HAIL.SO / DISPATCH · 2026-07-25 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Perplexity
Sonar
×
Meta
Llama 4 Scout
×
Alibaba
Qwen3-Max
×
Mistral
Ministral 3 14B
×
Output $/MTok$1.00$0.59$6.00$0.20
Input $/MTok$1.00$0.18$1.20$0.20
Cached input $/MTok
Context window128,00010,485,760262,144262,144
Output cap8,0008,19232,7688,192
Modalitiesin: text / out: textin: text, image / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilySonarLlama 4Qwen 3 MaxMinistral
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

2 models
Rev.ai
Rev.ai Reverb
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.003300$0.002150
$/min batch
Streaming
Realtime
Languagesen56+
Diarizationincludedincluded
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗