InferenceIndexer MCP Server
Query live and historical AI inference pricing, provider data, and SIT index values through MCP tools.
Search/list models by text, tier, sort, and limit with current input/output/blended pricing.
Get full details for one model, including pricing, tier, SIT score, and cost/IQ.
Retrieve historical price trends for a model over a configurable day window.
List all providers and inspect a provider’s models, tier breakdown, and price range.
Compare one model’s pricing across providers that host it.
Fetch the latest SIT-Composite index value and historical trend.
Note: the README mentions
recommend_modelsandexplain_model, but they are not present in the provided server schema.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@InferenceIndexer MCP Server Compare GPT-4o pricing across providers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
InferenceIndexer MCP Server
Model Context Protocol server exposing InferenceIndexer's live + historical inference pricing as agent callable tools. Instead of an agent assembling inference pricing itself (slow, incomplete), it can call these tools to get complete pricing, historical trends, provider comparison, and the SIT index.
Tools
Tool | Description |
| Call this first: rank models under your constraints (budget, context, ZDR, quality floor) with ready-to-call endpoint configs |
| Everything about one model in one call: pricing, trend, endpoints, privacy flags |
| Search/list models with current pricing (by text, tier, sort) |
| Full detail + current price for one model |
| Historical price trends for one model (the differentiator) |
| All providers with model counts + price stats |
| Detail for one provider (models, tiers, price range) |
| Current SIT-Composite index value + tier breakdown |
| SIT-Composite index history / trend |
| Price of one model across all providers that host it |
Related MCP server: apipriceindex-mcp
Config (env)
II_API_BASE- InferenceIndexer API base (defaulthttps://api.inferenceindexer.ai)II_API_KEY- Optional bearer key (public server works without one; a key raises rate limits)II_SSR_SECRET- Optional first-party secret for self-hosted/higher-tier use only. Not set on the public server.
Run
stdio (recommended for local/agent-run):
uv sync
uv run inferenceindexer-mcpServe over HTTP/SSE (for remote clients, e.g. the hosted endpoint at https://api.inferenceindexer.ai/mcp):
uv run inferenceindexer-mcp --transport streamable-http --port 8899Connect an agent / MCP client
Claude Desktop / generic MCP client (stdio):
{
"mcpServers": {
"inferenceindexer": {
"command": "uvx",
"args": ["inferenceindexer-mcp", "--transport", "stdio"]
}
}
}Updated Oct 2026. Hosted (no install): https://api.inferenceindexer.ai/mcp - add "url": "https://api.inferenceindexer.ai/mcp" to mcpServers for streamable-http clients.
Available Tools
8 toolscompare_providersAInspect
Compare the price of one model across the providers that host it.
Args: model_id: Canonical model id, e.g. 'meta/muse-spark-1.1'. Returns: per-provider endpoints with pricing, showing where direct provider prices diverge (e.g. from OpenRouter's negotiated rate).
Inputs: model_id (required). Returns: object
get_composite_historyAInspect
Get SIT-Composite index history / trend over time.
Args: days: History window in days (1-90, default 30). Returns: historical composite index values.
Inputs: days. Returns: object
get_composite_latestAInspect
Get the current SIT-Composite index value + per-tier breakdown.
The SIT-Composite is a usage-weighted mean of the top-50 models by token volume, reflecting what developers actually pay for inference.
Inputs: no named parameters. Returns: object
get_modelAInspect
Get full detail + current pricing for one model by its id.
Args: model_id: Canonical model id, e.g. 'openai/gpt-5.6' or 'anthropic/claude-sonnet-5'. Returns: pricing, tier, SIT score, quality-adjusted price (Cost/IQ).
Inputs: model_id (required). Returns: object
get_model_historyAInspect
Get HISTORICAL price data / trends for one model.
This is InferenceIndexer's differentiator: aggregators like OpenRouter expose only current price; this returns the price over time (input, output, blended $/M), enabling trend analysis.
Args: model_id: Canonical model id, e.g. 'openai/gpt-5.6'. days: History window in days (1-365, default 30; plan-dependent). Returns: historical price series for the model.
Inputs: model_id (required), days. Returns: object
get_providerAInspect
Get detail for one provider: models, tier breakdown, price range.
Args: provider_name: Provider name, e.g. 'DeepInfra', 'Novita', 'Venice'. Returns: provider detail with model list and pricing.
Inputs: provider_name (required). Returns: object
list_providersAInspect
List all inference providers with model counts and price stats.
Inputs: no named parameters. Returns: object
search_modelsAInspect
Search and list AI inference models with current pricing.
Args: query: Text search on model id/name (optional). tier: Filter by tier: frontier | standard | budget | micro | zdr | eu (optional). limit: Max results (1-100, default 25). sort: Sort key, e.g. 'blended' (price), 'sit' (SIT score) (optional). Returns: models with input/output/blended $/M pricing, provider, tier.
Inputs: sort, tier, limit, query. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool addresses a distinct resource/action combination: model search, provider list, model detail, model history, provider detail, composite index (current/history), and cross-provider comparison. The overlap between search_models and get_model is minimal as one is for discovery and the other for a specific model.
All tool names follow a consistent verb_noun snake_case pattern (search, list, get, get, get, get, get, compare) with no mixed styles or vague verbs. The pattern is predictable and immediately conveys the operation and target.
8 tools is well within the ideal range for a focused read-only inference pricing service. Each tool covers a necessary aspect of exploring models, providers, and composite indices without redundancy or bloat.
The domain of tracking inference model pricing and providers is fully covered with search, detail, history, provider listing/detail, cross-provider comparison, and composite index (current and historical). No obvious gaps exist for the stated purpose of an inference indexer.
Related MCP Connectors
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Related MCP Servers
- AlicenseAqualityBmaintenanceGlobal price benchmarking for AI inference across 2,600+ SKUs from 47 vendors. Query live pricing, market indexes, and model specs via 8 tools. Free tier available.8MIT

apipriceindex-mcpofficial
AlicenseAqualityBmaintenanceGives AI agents live, verified LLM API prices from apipriceindex.com, enabling cost estimation, model search, and price lookups with verification metadata.8109 PyPIMIT- AlicenseAqualityCmaintenanceEnables AI agents to retrieve live GPU rental prices, compare models, and access market summaries and historical price data through four read-only MCP tools.4MIT
- AlicenseAqualityBmaintenanceEnables MCP clients to query live OpenRouter LLM pricing and monthly price history back to 2023 without API keys. It supports finding the cheapest model for a job, estimating workload costs, tracking price changes, and comparing providers.5MIT