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

side by side.

← all costsclear
01

Large language models

3 models
Alibaba
Qwen3-Coder-Plus
×
Perplexity
Sonar
×
Mistral
Codestral 25.08
×
Output $/MTok$5.00$1.00$0.90
Input $/MTok$1.00$1.00$0.30
Cached input $/MTok
Context window1,048,576128,000262,144
Output cap65,5368,0008,192
Modalitiesin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3 CoderSonarCodestral
Knowledge cutoff
Verified2026-05-192026-05-192026-05-18
Sourceprovider page ↗provider page ↗provider page ↗
03

Text to speech

3 models
Rime
Rime Mist v3
×
Smallest.ai
Lightning v3.1
×
Deepgram
Deepgram Aura 2
×
$/1M chars$30.00$25.00$30.00
Voice qualityneuralneuralneural
Voice cloning✓ included
Voice count94217
Languagesenen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, oren, es, de, fr, nl, it, ja
SSML support
TTFB100ms200ms
Output formatspcm, wav, mp3, mulawwav, mp3, linear16, mulaw, alaw, opus
Verified2026-05-192026-05-192026-05-19
Sourceprovider page ↗provider page ↗provider page ↗