HAIL.SO / DISPATCH · 2026-06-19 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
DeepSeek
DeepSeek R1
×
OpenAI
OpenAI o3
×
Perplexity
Sonar
×
Alibaba
Qwen3-Coder-Plus
×
Output $/MTok$0.28$8.00$1.00$5.00
Input $/MTok$0.14$2.00$1.00$1.00
Cached input $/MTok$0.0028$0.5000
Context window1,048,576200,000128,0001,048,576
Output cap384,000100,0008,00065,536
Modalitiesin: text / out: textin: text, image / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyDeepSeek R1o-seriesSonarQwen 3 Coder
Knowledge cutoff2024-06-01
Verified2026-05-18stale 32d2026-05-17stale 33d2026-05-19stale 31d2026-05-19stale 31d
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 31d2026-05-19stale 31d
Sourceprovider page ↗provider page ↗