HAIL.SO / DISPATCH · 2026-07-12 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Perplexity
Sonar
×
Mistral
Codestral 25.08
×
DeepSeek
DeepSeek V3
×
xAI
Grok 4.3
×
Output $/MTok$1.00$0.90$0.28$2.50
Input $/MTok$1.00$0.30$0.14$1.25
Cached input $/MTok$0.0028
Context window128,000131,0721,048,5761,000,000
Output cap8,0008,192384,0001,000,000
Modalitiesin: text / out: textin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilySonarCodestralDeepSeek V3Grok 4
Knowledge cutoff
Verified2026-07-022026-07-022026-07-022026-07-02
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Deepgram
Nova-3 Multilingual
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.005800$0.002150
$/min batch$0.009200
Streaming
Realtime
Languages61+56+
Diarizationextra-costincluded
TTFW
Verified2026-07-022026-07-02
Sourceprovider page ↗provider page ↗