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

side by side.

← all costsclear
01

Large language models

5 models
Alibaba
Qwen3.7-Plus
×
Perplexity
Sonar
×
DeepSeek
DeepSeek V3
×
Meta
Llama 4 Maverick
×
Alibaba
Qwen3.6-Flash
×
Output $/MTok$1.60$1.00$0.28$0.85$1.50
Input $/MTok$0.40$1.00$0.14$0.27$0.25
Cached input $/MTok$0.0028
Context window1,048,576128,0001,048,5761,048,5761,048,576
Output cap65,5368,000384,0008,19265,536
Modalitiesin: text, image / out: textin: text / out: textin: text / out: textin: text, image / out: textin: text, image, video / out: text
Tool use
Structured output
FamilyQwen 3.7 PlusSonarDeepSeek V3Llama 4Qwen 3.6 Flash
Knowledge cutoff2024-08-31
Verified2026-07-192026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
Rev.ai
Rev.ai Reverb
×
$/min$0.003300
$/min batch
Streaming
Realtime
Languagesen
Diarizationincluded
TTFW
Verified2026-07-19
Sourceprovider page ↗