HAIL.SO / DISPATCH · 2026-06-06 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
DeepSeek
DeepSeek V3
×
Alibaba
Qwen3-Coder-Plus
×
Mistral
Codestral 25.08
×
Perplexity
Sonar
×
Output $/MTok$0.28$5.00$0.90$1.00
Input $/MTok$0.14$1.00$0.30$1.00
Cached input $/MTok$0.0028
Context window1,048,5761,048,576262,144128,000
Output cap384,00065,5368,1928,000
Modalitiesin: text / out: textin: text / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyDeepSeek V3Qwen 3 CoderCodestralSonar
Knowledge cutoff
Verified2026-05-182026-05-192026-05-182026-05-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
02

Speech to text

1 model
AssemblyAI
Universal-2
×
$/min$0.002500
$/min batch
Streaming
Realtime
Languages99+
Diarizationextra-cost
TTFW
Verified2026-05-05stale 32d
Sourceprovider page ↗
03

Text to speech

1 model
LMNT
LMNT Blizzard
×
$/1M chars$50.00
Voice qualityneural
Voice cloning✓ included
Voice count
Languages31+
SSML support
TTFB
Output formats
Verified2026-05-19
Sourceprovider page ↗