Price Per Token

What is Price Per Token?

Price Per Token is a website that puts the API cost of large language models into one filterable table, so a developer can see what a model charges before wiring it into an app. Each row names the provider and model, then shows context window, input price, output price and cached-input price, and some rows add coding, MMLU and GPQA scores. Filters narrow the list to models with tool use, vision, reasoning, web search, PDF input, caching, audio input or open weights. The homepage shows a last-updated timestamp and a list of newly released models, and a newsletter covers pricing changes each week. Beyond the table, the site offers an MCP server that hands live pricing and benchmark data to AI agents, provider-versus-provider comparison pages for inference hosts and cloud platforms, and a cost-aware LLM gateway with budget limits and request traces. Browsing the pricing table is free and no plans are published; the gateway's pricing is not listed.

Use cases

• Compare LLM API prices by provider
• Find cheap models that support tool use
• Check cached-input token costs
• Track newly released models
• Give an AI agent live pricing data
• Compare inference providers for one model

Who it's for

• AI developers
• Startup founders
• Engineering managers
• Agent builders

Why use Price Per Token

• One page replaces a dozen provider pricing pages, which makes comparing token costs for a project quick.
• Capability filters cut a long model list down to those that support the features your app depends on.
• Cached-input prices sit next to standard ones, which matters when prompts repeat long context.
• The MCP server lets a coding agent look up current prices rather than guess from older training data.
• Provider comparison pages show where the same model costs less on a different host.

Price Per Token features

• Table of input, output and cached-input prices per model
• Capability filters for tool use, vision, reasoning and more
• Context window shown for every model
• MMLU and GPQA benchmark columns where available
• List of newly released models with dates
• Side-by-side comparison pages for inference providers
• MCP server with live pricing and benchmarks
• LLM gateway with cost tracking and spending limits
• Weekly newsletter on pricing changes

Price Per Token integrations

• OpenAI SDK

How to get started with Price Per Token

1. Open pricepertoken.com; the table loads without sign-in.
2. Tick the capability filters your app needs, such as tool use or vision.
3. Sort by input or output price and check each model's context window.
4. Look at the benchmark columns where a model has scores, then follow the Try link to test it.
5. Optionally join the newsletter or add the MCP server to your agent for live lookups.

Price Per Token limitations

• The table is a reference; you still call each provider's API yourself
• A sponsored routing-service placement appears on the homepage
• Many benchmark cells are empty
• Gateway pricing is not listed on the site

Price Per Token pricing

Price Per Token is free to use.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

Price Per Token alternatives

The main Price Per Token alternatives listed on Debuly are OpenRouter, Helicone, LiteLLM, AIFast Model Check, BurnRate and CLIRank. The table compares pricing and platforms; order is A–Z.

1. 

   AIFast Model Check

   Online checker that probes OpenAI-compatible API gateways for model mismatch, degraded capability and routing changes, with itemized evidence.

   Developer platformsResearch and search
   FreeVisit AIFast Model Check (official site)
2. 

   BurnRate

   AI cost analytics that combines OpenAI and Anthropic spend in one dashboard, with budgets and a local CLI for coding-tool sessions.

   Developer platformsProductivity
   FreemiumVisit BurnRate (official site)
3. 

   CLIRank

   Free scorecard of 420 APIs rated on how well coding agents can use them, queryable through an MCP server and a JSON API.

   Developer platformsCodingResearch and search
   FreeVisit CLIRank (official site)
4. 

   Helicone

   Open-source LLM observability and AI gateway that logs requests, tracks cost and latency, and routes to 100+ models through one API.

   Developer platformsCoding
   FreemiumVisit Helicone (official site)
5. 

   LiteLLM

   Open-source AI gateway and Python SDK that gives one OpenAI-format API to 100+ LLM providers, with keys, budgets and cost tracking.

   Developer platformsCodingAutomation and agents
   Open sourceVisit LiteLLM (official site)
6. 

   OpenRouter

   Unified OpenAI-compatible API for 500+ AI models with provider fallbacks, pay-as-you-go credits and a free tier

   Developer platformsChat assistantsAutomation and agents
   FreemiumVisit OpenRouter (official site)

Price Per Token FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from pricepertoken.com · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.