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

side by side.

← all costsclear
01

Large language models

3 models
Meta
Llama 4 Maverick
×
Alibaba
Qwen3.7-Plus
×
Perplexity
Sonar
×
Output $/MTok$0.85$1.60$1.00
Input $/MTok$0.27$0.40$1.00
Cached input $/MTok
Context window1,048,5761,048,576128,000
Output cap8,19265,5368,000
Modalitiesin: text, image / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilyLlama 4Qwen 3.7 PlusSonar
Knowledge cutoff2024-08-31
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Cartesia
Ink Whisper
×
AssemblyAI
Universal-Streaming
×
$/min$0.003000$0.002500
$/min batch$0.001500
Streaming
Realtime
Languages99+en
Diarizationunsupportedextra-cost
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
03

Text to speech

1 model
Rime
Rime Mist v3
×
$/1M chars$30.00
Voice qualityneural
Voice cloning
Voice count94
Languagesen
SSML support
TTFB37ms
Output formats
Verified2026-07-19
Sourceprovider page ↗