HAIL.SO / DISPATCH · 2026-07-23 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Perplexity
Sonar
×
DeepSeek
DeepSeek R1
×
Anthropic
Claude Fable 5
×
DeepSeek
DeepSeek V3
×
Output $/MTok$1.00$0.28$50.00$0.28
Input $/MTok$1.00$0.14$10.00$0.14
Cached input $/MTok$0.0028$1.0000$0.0028
Context window128,0001,048,5761,000,0001,048,576
Output cap8,000384,000128,000384,000
Modalitiesin: text / out: textin: text / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilySonarDeepSeek R1Claude 5DeepSeek V3
Knowledge cutoff2026-01-31
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Speechmatics
Speechmatics Melia 1
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.002150$0.002150
$/min batch
Streaming
Realtime
Languages68+56+
Diarizationincludedincluded
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗