DeepSeek-V4-Flash-0731 is now available on Ollama's cloud

DeepSeek-V4-Flash-0731 [ollama.com/library/deepseek-v4-flash:0731-cloud] is now available to run via Ollama’s cloud. This
update to DeepSeek-V4-Flash substantially enhances the model's agentic capabilities.

* Fast, efficient performance: low-latency, high-throughput access via Ollama’s cloud with up to 10x more usage vs closed
frontier models.

* Reliable tool calling and reasoning: support for three reasoning effort levels: low, high, and max with reliable function
calling even at long contexts.

* Private by default: this model is hosted in the US and Europe with zero data retention on Ollama's cloud. Your data is never
trained on.

To use with Claude Code:

ollama launch claude --model deepseek-v4-flash:0731-cloud

To use with assistants like Hermes or OpenClaw:

ollama launch hermes --model deepseek-v4-flash:0731-cloud
ollama launch openclaw --model deepseek-v4-flash:0731-cloud

Using Ollama as a team and interested in a Team plan? Let us know
[ollama.typeform.com/to/FFV2AVPu#email=…tmail.com]

❤️ Ollama

You are receiving this email because you opted in to receive updates from Ollama
Ollama, 744 High Street, Palo Alto, CA 94301
Unsubscribe [app.loops.so/unsubscribe/cmsd1lz6r0ush…22d6467e9]