HAIL.SO / DISPATCH · 2026-07-22 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Mistral
Ministral 3 3B
×
OpenAI
OpenAI o3
×
Perplexity
Sonar
×
Alibaba
Qwen3-Max
×
Output $/MTok$0.10$8.00$1.00$6.00
Input $/MTok$0.10$2.00$1.00$1.20
Cached input $/MTok$0.5000
Context window262,144200,000128,000262,144
Output cap8,192100,0008,00032,768
Modalitiesin: text, image / out: textin: text, image / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyMinistralo-seriesSonarQwen 3 Max
Knowledge cutoff2024-06-012025-06-30
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Deepgram
Nova-3 Medical
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.004800$0.002150
$/min batch$0.004300
Streaming
Realtime
Languagesen, en-US, en-AU, en-CA, en-GB, en-IE, en-IN, en-NZ56+
Diarizationextra-costincluded
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗