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

side by side.

← all costsclear
01

Large language models

3 models
Perplexity
Sonar
×
Alibaba
Qwen3.6-Flash
×
OpenAI
GPT-5
×
Output $/MTok$1.00$1.50$10.00
Input $/MTok$1.00$0.25$1.25
Cached input $/MTok$0.1250
Context window128,0001,048,576400,000
Output cap8,00065,536128,000
Modalitiesin: text / out: textin: text, image, video / out: textin: text, image / out: text
Tool use
Structured output
FamilySonarQwen 3.6 FlashGPT-5
Knowledge cutoff2024-09-30
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Cartesia
Ink Whisper
×
Deepgram
Flux (English)
×
$/min$0.003000$0.006500
$/min batch$0.001500
Streaming
Realtime
Languages99+en
Diarizationunsupported
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
03

Text to speech

1 model
Rime
Rime Mist v3
×
$/1M chars$30.00
Voice qualityneural
Voice cloning
Voice count94
Languagesen
SSML support
TTFB37ms
Output formats
Verified2026-07-19
Sourceprovider page ↗