HAIL.SO / DISPATCH · 2026-07-12 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Mistral
Codestral 25.08
×
OpenAI
OpenAI o3
×
Alibaba
Qwen3-Max
×
Output $/MTok$0.90$8.00$6.00
Input $/MTok$0.30$2.00$1.20
Cached input $/MTok$0.5000
Context window131,072200,000262,144
Output cap8,192100,00032,768
Modalitiesin: text / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilyCodestralo-seriesQwen 3 Max
Knowledge cutoff2024-06-012025-06-30
Verified2026-07-022026-07-022026-07-02
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Cartesia
Ink Whisper
×
$/min$0.003000
$/min batch$0.001500
Streaming
Realtime
Languages99+
Diarizationunsupported
TTFW
Verified2026-07-02
Sourceprovider page ↗
03

Text to speech

2 models
Smallest.ai
Lightning v3.1
×
Cartesia
Sonic 2
×
$/1M chars$17.50$50.00
Voice qualityneuralneural
Voice cloning✓ included✓ included
Voice count217
Languagesen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, oren, fr, de, es, pt, zh, ja, ko
SSML support
TTFB200ms90ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-022026-07-02
Sourceprovider page ↗provider page ↗