HAIL.SO / DISPATCH · 2026-06-18 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Perplexity
Sonar
×
Mistral
Codestral 25.08
×
Alibaba
Qwen3-Coder-Plus
×
Output $/MTok$1.00$0.90$5.00
Input $/MTok$1.00$0.30$1.00
Cached input $/MTok
Context window128,000262,1441,048,576
Output cap8,0008,19265,536
Modalitiesin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilySonarCodestralQwen 3 Coder
Knowledge cutoff
Verified2026-05-19stale 30d2026-05-18stale 31d2026-05-19stale 30d
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Rev.ai
Rev.ai Reverb
×
$/min$0.003300
$/min batch
Streaming
Realtime
Languagesen
Diarizationincluded
TTFW
Verified2026-05-19stale 30d
Sourceprovider page ↗
03

Text to speech

2 models
Smallest.ai
Lightning v3.1
×
Deepgram
Deepgram Aura 2
×
$/1M chars$25.00$30.00
Voice qualityneuralneural
Voice cloning✓ included
Voice count217
Languagesen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, oren, es, de, fr, nl, it, ja
SSML support
TTFB200ms
Output formatspcm, wav, mp3, mulawwav, mp3, linear16, mulaw, alaw, opus
Verified2026-05-19stale 30d2026-05-19stale 30d
Sourceprovider page ↗provider page ↗