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
×
Alibaba
Qwen3-Coder-Plus
×
Perplexity
Sonar
×
Output $/MTok$0.90$5.00$1.00
Input $/MTok$0.30$1.00$1.00
Cached input $/MTok
Context window262,1441,048,576128,000
Output cap8,19265,5368,000
Modalitiesin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyCodestralQwen 3 CoderSonar
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
×
Deepgram
Deepgram Aura 2
×
Rime
Rime Mist v3
×
$/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, oren, es, de, fr, nl, it, jaen
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 ↗