HAIL.SO / DISPATCH · 2026-07-23 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Alibaba
Qwen3.6-Flash
×
Mistral
Codestral 25.08
×
DeepSeek
DeepSeek R1
×
Output $/MTok$1.50$0.90$0.28
Input $/MTok$0.25$0.30$0.14
Cached input $/MTok$0.0028
Context window1,048,576131,0721,048,576
Output cap65,5368,192384,000
Modalitiesin: text, image, video / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashCodestralDeepSeek R1
Knowledge cutoff
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
03

Text to speech

3 models
Cartesia
Sonic Turbo
×
Smallest.ai
Lightning v3.1
×
Rime
Rime Mist v3
×
$/1M chars$50.00$17.50$30.00
Voice qualityneuralneuralneural
Voice cloning✓ included✓ included
Voice count21794
Languagesen, fr, de, es, pt, zh, ja, hi, koen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, oren
SSML support
TTFB40ms200ms37ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗