Call DeepSeek models from the terminal, and check the balance funding them
Connect DeepSeek with an API key and your agent can reach its models without leaving the terminal. Send a prompt through DEEPSEEK_CREATE_CHAT_COMPLETION or the Anthropic-compatible DEEPSEEK_CREATE_ANTHROPIC_MESSAGE, see what is available with DEEPSEEK_LIST_MODELS, and read remaining credit with DEEPSEEK_GET_USER_BALANCE. All four are read-only and answer right away.
4 tools, all read-only. They answer instantly, and every call is logged.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
No. Every one of the 4 tools LuumenAI has for DeepSeek is read-only, so it can answer questions from DeepSeek but cannot change anything in it. Read actions still follow the configured access and approval policy, and are recorded on the audit trail.
You decide. Access is granted per agent, skill, and team, and per environment — production is not staging.
Every call to DeepSeek is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Connect in minutes. Every action scoped, approved, and audited from day one.