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

side by side.

← all costsclear
01

Large language models

3 models
OpenAI
GPT-5
×
Perplexity
Sonar
×
Alibaba
Qwen3.7-Plus
×
Output $/MTok$10.00$1.00$1.60
Input $/MTok$1.25$1.00$0.40
Cached input $/MTok$0.1250
Context window400,000128,0001,048,576
Output cap128,0008,00065,536
Modalitiesin: text, image / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyGPT-5SonarQwen 3.7 Plus
Knowledge cutoff2024-09-30
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Speechmatics
Speechmatics Enhanced
×
Deepgram
Nova-3 Medical
×
$/min$0.002150$0.004800
$/min batch$0.004300
Streaming
Realtime
Languages56+en, en-US, en-AU, en-CA, en-GB, en-IE, en-IN, en-NZ
Diarizationincludedextra-cost
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
03

Text to speech

1 model
Smallest.ai
Lightning v3.1
×
$/1M chars$17.50
Voice qualityneural
Voice cloning✓ included
Voice count217
Languagesen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or
SSML support
TTFB200ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-19
Sourceprovider page ↗