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
Qwen3.6-Flash
×
DeepSeek
DeepSeek V4 Pro
×
Alibaba
Qwen3-Max
×
Output $/MTok$1.50$0.87$6.00
Input $/MTok$0.25$0.43$1.20
Cached input $/MTok$0.0036
Context window1,048,5761,048,576262,144
Output cap65,536384,00032,768
Modalitiesin: text, image, video / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashDeepSeek V4Qwen 3 Max
Knowledge cutoff2025-06-30
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

3 models
Rev.ai
Rev.ai Reverb
×
Speechmatics
Speechmatics Enhanced
×
AssemblyAI
Universal-Streaming
×
$/min$0.003300$0.002150$0.002500
$/min batch
Streaming
Realtime
Languagesen56+en
Diarizationincludedincludedextra-cost
TTFW
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗