Whisper Large v3 Turbo API
About
Whisper Large v3 Turbo is a high-performance LLM available via the evroc API, ideal for scalable text generation and natural language processing. This model delivers cost-effective pricing at $0.0023/1M input and $0.0023/1M output tokens, open weights architecture. Access Whisper Large v3 Turbo via the evroc API with up to 448 output tokens.
Capabilities
Input Modalities
audio
Output Modalities
text
Reasoning
No
Structured Output
No
Tool Use
No
WeightsOpen
Temperature
Fixed
Attachment
Not Supported
Limits
Context Window
448
Tokens
Input Limit
448
Tokens
Max Output
448
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.0023
Output
$0.0023
Audio (per 1M tokens)
Output
$2.30
Frequently Asked Questions
Whisper Large v3 Turbo by evroc costs $0.0023 per 1M input tokens and $0.0023 per 1M output tokens.
Model Details
ID
openai/whisper-large-v3-turbo
Provider
evrocFamily
whisper
Release Date
Oct 1, 2024
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
EVROC_API_KEY
API Base URL
https://models.think.evroc.com/v1