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

side by side.

← all costsclear
01

Large language models

3 models
Perplexity
Sonar
×
Alibaba
Qwen3.7-Plus
×
DeepSeek
DeepSeek V4 Pro
×
Output $/MTok$1.00$1.60$0.87
Input $/MTok$1.00$0.40$0.43
Cached input $/MTok$0.0036
Context window128,0001,048,5761,048,576
Output cap8,00065,536384,000
Modalitiesin: text / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilySonarQwen 3.7 PlusDeepSeek V4
Knowledge cutoff
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

3 models
Rev.ai
Rev.ai Reverb
×
Deepgram
Nova-3 Multilingual
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.003300$0.005800$0.002150
$/min batch$0.009200
Streaming
Realtime
Languagesen61+56+
Diarizationincludedextra-costincluded
TTFW
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗