HAIL.SO / DISPATCH · 2026-06-10 · 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
×
OpenAI
OpenAI o3
×
Output $/MTok$0.90$5.00$8.00
Input $/MTok$0.30$1.00$2.00
Cached input $/MTok$0.5000
Context window262,1441,048,576200,000
Output cap8,19265,536100,000
Modalitiesin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyCodestralQwen 3 Codero-series
Knowledge cutoff2024-06-01
Verified2026-05-182026-05-192026-05-17
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Speechmatics
Speechmatics Enhanced
×
$/min$0.004000
$/min batch
Streaming
Realtime
Languages55+
Diarizationincluded
TTFW
Verified2026-05-19
Sourceprovider page ↗
03

Text to speech

2 models
Deepgram
Deepgram Aura 2
×
Smallest.ai
Lightning v3.1
×
$/1M chars$30.00$25.00
Voice qualityneuralneural
Voice cloning✓ included
Voice count217
Languagesen, es, de, fr, nl, it, jaen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or
SSML support
TTFB200ms
Output formatswav, mp3, linear16, mulaw, alaw, opuspcm, wav, mp3, mulaw
Verified2026-05-192026-05-19
Sourceprovider page ↗provider page ↗