HAIL.SO / DISPATCH · 2026-07-02 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
DeepSeek
DeepSeek R1
×
Perplexity
Sonar
×
OpenAI
GPT-5 mini
×
Mistral
Codestral 25.08
×
Output $/MTok$0.28$1.00$2.00$0.90
Input $/MTok$0.14$1.00$0.25$0.30
Cached input $/MTok$0.0028$0.0250
Context window1,048,576128,000400,000131,072
Output cap384,0008,000128,0008,192
Modalitiesin: text / out: textin: text / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilyDeepSeek R1SonarGPT-5Codestral
Knowledge cutoff2024-05-31
Verified2026-07-022026-07-022026-07-022026-07-02
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
03

Text to speech

2 models
Cartesia
Sonic 2
×
LMNT
LMNT Blizzard
×
$/1M chars$50.00$50.00
Voice qualityneuralneural
Voice cloning✓ included✓ included
Voice count
Languagesen, fr, de, es, pt, zh, ja, ko31+
SSML support
TTFB90ms
Output formats
Verified2026-07-022026-07-02
Sourceprovider page ↗provider page ↗