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

side by side.

← all costsclear
01

Large language models

4 models
Alibaba
Qwen3.6-Flash
×
OpenAI
GPT-4o
×
Perplexity
Sonar
×
Perplexity
Sonar Pro
×
Output $/MTok$1.50$10.00$1.00$15.00
Input $/MTok$0.25$2.50$1.00$3.00
Cached input $/MTok$1.2500
Context window1,048,576128,000128,000200,000
Output cap65,53616,3848,0008,000
Modalitiesin: text, image, video / out: textin: text, image / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashGPT-4oSonarSonar
Knowledge cutoff2023-10-01
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
AssemblyAI
Universal-3.5 Pro Realtime
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.007500$0.002150
$/min batch
Streaming
Realtime
Languagesen, es, fr, de, it, pt, ar, da, nl, fi, he, hi, ja, zh, no, sv, tr, vi56+
Diarizationextra-costincluded
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗