HAIL.SO / DISPATCH · 2026-07-27 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

5 models
Perplexity
Sonar
×
OpenAI
GPT-4o mini
×
Alibaba
Qwen3-Max
×
DeepSeek
DeepSeek V3
×
OpenAI
OpenAI o3
×
Output $/MTok$1.00$0.60$6.00$0.28$8.00
Input $/MTok$1.00$0.15$1.20$0.14$2.00
Cached input $/MTok$0.0750$0.0028$0.5000
Context window128,000128,000262,1441,048,576200,000
Output cap8,00016,38432,768384,000100,000
Modalitiesin: text / out: textin: text, image / out: textin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilySonarGPT-4oQwen 3 MaxDeepSeek V3o-series
Knowledge cutoff2023-10-012025-06-302024-06-01
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
OpenAI
Whisper
×
$/min$0.006000
$/min batch
Streaming
Realtime
Languages99+
Diarizationunsupported
TTFW
Verified2026-07-19
Sourceprovider page ↗