HAIL.SO / DISPATCH · 2026-07-27 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
DeepSeek
DeepSeek R1
×
DeepSeek
DeepSeek V3
×
Alibaba
Qwen3-Max
×
OpenAI
OpenAI o1
×
Output $/MTok$0.28$0.28$6.00$60.00
Input $/MTok$0.14$0.14$1.20$15.00
Cached input $/MTok$0.0028$0.0028$7.5000
Context window1,048,5761,048,576262,144200,000
Output cap384,000384,00032,768100,000
Modalitiesin: text / out: textin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyDeepSeek R1DeepSeek V3Qwen 3 Maxo-series
Knowledge cutoff2025-06-302023-10-01
Verified2026-07-272026-07-272026-07-272026-07-27
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
03

Text to speech

2 models
Deepgram
Deepgram Aura 2
×
Cartesia
Sonic 3
×
$/1M chars$30.00$50.00
Voice qualityneuralneural
Voice cloning✓ included
Voice count
Languagesen, es, de, fr, nl, it, ja44+
SSML support
TTFB
Output formatswav, mp3, linear16, mulaw, alaw, opus
Verified2026-07-192026-07-27
Sourceprovider page ↗provider page ↗