HAIL.SO / DISPATCH · 2026-06-06 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Alibaba
Qwen3-Coder-Plus
×
OpenAI
OpenAI o4-mini
×
Perplexity
Sonar
×
Output $/MTok$5.00$4.40$1.00
Input $/MTok$1.00$1.10$1.00
Cached input $/MTok$0.2750
Context window1,048,576200,000128,000
Output cap65,536100,0008,000
Modalitiesin: text / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3 Codero-seriesSonar
Knowledge cutoff2024-06-01
Verified2026-05-192026-05-172026-05-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
AssemblyAI
Universal-Streaming
×
Rev.ai
Rev.ai Reverb
×
$/min$0.002500$0.003300
$/min batch
Streaming
Realtime
Languagesenen
Diarizationextra-costincluded
TTFW
Verified2026-05-05stale 32d2026-05-19
Sourceprovider page ↗provider page ↗
03

Text to speech

1 model
Cartesia
Sonic 3.5
×
$/1M chars$50.00
Voice qualityneural
Voice cloning✓ included
Voice count
Languages42+
SSML support
TTFB90ms
Output formatsraw/pcm_f32le, raw/pcm_s16le, raw/pcm_mulaw, raw/pcm_alaw, wav, mp3
Verified2026-05-05stale 32d
Sourceprovider page ↗