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

side by side.

← all costsclear
01

Large language models

3 models
Perplexity
Sonar
×
DeepSeek
DeepSeek V3
×
OpenAI
GPT-4o
×
Output $/MTok$1.00$0.28$10.00
Input $/MTok$1.00$0.14$2.50
Cached input $/MTok$0.0028$1.2500
Context window128,0001,048,576128,000
Output cap8,000384,00016,384
Modalitiesin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilySonarDeepSeek V3GPT-4o
Knowledge cutoff2023-10-01
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

3 models
OpenAI
Whisper
×
Speechmatics
Speechmatics Enhanced
×
OpenAI
GPT Realtime Whisper
×
$/min$0.006000$0.002150$0.017000
$/min batch
Streaming
Realtime
Languages99+56+99+
Diarizationunsupportedincludedunsupported
TTFW
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗