HAIL.SO / DISPATCH · 2026-07-25 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Perplexity
Sonar
×
DeepSeek
DeepSeek V3
×
Alibaba
Qwen3.7-Plus
×
Meta
Llama 4 Maverick
×
Output $/MTok$1.00$0.28$1.60$0.85
Input $/MTok$1.00$0.14$0.40$0.27
Cached input $/MTok$0.0028
Context window128,0001,048,5761,048,5761,048,576
Output cap8,000384,00065,5368,192
Modalitiesin: text / out: textin: text / out: textin: text, image / out: textin: text, image / out: text
Tool use
Structured output
FamilySonarDeepSeek V3Qwen 3.7 PlusLlama 4
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
Rev.ai
Rev.ai Reverb
×
Cartesia
Ink Whisper
×
$/min$0.003300$0.003000
$/min batch$0.001500
Streaming
Realtime
Languagesen99+
Diarizationincludedunsupported
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗