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

side by side.

← all costsclear
01

Large language models

3 models
Alibaba
Qwen3-Coder-Plus
×
Mistral
Codestral 25.08
×
OpenAI
OpenAI o3
×
Output $/MTok$5.00$0.90$8.00
Input $/MTok$1.00$0.30$2.00
Cached input $/MTok$0.5000
Context window1,048,576262,144200,000
Output cap65,5368,192100,000
Modalitiesin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyQwen 3 CoderCodestralo-series
Knowledge cutoff2024-06-01
Verified2026-05-192026-05-182026-05-17
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
LMNT
LMNT Blizzard
×
Cartesia
Sonic 3.5
×
$/1M chars$50.00$50.00
Voice qualityneuralneural
Voice cloning✓ included✓ included
Voice count
Languages31+42+
SSML support
TTFB90ms
Output formatsraw/pcm_f32le, raw/pcm_s16le, raw/pcm_mulaw, raw/pcm_alaw, wav, mp3
Verified2026-05-192026-05-05stale 32d
Sourceprovider page ↗provider page ↗