Models
Open models over one API, at the lowest price we can offer. Every model works with OpenAI and Anthropic SDKs and with the coding agents you already use.
Price per 1M tokens
| Model | Input | Cached input | Output | Context |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.06 | $0.003 | $0.24 | 1M |
| GLM 5.3 Flash | $0.12 | $0.024 | $0.40 | 1M |
DeepSeek V4.1 Flash
Fast 1M-context reasoning model with aggressive cache pricing, built for high-volume agent traffic. Always the latest version, now 1017.
Model id deepseek/deepseek-v4.1-flash. $0.06 input, $0.003 cached input and $0.24 output per 1M tokens. 1M context, up to 384K output tokens per request, 200+ tokens per second.
GLM 5.3 Flash
Z.ai's fast multimodal model for coding and long-horizon agent work, with a 1M context. Always the latest version, now 0828.
Model id z-ai/glm-5.3-flash. $0.12 input, $0.024 cached input and $0.40 output per 1M tokens. 1M context, up to 131K output tokens per request, 100+ tokens per second.
Questions
How is model usage priced?
Per token, in USD per 1M tokens, with separate prices for input, cached input and output tokens. You pay only for what you use, from prepaid credit.
What is the cheapest model on OpenScale?
DeepSeek V4.1 Flash, at $0.06 per 1M input tokens, $0.003 per 1M cached input tokens and $0.24 per 1M output tokens.
Are the models OpenAI and Anthropic compatible?
Yes. Every model works with OpenAI SDKs at https://api.openscale.so/v1 (Chat Completions and Responses) and with Anthropic SDKs at https://api.openscale.so/anthropic.
Where is the live list of model ids?
GET https://api.openscale.so/v1/models lists every model id with its limits and capabilities. No API key needed.
Plain Markdown version of this page: /models.md. Full API reference: /docs.