OpenScale
Serverless
Low-cost per-token API for fast open-weight models (DeepSeek V4.1 Flash, GLM 5.3 Flash) behind an OpenAI-compatible endpoint with 1M-token context, vision, tool calling and structured outputs. No minimums; chat requests are not stored. YC-backed.
Features
OpenAI Compatible
Streaming
Batching
Fine-tuning
Embeddings
Vision
Audio
Function Calling
JSON Mode
Compliance
SOC 2
HIPAA
GDPR
Pricing Model
per token Free tier: Free credits on signup
Details
Models 3
API Base
https://api.openscale.so/v1 LLM Inference
Model Catalog (3)
| Model | Type | Input $/1M | Output $/1M | Context | Speed | Status |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash DeepSeek | llm | $0.060 | $0.240 | 1.0M | — | |
| DeepSeek V4.1 Flash DeepSeek Fast | llm | $0.280 | $1.10 | 1.0M | — | |
| GLM 5.3 Flash Z.ai | llm | $0.120 | $0.400 | 1.0M | — |
OpenScale API FAQ
Is the OpenScale API free?
Yes, OpenScale has a free tier: Free credits on signup. Paid usage is billed per model.
What is the cheapest OpenScale model?
DeepSeek V4.1 Flash at $0.06 in / $0.24 out per 1M tokens, based on the 3 models we track for OpenScale.
How many models does OpenScale offer?
We track 3 OpenScale models: 3 LLM.
Is the OpenScale API OpenAI-compatible?
Yes. OpenScale exposes an OpenAI-compatible endpoint, so you can use the OpenAI SDKs by changing the base URL and API key.