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

side by side.

← all costsclear
01

Large language models

4 models
Mistral
Codestral 25.08
×
Alibaba
Qwen3-Max
×
Perplexity
Sonar
×
DeepSeek
DeepSeek V3
×
Output $/MTok$0.90$6.00$1.00$0.28
Input $/MTok$0.30$1.20$1.00$0.14
Cached input $/MTok$0.0028
Context window131,072262,144128,0001,048,576
Output cap8,19232,7688,000384,000
Modalitiesin: text / out: textin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyCodestralQwen 3 MaxSonarDeepSeek V3
Knowledge cutoff2025-06-30
Verified2026-07-022026-07-022026-07-022026-07-02
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
AssemblyAI
Universal-Streaming
×
OpenAI
Whisper
×
$/min$0.002500$0.006000
$/min batch
Streaming
Realtime
Languagesen99+
Diarizationextra-costunsupported
TTFW
Verified2026-07-022026-07-02
Sourceprovider page ↗provider page ↗