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
Qwen3.7-Plus
×
Perplexity
Sonar
×
OpenAI
GPT-5
×
Output $/MTok$1.60$1.00$10.00
Input $/MTok$0.40$1.00$1.25
Cached input $/MTok$0.1250
Context window1,048,576128,000400,000
Output cap65,5368,000128,000
Modalitiesin: text, image / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyQwen 3.7 PlusSonarGPT-5
Knowledge cutoff2024-09-30
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

3 models
Microsoft Azure
Azure Speech (Real-time)
×
Speechmatics
Speechmatics Enhanced
×
AssemblyAI
Universal-Streaming
×
$/min$0.016667$0.002150$0.002500
$/min batch
Streaming
Realtime
Languages100+56+en
Diarizationextra-costincludedextra-cost
TTFW
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗