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

side by side.

← all costsclear
01

Large language models

3 models
DeepSeek
DeepSeek V3
×
Alibaba
Qwen3-Coder-Plus
×
OpenAI
OpenAI o1
×
Output $/MTok$0.28$5.00$60.00
Input $/MTok$0.14$1.00$15.00
Cached input $/MTok$0.0028$7.5000
Context window1,048,5761,048,576200,000
Output cap384,00065,536100,000
Modalitiesin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyDeepSeek V3Qwen 3 Codero-series
Knowledge cutoff2023-10-01
Verified2026-05-182026-05-192026-05-17
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
AssemblyAI
Universal-Streaming
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.002500$0.004000
$/min batch
Streaming
Realtime
Languagesen55+
Diarizationextra-costincluded
TTFW
Verified2026-05-05stale 32d2026-05-19
Sourceprovider page ↗provider page ↗
03

Text to speech

1 model
Cartesia
Sonic 2
×
$/1M chars$50.00
Voice qualityneural
Voice cloning✓ included
Voice count
Languages15+
SSML support
TTFB90ms
Output formats
Verified2026-05-19
Sourceprovider page ↗