HAIL.SO / DISPATCH · 2026-07-24 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Perplexity
Sonar
×
Alibaba
Qwen3.6-Flash
×
Mistral
Codestral 25.08
×
xAI
Grok 3
×
Output $/MTok$1.00$1.50$0.90$15.00
Input $/MTok$1.00$0.25$0.30$3.00
Cached input $/MTok$0.7500
Context window128,0001,048,576131,072131,072
Output cap8,00065,5368,192131,072
Modalitiesin: text / out: textin: text, image, video / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilySonarQwen 3.6 FlashCodestralGrok 3
Knowledge cutoff2024-11-30
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Deepgram
Nova-3 Medical
×
$/min$0.004800
$/min batch$0.004300
Streaming
Realtime
Languagesen, en-US, en-AU, en-CA, en-GB, en-IE, en-IN, en-NZ
Diarizationextra-cost
TTFW
Verified2026-07-19
Sourceprovider page ↗
03

Text to speech

1 model
LMNT
LMNT Blizzard
×
$/1M chars$50.00
Voice qualityneural
Voice cloning✓ included
Voice count
Languages31+
SSML support
TTFB
Output formats
Verified2026-07-19
Sourceprovider page ↗