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

side by side.

← all costsclear
01

Large language models

3 models
Perplexity
Sonar
×
Alibaba
Qwen3.7-Plus
×
Mistral
Ministral 3 14B
×
Output $/MTok$1.00$1.60$0.20
Input $/MTok$1.00$0.40$0.20
Cached input $/MTok
Context window128,0001,048,576262,144
Output cap8,00065,5368,192
Modalitiesin: text / out: textin: text, image / out: textin: text, image / out: text
Tool use
Structured output
FamilySonarQwen 3.7 PlusMinistral
Knowledge cutoff
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

3 models
Google
Chirp 3
×
AssemblyAI
Universal-2
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.016000$0.002500$0.002150
$/min batch
Streaming
Realtime
Languages98+99+56+
Diarizationincludedextra-costincluded
TTFW
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗