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

side by side.

← all costsclear
01

Large language models

4 models
Meta
Llama 4 Scout
×
DeepSeek
DeepSeek R1
×
Perplexity
Sonar
×
Alibaba
Qwen3.7-Max
×
Output $/MTok$0.59$0.28$1.00$7.50
Input $/MTok$0.18$0.14$1.00$2.50
Cached input $/MTok$0.0028
Context window10,485,7601,048,576128,0001,048,576
Output cap8,192384,0008,00065,536
Modalitiesin: text, image / out: textin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyLlama 4DeepSeek R1SonarQwen 3.7 Max
Knowledge cutoff2024-08-31
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Cartesia
Ink Whisper
×
Rev.ai
Rev.ai Reverb
×
$/min$0.003000$0.003300
$/min batch$0.001500
Streaming
Realtime
Languages99+en
Diarizationunsupportedincluded
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗