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

side by side.

← all costsclear
01

Large language models

4 models
Perplexity
Sonar
×
OpenAI
OpenAI o3
×
Mistral
Codestral 25.08
×
Alibaba
Qwen3.7-Plus
×
Output $/MTok$1.00$8.00$0.90$1.60
Input $/MTok$1.00$2.00$0.30$0.40
Cached input $/MTok$0.5000
Context window128,000200,000131,0721,048,576
Output cap8,000100,0008,19265,536
Modalitiesin: text / out: textin: text, image / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilySonaro-seriesCodestralQwen 3.7 Plus
Knowledge cutoff2024-06-01
Verified2026-07-192026-07-272026-07-272026-07-27
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Speechmatics
Speechmatics Enhanced
×
Deepgram
Nova-3 Multilingual
×
$/min$0.002150$0.005800
$/min batch$0.009200
Streaming
Realtime
Languages56+61+
Diarizationincludedextra-cost
TTFW
Verified2026-07-192026-07-27
Sourceprovider page ↗provider page ↗