HAIL.SO / DISPATCH · 2026-07-22 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Alibaba
Qwen3.6-Flash
×
Perplexity
Sonar
×
OpenAI
GPT-4.1
×
Anthropic
Claude Fable 5
×
Output $/MTok$1.50$1.00$8.00$50.00
Input $/MTok$0.25$1.00$2.00$10.00
Cached input $/MTok$0.5000$1.0000
Context window1,048,576128,0001,047,5761,000,000
Output cap65,5368,00032,768128,000
Modalitiesin: text, image, video / out: textin: text / out: textin: text, image / out: textin: text, image / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashSonarGPT-4.1Claude 5
Knowledge cutoff2024-06-012026-01-31
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
03

Text to speech

2 models
Smallest.ai
Lightning v3.1
×
LMNT
LMNT Blizzard
×
$/1M chars$17.50$50.00
Voice qualityneuralneural
Voice cloning✓ included✓ included
Voice count217
Languagesen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or31+
SSML support
TTFB200ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗