HAIL.SO / DISPATCH · 2026-07-27 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Alibaba
Qwen3.6-Flash
×
OpenAI
GPT-5
×
Perplexity
Sonar
×
OpenAI
OpenAI o3
×
Output $/MTok$1.50$10.00$1.00$8.00
Input $/MTok$0.25$1.25$1.00$2.00
Cached input $/MTok$0.1250$0.5000
Context window1,048,576400,000128,000200,000
Output cap65,536128,0008,000100,000
Modalitiesin: text, image, video / out: textin: text, image / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashGPT-5Sonaro-series
Knowledge cutoff2024-09-302024-06-01
Verified2026-07-272026-07-272026-07-192026-07-27
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Microsoft Azure
Azure Speech (Batch)
×
Gladia
Gladia Solaria-1
×
$/min$0.003000$0.012500
$/min batch$0.010170
Streaming
Realtime
Languages100+100+
Diarizationincludedincluded
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗