Open Source
DeepSeek-V4.1-Flash-1017
Multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters.Input Tokens$0.10 / 1M
Output Tokens$0.35 / 1M
Cache Tokens$0.003 / 1M
LLM
Open Source Frontier Models
Open Source Frontier Models
The latest open source frontier LLMs, now live on Deploy
Democratizing Open Source Intelligence
Democratizing Open Source Intelligence
Explore the latest open source frontier models available on Deploy.
Open Source
Z.AI GLM-5.3-Flash
The first natively multimodal model in the GLM-5 series from Z.ai.Input Tokens$0.05 / 1M
Output Tokens$0.17 / 1M
Cache Tokens$0.01 / 1M
LLM
High performance. Low cost.
High performance. Low cost.
The latest frontier intelligence shouldn’t break the bank.
Deploy’s optimized inference infrastructure delivers production-ready performance — low cost, low latency, no operational overhead.
Scale seamlessly
Scale seamlessly
From one request to billions,your inference layer shouldn’t be the bottleneck. Deploy is built to absorb spikes and scale with you, keeping latency low and costs aligned with production traffic.
Usage-based pricing
Usage-based pricing
Whether you’re experimenting on your own or scaling at the enterprise level, we’ve got a plan that fits.
Developers
Developers
Perfect for small teams and early-stage projects
Pay-as-you-go usage billing
Access to open source model library
Enterprise
Enterprise
Premium capabilities and support for enterprises
Custom Pricing to fit your organization’s usage
Highest Rate Limits to handle large-scale traffic