HAIL.SO / DISPATCH · 2026-06-24 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
OpenAI
GPT-4o
×
Perplexity
Sonar
×
Alibaba
Qwen3-Coder-Plus
×
OpenAI
OpenAI o3
×
Output $/MTok$10.00$1.00$5.00$8.00
Input $/MTok$2.50$1.00$1.00$2.00
Cached input $/MTok$1.2500$0.5000
Context window128,000128,0001,048,576200,000
Output cap16,3848,00065,536100,000
Modalitiesin: text, image / out: textin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyGPT-4oSonarQwen 3 Codero-series
Knowledge cutoff2023-10-012024-06-01
Verified2026-05-17stale 38d2026-05-19stale 36d2026-05-19stale 36d2026-05-17stale 38d
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
03

Text to speech

2 models
Smallest.ai
Lightning v3.1
×
Deepgram
Deepgram Aura 2
×
$/1M chars$25.00$30.00
Voice qualityneuralneural
Voice cloning✓ included
Voice count217
Languagesen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, oren, es, de, fr, nl, it, ja
SSML support
TTFB200ms
Output formatspcm, wav, mp3, mulawwav, mp3, linear16, mulaw, alaw, opus
Verified2026-05-19stale 36d2026-05-19stale 36d
Sourceprovider page ↗provider page ↗