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

side by side.

← all costsclear
01

Large language models

3 models
Perplexity
Sonar
×
Alibaba
Qwen3.7-Max
×
OpenAI
OpenAI o4-mini
×
Output $/MTok$1.00$7.50$4.40
Input $/MTok$1.00$2.50$1.10
Cached input $/MTok$0.2750
Context window128,0001,048,576200,000
Output cap8,00065,536100,000
Modalitiesin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilySonarQwen 3.7 Maxo-series
Knowledge cutoff2024-06-01
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

3 models
Google
Chirp 2
×
Speechmatics
Speechmatics Enhanced
×
Deepgram
Nova-3 Multilingual
×
$/min$0.016000$0.002150$0.005800
$/min batch$0.009200
Streaming
Realtime
Languages20+56+61+
Diarizationincludedincludedextra-cost
TTFW
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗