Compare AI model inference pricing across all major providers: input/output cost per 1M tokens, context window, capability tier, and best-value recommendations. Use this tool when: - An AI agent needs to select the most cost-effective model for a given task - A cost-optimisation agent is comparin...
AI agents call get_model_prices to retrieve information from Omni Service Node without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries pricing information from AI model providers. It has no side effects—it does not create, modify, delete data, execute code, or move money. The financial context (pricing data) is incidental; the tool itself does not commit financial obligations or process payments. Classification as Read is appropriate for a lookup/comparison utility.
From the tool's definition Tool description states it 'Compare[s] AI model inference pricing' and 'Returns per model: provider, model_name, input_cost_per_1m_tokens, output_cos[t]'.
Attacks that exploit this kind of access
Compare AI model inference pricing across all major providers: input/output cost per 1M tokens, context window, capability tier, and best-value recommendations. Use this tool when: - An AI agent needs to select the most cost-effective model for a given task - A cost-optimisation agent is comparing providers to reduce inference spend - You need to know the latest pricing after a provider update (prices change frequently) - An agent is building a routing layer and needs price/capability data to make routing decisions Returns per model: provider, model_name, input_cost_per_1m_tokens, output_cost_per_1m_tokens, context_window_tokens, capability_tier, multimodal, best_for. Example: getModelPrices({ providers:. It is categorised as a Read tool in the Omni Service Node MCP Server, which means it retrieves data without modifying state.
Register the Omni Service Node MCP server in PolicyLayer and add a rule for get_model_prices: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Omni Service Node. Nothing to install.
get_model_prices is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_model_prices rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_model_prices. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_model_prices is provided by the Omni Service Node MCP server (luckkyyy23/omni-service-node). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →