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
×
Mistral
Codestral 25.08
×
OpenAI
OpenAI o3
×
Perplexity
Sonar
×
Output $/MTok$1.50$0.90$8.00$1.00
Input $/MTok$0.25$0.30$2.00$1.00
Cached input $/MTok$0.5000
Context window1,048,576131,072200,000128,000
Output cap65,5368,192100,0008,000
Modalitiesin: text, image, video / out: textin: text / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashCodestralo-seriesSonar
Knowledge cutoff2024-06-01
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Gladia
Gladia Solaria-1
×
$/min$0.012500
$/min batch$0.010170
Streaming
Realtime
Languages100+
Diarizationincluded
TTFW
Verified2026-07-19
Sourceprovider page ↗
03

Text to speech

1 model
Google
Google Cloud TTS — WaveNet
×
$/1M chars$4.00
Voice qualityneural
Voice cloning
Voice count
Languages40+
SSML support
TTFB
Output formats
Verified2026-07-19
Sourceprovider page ↗