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

side by side.

← all costsclear
01

Large language models

5 models
OpenAI
GPT-4.1
×
Perplexity
Sonar
×
Alibaba
Qwen3.7-Max
×
OpenAI
GPT-4o
×
Mistral
Codestral 25.08
×
Output $/MTok$8.00$1.00$7.50$10.00$0.90
Input $/MTok$2.00$1.00$2.50$2.50$0.30
Cached input $/MTok$0.5000$1.2500
Context window1,047,576128,0001,048,576128,000131,072
Output cap32,7688,00065,53616,3848,192
Modalitiesin: text, image / out: textin: text / out: textin: text / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilyGPT-4.1SonarQwen 3.7 MaxGPT-4oCodestral
Knowledge cutoff2024-06-012023-10-01
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
Speechmatics
Speechmatics Melia 1
×
$/min$0.002150
$/min batch
Streaming
Realtime
Languages68+
Diarizationincluded
TTFW
Verified2026-07-19
Sourceprovider page ↗