Skip to main content
Glama

AI model API prices

get_model_prices
Read-onlyIdempotent

Each AI model's posted API prices in USD per 1M input, cached input and output tokens and its price at the mix of tokens agents send (the models behind the token index and the Intelligence Index chart's, each with its page), with its usage share and its 1-month change. Give a model (name or page id, e.g. "Claude Opus 5.5" or "kimi-k3") for its daily price history as its page's chart draws it (a name several models share answers with each one's prices), or a company to list its models. Every other model OpenRouter prices is on the Every AI model page (https://computescreener.com/models): give its name or id (e.g. "meta-llama/llama-3.3-70b-instruct"), any company on it (e.g. "Cohere"), or every: true to list them, with sort: "price" for the cheapest input price first. For questions like "what does Claude Sonnet cost per 1M input and output tokens?", "the cheapest AI model API" or "the cheapest provider of a model".

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_model_prices"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo"price": the cheapest input price first, then output (every model's default); "name": by company and name. A company's models otherwise come by usage, as its page lists them.
everyNoList every model on the Every AI model page (/models), not only those with a page.
limitNoHow many models to list (the Every AI model page lists over 300).
modelNoA model's name, page id or OpenRouter id; omit to list models.
companyNoList only this company's models: one of the token index's companies (Anthropic, OpenAI, Google, xAI, Meta, Moonshot AI, Alibaba, DeepSeek, Z.ai, Xiaomi, StepFun, MiniMax, Mistral, Reflection AI, NVIDIA, Thinking Machines) or any other company on the Every AI model page (e.g. "Cohere", "Amazon").

Output Schema

NameRequiredDescriptionDefault
noteNo
unitYes
totalNoHow many models the list has before limit
fieldsNoWhat each figure of a model's row is
modelsYes
licenseNo
sourcesNo
updatedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • changedInput schema / properties / sort / description
      Previous value: -"\"price\": the cheapest at the mix first (every model's default); \"name\": by company and name. A company's models otherwise come by usage, as its page lists them."New value: +"\"price\": the cheapest input price first, then output (every model's default); \"name\": by company and name. A company's models otherwise come by usage, as its page lists them."
    • removedOutput schema / properties / models / items / properties / list_price
      Removed value: -{
      -  "description": "3 input : 1 output, USD per 1M tokens (break-even throughput uses it)",
      -  "type": [
      -    "number",
      -    "null"
      -  ]
      -}
    • removedOutput schema / properties / models / items / properties / lowest_price
      Removed value: -{
      -  "description": "The lowest provider's price at the mix, USD per 1M tokens",
      -  "type": [
      -    "number",
      -    "null"
      -  ]
      -}
    • addedOutput schema / properties / models / items / properties / lowest_provider / description
      Added value: +"The cheapest provider serving it (the Every AI model page's Cheapest)"
    • changedOutput schema / properties / models / items / properties / price / description
      Previous value: -"USD per 1M tokens at the mix (87% cache read, 12% input, 1% output)"New value: +"USD per 1M tokens at the mix (87% cache read, 12% input, 1% output), as the model's own page shows it (models with a page only)"
    • removedOutput schema / properties / models / items / properties / priced_by
      Removed value: -{
      -  "description": "company: its maker's own price; providers: the median of the providers serving it",
      -  "type": [
      -    "string",
      -    "null"
      -  ]
      -}
    • changedOutput schema / properties / models / items / properties / providers / description
      Previous value: -"Providers serving it at a standard price"New value: +"Providers serving it (the Every AI model page's Providers)"
    • removedOutput schema / properties / models / items / properties / source_url
      Removed value: -{
      -  "description": "Where its prices can be checked",
      -  "type": [
      -    "string",
      -    "null"
      -  ]
      -}
  2. Changed7 schema fields changed
    • changedInput schema / properties / company / description
      Previous value: -"List only this company's models."New value: +"List only this company's models: one of the token index's companies (Anthropic, OpenAI, Google, xAI, Meta, Moonshot AI, Alibaba, DeepSeek, Z.ai, Xiaomi, StepFun, MiniMax, Mistral, Reflection AI, NVIDIA, Thinking Machines) or any other company on the Every AI model page (e.g. \"Cohere\", \"Amazon\")."
    • removedInput schema / properties / company / enum
      Removed value: -[
      -  "Anthropic",
      -  "OpenAI",
      -  "Google",
      -  "xAI",
      -  "Meta",
      -  "Moonshot AI",
      -  "Alibaba",
      -  "DeepSeek",
      -  "Z.ai",
      -  "Xiaomi",
      -  "StepFun",
      -  "MiniMax",
      -  "Mistral",
      -  "Reflection AI",
      -  "NVIDIA",
      -  "Thinking Machines"
      -]
    • addedInput schema / properties / limit
      Added value: +{
      +  "default": 50,
      +  "description": "How many models to list (the Every AI model page lists over 300).",
      +  "maximum": 400,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / sort
      Added value: +{
      +  "description": "\"price\": the cheapest at the mix first (every model's default); \"name\": by company and name. A company's models otherwise come by usage, as its page lists them.",
      +  "enum": [
      +    "price",
      +    "name"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / fields
      Added value: +{
      +  "description": "What each figure of a model's row is",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / note
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / total
      Added value: +{
      +  "description": "How many models the list has before limit",
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
  3. Changed7 schema fields changed
    • addedInput schema / properties / every
      Added value: +{
      +  "description": "List every model on the Every AI model page (/models), not only those with a page.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / model / description
      Previous value: -"A model's name or page id; omit to list models."New value: +"A model's name, page id or OpenRouter id; omit to list models."
    • addedOutput schema / properties / models / items / properties / lowest_price
      Added value: +{
      +  "description": "The lowest provider's price at the mix, USD per 1M tokens",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / models / items / properties / lowest_provider
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / models / items / properties / priced_by
      Added value: +{
      +  "description": "company: its maker's own price; providers: the median of the providers serving it",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / models / items / properties / providers
      Added value: +{
      +  "description": "Providers serving it at a standard price",
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / models / items / properties / source_url
      Added value: +{
      +  "description": "Where its prices can be checked",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  4. Changed13 schema fields changed
    • changedInput schema / properties / company / enum
      Previous value: -[
      -  "Anthropic",
      -  "OpenAI",
      -  "Google",
      -  "xAI",
      -  "Meta",
      -  "Moonshot AI",
      -  "Alibaba",
      -  "DeepSeek",
      -  "Z.ai",
      -  "Xiaomi"
      -]New value: +[
      +  "Anthropic",
      +  "OpenAI",
      +  "Google",
      +  "xAI",
      +  "Meta",
      +  "Moonshot AI",
      +  "Alibaba",
      +  "DeepSeek",
      +  "Z.ai",
      +  "Xiaomi",
      +  "StepFun",
      +  "MiniMax",
      +  "Mistral",
      +  "Reflection AI",
      +  "NVIDIA",
      +  "Thinking Machines"
      +]
    • removedOutput schema / properties / models / items / properties / blended_price
      Removed value: -{
      -  "description": "3 input : 1 output, USD per 1M tokens",
      -  "type": [
      -    "number",
      -    "null"
      -  ]
      -}
    • addedOutput schema / properties / models / items / properties / cache_read_price
      Added value: +{
      +  "description": "Posted USD per 1M cached input tokens (the input price where none is posted)",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • changedOutput schema / properties / models / items / properties / change_1m_pct / description
      Previous value: -"Blended price change over 30 days, percent"New value: +"Change of its price at the mix over 1 month, percent (its page's 1M)"
    • removedOutput schema / properties / models / items / properties / changes
      Removed value: -{
      -  "items": {
      -    "properties": {
      -      "date": {
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      },
      -      "input_price": {
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "output_price": {
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      }
      -    },
      -    "type": [
      -      "object",
      -      "null"
      -    ]
      -  },
      -  "type": [
      -    "array",
      -    "null"
      -  ]
      -}
    • removedOutput schema / properties / models / items / properties / history / items / properties / input_price
      Removed value: -{
      -  "type": [
      -    "number",
      -    "null"
      -  ]
      -}
    • removedOutput schema / properties / models / items / properties / history / items / properties / output_price
      Removed value: -{
      -  "type": [
      -    "number",
      -    "null"
      -  ]
      -}
    • addedOutput schema / properties / models / items / properties / history / items / properties / price
      Added value: +{
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • removedOutput schema / properties / models / items / properties / history / items / properties / usage_share
      Removed value: -{
      -  "type": [
      -    "number",
      -    "null"
      -  ]
      -}
    • removedOutput schema / properties / models / items / properties / last_change
      Removed value: -{
      -  "description": "Last day its posted prices changed",
      -  "type": [
      -    "string",
      -    "null"
      -  ]
      -}
    • addedOutput schema / properties / models / items / properties / list_price
      Added value: +{
      +  "description": "3 input : 1 output, USD per 1M tokens (break-even throughput uses it)",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / models / items / properties / price
      Added value: +{
      +  "description": "USD per 1M tokens at the mix (87% cache read, 12% input, 1% output)",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • changedOutput schema / properties / models / items / properties / usage_share / description
      Previous value: -"Share of the company's tokens that day (0 to 1)"New value: +"Share of the company's tokens that day (0 to 1); null outside the index"
  5. Changed16 schema fields changed
    • changedOutput schema / properties / license / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / properties / changes / items / properties / date / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / properties / changes / items / type
      Previous value: -"object"New value: +[
      +  "object",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / properties / changes / type
      Previous value: -"array"New value: +[
      +  "array",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / properties / company / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / properties / date / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / properties / history / items / properties / date / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / properties / history / items / type
      Previous value: -"object"New value: +[
      +  "object",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / properties / history / type
      Previous value: -"array"New value: +[
      +  "array",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / properties / model / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / properties / url / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / models / items / type
      Previous value: -"object"New value: +[
      +  "object",
      +  "null"
      +]
    • changedOutput schema / properties / models / type
      Previous value: -"array"New value: +[
      +  "array",
      +  "null"
      +]
    • changedOutput schema / properties / sources / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / unit / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • changedOutput schema / properties / updated / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
  6. Added

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, closed-world behavior, and the description does not contradict them. It adds genuinely new context: that the default view is page-backed models only, that company listings default to usage order, and that over 300 models exist behind every: true. Missing: rate limits or pagination interaction with limit/max 400.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense run-on paragraph that opens with a long enumeration of returned fields before explaining what the tool does. Contractions and merged clauses ("...and its price at the mix of tokens agents send (the models behind the token index and the Intelligence Index chart's, each with its page)") force re-reading, and the key routing rules are buried mid-paragraph.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-required-parameter tool with an output schema and five documented params, the description covers both coverage modes, sorting behavior, and id formats well enough to call it correctly. The returned price fields are described awkwardly but an output schema exists, so that is not a blocking gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description mostly restates enum and default semantics already in the schema (sort, every, limit). It does add real value for the model parameter by giving concrete id formats ("Claude Opus 5.5", "meta-llama/llama-3.3-70b-instruct"), which is not in the schema itself.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

It names the resource specifically (AI model API prices in USD per 1M input/cached input/output tokens) and the two coverage tiers: models with their own page vs every model OpenRouter prices. The verb and subject are clear, but the first sentence is cluttered with output-field enumeration before the action is stated, which blunts the initial read.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit branching: pass a model for daily price history, a company to list that company's models, or every: true plus sort: "price" for the full list cheapest-first. It also anchors the tool to concrete user questions ("what does Claude Sonnet cost per 1M input and output tokens?"). It does not, however, say when to prefer the siblings get_provider_prices or get_token_prices instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources