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
×
Perplexity
Sonar
×
DeepSeek
DeepSeek R1
×
Mistral
Codestral 25.08
×
Output $/MTok$1.50$1.00$0.28$0.90
Input $/MTok$0.25$1.00$0.14$0.30
Cached input $/MTok$0.0028
Context window1,048,576128,0001,048,576131,072
Output cap65,5368,000384,0008,192
Modalitiesin: text, image, video / out: textin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashSonarDeepSeek R1Codestral
Knowledge cutoff
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
03

Text to speech

2 models
Deepgram
Deepgram Aura 2
×
Smallest.ai
Lightning v3.1
×
$/1M chars$30.00$17.50
Voice qualityneuralneural
Voice cloning✓ included
Voice count217
Languagesen, es, de, fr, nl, it, jaen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or
SSML support
TTFB200ms
Output formatswav, mp3, linear16, mulaw, alaw, opuspcm, mp3, wav, ulaw, alaw
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗