HAIL.SO / DISPATCH · 2026-06-21 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Perplexity
Sonar
×
DeepSeek
DeepSeek V3
×
OpenAI
OpenAI o3
×
Alibaba
Qwen3-Coder-Plus
×
Output $/MTok$1.00$0.28$8.00$5.00
Input $/MTok$1.00$0.14$2.00$1.00
Cached input $/MTok$0.0028$0.5000
Context window128,0001,048,576200,0001,048,576
Output cap8,000384,000100,00065,536
Modalitiesin: text / out: textin: text / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilySonarDeepSeek V3o-seriesQwen 3 Coder
Knowledge cutoff2024-06-01
Verified2026-05-19stale 33d2026-05-18stale 34d2026-05-17stale 35d2026-05-19stale 33d
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 33d2026-05-19stale 33d
Sourceprovider page ↗provider page ↗