NEWS · COMPANIES · #3037
Cohere adds leading open models to Model Vault, including DeepSeek v4.1 Flash and Gemma 4
Cohere announced that its managed inference product Model Vault (and Model Vault Encrypted) now supports leading open models—such as DeepSeek V4.1 Flash, Gemma 4, GPT-OSS, Phi, GLM 5.3 Flash, MiMo V2.6 Pro and NVIDIA Nemotron—allowing enterprises to run Cohere’s models and third-party open models on a single-tenant, encrypted platform with zero prompt/output retention by default. Model Vault is live in the US, EU and Canada, while Model Vault Encrypted is live in the US with EU and Canada support coming soon, and the offering includes confidential-computing protections so neither Cohere nor cloud providers can see processed prompts/outputs in the encrypted option.
KEY POINTS
- Cohere announced that its managed inference product Model Vault (and Model Vault Encrypted) now supports leading open models—such as DeepSeek V4.1 Flash, Gemma 4, GPT-OSS, Phi, GLM 5.3 Flash, MiMo V2.6 Pro and NVIDIA Nemotron—allowing enterprises to run Cohere’s models and third-party open models on a single-tenant, encrypted platform with zero prompt/output retention by default.
- Model Vault is live in the US, EU and Canada, while Model Vault Encrypted is live in the US with EU and Canada support coming soon, and the offering includes confidential-computing protections so neither Cohere nor cloud providers can see processed prompts/outputs in the encrypted option.
- This gives enterprises a managed, regionally controlled way to run a choice of open and vendor models securely (including confidential-computing and zero-retention options), lowering barriers for sensitive workloads that cannot use shared APIs.
WHY IT MATTERS
This gives enterprises a managed, regionally controlled way to run a choice of open and vendor models securely (including confidential-computing and zero-retention options), lowering barriers for sensitive workloads that cannot use shared APIs.