Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Inference Indexer

    1

    Optimize AI spend by ranking 690+ models and 70+ providers by quality-adjusted cost and compliance.

    Free

    2 usesSecurity scanned
    Inference Indexer

    Inference Indexer

    Example session with this skill installed

    Which reasoning model should I use? I need at least 32k context and my budget is $5.00 per million tokens. I need zero data retention.

    • Read your context and instructions
    • Compiled the inference indexer

    I have queried the InferenceIndexer API for reasoning models meeting your 32k context and ZDR requirements within a $5.00/M budget.

    Recommended Reasoning Models (ZDR Provider-Reported)

    Model IDProviderBlended Price ($/M)Cost/IQContextWhy
    xiaomi/mimo-v2.6-flashDeepInfra$0.2240.2371.05MRank 1 by Cost/IQ of models under $5.0/M blended, 32k+ context, on a zero-data-retention provider; cheapest verified endpoint at DeepInfra.
    inclusionai/ling-3.0-flash-vlNovita$0.1470.239131kRank 2 under the same constraint set; cheapest verified endpoint at Novita.
    deepseek/deepseek-v4-flashDeepInfra$0.2240.2611.05MRank 3 under the same constraint set; cheapest verified endpoint at DeepInfra.

    Endpoint Configuration for Top Pick:

    • Provider: DeepInfra
    • Base URL: https://api.deepinfra.com/v1/openai
    • Model ID: XiaomiMiMo/MiMo-V2.6-Flash
    • ZDR Status: Provider-stated True

    Next steps

    1. Update your client base_url to the DeepInfra endpoint provided above.
    2. Run a 1,000 token test to verify latency meets your requirements.
    3. Call explain_model for xiaomi/mimo-v2.6-flash to see the 7-day price trend.

    All results are live API output: the index refreshes hourly, so these prices beat anything an LLM remembers.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    High inference costs and opaque model pricing stall production deployments. Finding the right balance between intelligence and spend usually involves manual spreadsheet work across dozens of provider pages.

    This skill connects to the InferenceIndexer API to automate model selection and price auditing. It queries a verified index of over 70 providers and 690 models to find the most cost-effective endpoint for any specific task. Instead of guessing which model is best, it uses deterministic ranking based on Cost/IQ (quality-adjusted cost) and returns ready-to-use endpoint configurations.

    What it does

    • Rank models by efficiency using the Cost/IQ metric to find the highest intelligence for the lowest price.
    • Audit agent spend with a built-in script that calculates monthly and annual savings by switching providers.
    • Filter by compliance including Zero-Data-Retention (ZDR) and EU-sovereign hosting requirements.
    • Generate endpoint configs providing the exact base_url and model_id needed to swap providers immediately.
    • Track price trends to identify model degradation, pricing changes, or new high-value launches.

    How it works

    1. Call recommend_models with task constraints like budget, context window, or modality.
    2. Review the why string and Cost/IQ ranking to select a verified provider.
    3. Run the what_am_i_costing.py script to benchmark current usage against the market.
    4. Use the endpoint_config object to update your LLM client pointing to the cheaper host.

    Frameworks & tools

    This skill requires the inferenceindexer MCP server. It interacts with the InferenceIndexer API and includes a Python 3 utility script for cost auditing.

    Why this beats prompting it yourself

    LLMs have stale knowledge of pricing and often hallucinate provider capabilities or ZDR status. This skill uses a live, deterministic API index where every result carries verifiable evidence and fresh pricing data (updated every 6 hours).

    Use cases

    • Selecting the cheapest reliable reasoning model for a complex sub-agent.
    • Generating a cost-savings report for a production app spending over $1,000/month on inference.
    • Finding EU-sovereign endpoints for a GDPR-compliant data extraction task.
    • Comparing intelligence scores (AA Index) across new model releases to justify an upgrade.

    Known limitations

    Pricing data is refreshed every 6 hours and intelligence scores every 7 days. ZDR and EU-sovereign status are provider-reported and not independently verified by the index.

    Data fresh to 6h for prices and 7d for AA scores. ZDR/EU flags are provider-reported, not independently verified. Requires Python 3 for the cost audit script.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Inferenceindexer

    Permissions

    Terminal / Shell
    Network Access

    Allowed Hosts

    api.inferenceindexer.ai
    www.inferenceindexer.ai
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill automates model selection by ranking 690+ models across 70+ providers based on 'Cost/IQ'—a quality-adjusted metric that ensures you get the highest intelligence for the lowest price without manual spreadsheet work.

    The skill requires the inferenceindexer MCP server and an active API key to fetch live data. It also includes a Python 3 utility script for auditing your existing spend against current market rates.

    Yes, the skill allows you to filter results by specific requirements like Zero-Data-Retention (ZDR) and EU-sovereign hosting, ensuring your chosen provider meets strict GDPR or enterprise privacy standards.

    Pricing data is refreshed every 6 hours and intelligence scores (AA Index) are updated every 7 days, ensuring your agent always has access to current market conditions and the latest model releases.

    Unlike static prompts, this skill uses a live, deterministic API index to prevent hallucinations regarding provider capabilities and pricing, providing verifiable 'base_url' and 'model_id' configs for immediate deployment.

    You get full access to the 'recommend_models' tool, the 'what_am_i_costing.py' auditing script, and the configuration to connect your agent to the InferenceIndexer API.

    New in LLM Ops