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

side by side.

← all costsclear
01

Large language models

3 models
Alibaba
Qwen3.6-Flash
×
OpenAI
OpenAI o3
×
DeepSeek
DeepSeek R1
×
Output $/MTok$1.50$8.00$0.28
Input $/MTok$0.25$2.00$0.14
Cached input $/MTok$0.5000$0.0028
Context window1,048,576200,0001,048,576
Output cap65,536100,000384,000
Modalitiesin: text, image, video / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3.6 Flasho-seriesDeepSeek R1
Knowledge cutoff2024-06-01
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Google
Chirp 2
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.016000$0.002150
$/min batch
Streaming
Realtime
Languages20+56+
Diarizationincludedincluded
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
03

Text to speech

1 model
Smallest.ai
Lightning v3.1 Pro
×
$/1M chars$19.50
Voice qualityneural
Voice cloning
Voice count
Languagesen, hi, mr, ta, ml, te, kn, pa, bn, or, gu, ar, zh, id, ja, ko, ms, tr, vi, de, es, fr, it, pt, ru, el, fi, no, pl
SSML support
TTFB200ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-19
Sourceprovider page ↗