Models → Pricing → Docs → Blog → Changelog → Contact → Status →
Get started freeLog in
Free 1M tokens every month · no card needed

One API for coding agents. chatbots. RAG pipelines. vision apps. batch jobs. coding agents.

29 models behind one OpenAI-compatible endpoint. Change a single base URL — keep your SDK, your tools and your code.

  • 1M free tokens / month
  • Plans from $1.20
  • Every model on every plan

Works with the tools you already use — anything that accepts a custom OpenAI endpoint

0
models on every plan
0
token context on most models
0
free tokens, every month
0
per 1M tokens on Scale
Quickstart

Live in three steps

No SDK to learn, no migration. If your code talks to OpenAI, it already talks to FreeModel.

  1. 01~30 seconds

    Create a key

    Sign up free and generate an API key from your dashboard. Scope it to inference, models or embeddings.

  2. 02one line

    Point your client

    Set the base URL to freemodel.in/v1 and paste the key. Everything else in your code stays the same.

  3. 03live

    Ship

    Track every request, token and cent in the dashboard. Swap models without touching your integration.

Platform

Everything production needs.
Nothing it doesn’t.

Not a thin proxy — the plumbing that long-running agents and real apps depend on, built in from day one.

True streaming

Server-sent events with keep-alive pings and long-lived connections, so long agent turns aren’t dropped by proxies mid-answer.

  • SSEOpenAI chunks
  • 8skeep-alive
  • 15 minper request

Tool calling

Full round trips, parallel calls and streamed argument deltas — exactly what coding agents run on.

Vision input

Send screenshots, mockups and diagrams as base64 or URLs, with per-model capability discovery.

Usage analytics

Every request, token, latency figure and cent — per key and per model. Real numbers, no estimates.

  • Per keyspend caps
  • p95latency
  • CSVexport

Reasoning models

Chain-of-thought arrives in its own field, so thinking never contaminates your answer.

Simple payments

Pay with UPI in India or USDT (BEP-20) from anywhere. Payments are verified automatically and land in your balance — no card needed.

Integrations

Your setup, generated.

Pick your tool and model — copy the exact config. No guesswork, no docs digging.

settings
Catalog

Models to start with

Lightweight and fast, or deeply capable — the same API either way.

Browse all 29 models
Pricing

Bigger package, cheaper per token.

Every plan — free included — reaches every model. You only choose how many tokens you need.

PlanTokens / monthRate limitPricePer 1M tokens
FAQ

Common questions

How much does it cost?
Start free with 1M tokens every month. Paid plans begin at $1.20/month for 30M tokens and scale up from there. Every plan unlocks every model — you are only buying token volume, never feature access.
Do cheaper plans limit which models I can use?
No. Every plan, including the free tier, reaches the full catalog. Plans differ only in monthly token volume and per-minute rate limits.
Is this compatible with the OpenAI SDK?
Yes — completely. Point any official OpenAI SDK (Python, Node, Go, .NET) at our base URL and pass your key. Request and response shapes match the OpenAI spec, including streaming chunks, tool calls and error envelopes.
Which AI coding tools can I use it with?
Anything that accepts a custom OpenAI-compatible endpoint: Kilo Code, Cline, Cursor, opencode, Claude Code, Continue and Aider. Set the provider to “OpenAI Compatible”, paste the base URL and key, and pick a model — or use the config generator above.
What counts as a token?
Tokens cover both your prompt and the model’s reply, combined. Your plan allowance is spent first and resets monthly; anything beyond it bills against your account balance at each model’s published per-token rate.
Do you support streaming and tool calling?
Yes. Streaming uses server-sent events with keep-alive pings and a single request can stream for up to 15 minutes — suited to long agent turns. Tool calling supports full round trips, parallel calls and streamed argument deltas.
What happens if I run out of tokens?
Requests fall back to your balance. With an empty balance you get HTTP 402 and a clear error before the request reaches a model, so you are never billed unexpectedly and never cut off mid-response. Top up or upgrade and you resume immediately.
What payment methods do you accept?
UPI (Google Pay, PhonePe, Paytm and any UPI app) and USDT on BEP-20 / BNB Smart Chain. Both are confirmed automatically — no credit card needed.
Ready in about a minute

Your next feature is one base URL away.

Create a free account, grab a key and keep your existing SDK. 1M tokens are on us, every month.

https://freemodel.in/v1