HAIL.SO / DISPATCH · 2026-07-23 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Meta
Llama 4 Maverick
×
Perplexity
Sonar
×
Alibaba
Qwen3-Max
×
Alibaba
Qwen3.7-Max
×
Output $/MTok$0.85$1.00$6.00$7.50
Input $/MTok$0.27$1.00$1.20$2.50
Cached input $/MTok
Context window1,048,576128,000262,1441,048,576
Output cap8,1928,00032,76865,536
Modalitiesin: text, image / out: textin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyLlama 4SonarQwen 3 MaxQwen 3.7 Max
Knowledge cutoff2024-08-312025-06-30
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Speechmatics
Speechmatics Enhanced
×
$/min$0.002150
$/min batch
Streaming
Realtime
Languages56+
Diarizationincluded
TTFW
Verified2026-07-19
Sourceprovider page ↗
03

Text to speech

1 model
OpenAI
TTS-1
×
$/1M chars$15.00
Voice qualityneural
Voice cloning
Voice count
Languagesen
SSML support
TTFB
Output formats
Verified2026-07-19
Sourceprovider page ↗