.7 PlusSonarDeepSeek V3Grok 4
Knowledge cutoff2026-02-01
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Gladia
Gladia Solaria-3
×
$/min$0.010170
$/min batch
Streaming
Realtime
Languagesen, fr, de, es, it
Diarizationincluded
TTFW
Verified2026-07-19
Sourceprovider page ↗
03

Text to speech

1 model
Deepgram
Deepgram Aura 2
×
$/1M chars$30.00
Voice qualityneural
Voice cloning
Voice count
Languagesen, es, de, fr, nl, it, ja
SSML support
TTFB
Output formatswav, mp3, linear16, mulaw, alaw, opus
Verified2026-07-19
Sourceprovider page ↗