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

side by side.

← all costsclear
01

Large language models

4 models
Meta
Llama 4 Scout
×
xAI
Grok 4.5
×
Alibaba
Qwen3-Max
×
Perplexity
Sonar
×
Output $/MTok$0.59$6.00$6.00$1.00
Input $/MTok$0.18$2.00$1.20$1.00
Cached input $/MTok$0.3000
Context window10,485,760500,000262,144128,000
Output cap8,192500,00032,7688,000
Modalitiesin: text, image / out: textin: text, image / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyLlama 4Grok 4Qwen 3 MaxSonar
Knowledge cutoff2024-08-312026-02-012025-06-30
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider 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

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 ↗