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

side by side.

← all costsclear
01

Large language models

3 models
Alibaba
Qwen3-Max
×
Perplexity
Sonar
×
DeepSeek
DeepSeek V4 Pro
×
Output $/MTok$6.00$1.00$0.87
Input $/MTok$1.20$1.00$0.43
Cached input $/MTok$0.0036
Context window262,144128,0001,048,576
Output cap32,7688,000384,000
Modalitiesin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3 MaxSonarDeepSeek V4
Knowledge cutoff2025-06-30
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

3 models
Speechmatics
Speechmatics Enhanced
×
Cartesia
Ink Whisper
×
Google
Chirp 2
×
$/min$0.002150$0.003000$0.016000
$/min batch$0.001500
Streaming
Realtime
Languages56+99+20+
Diarizationincludedunsupportedincluded
TTFW
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗