HAIL.SO / DISPATCH · 2026-06-14 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Mistral
Codestral 25.08
×
Perplexity
Sonar
×
Alibaba
Qwen3-Coder-Plus
×
Output $/MTok$0.90$1.00$5.00
Input $/MTok$0.30$1.00$1.00
Cached input $/MTok
Context window262,144128,0001,048,576
Output cap8,1928,00065,536
Modalitiesin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyCodestralSonarQwen 3 Coder
Knowledge cutoff
Verified2026-05-182026-05-192026-05-19
Sourceprovider page ↗provider page ↗provider page ↗
03

Text to speech

3 models
Smallest.ai
Lightning v3.1
×
Rime
Rime Mist v3
×
Deepgram
Deepgram Aura 2
×
$/1M chars$25.00$30.00$30.00
Voice qualityneuralneuralneural
Voice cloning✓ included
Voice count21794
Languagesen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, orenen, es, de, fr, nl, it, ja
SSML support
TTFB200ms100ms
Output formatspcm, wav, mp3, mulawwav, mp3, linear16, mulaw, alaw, opus
Verified2026-05-192026-05-192026-05-19
Sourceprovider page ↗provider page ↗provider page ↗