OpenRouter

Verified ✅ Truly Free

A community-focused router for LLMs. Offers a specific list of truly free models with shared quotas.

Free Tier Multi-Model OpenAI Compatible No Credit Card Truly Free Community Pick DeepSeek V4 Llama 4
Get API Key Suggest Edit
5049

Overview

Provider Type

API

API Endpoint

https://openrouter.ai/api/v1

Free Tier Highlights

20 requests/minute

Why Choose OpenRouter?

OpenRouter stands out for its unique features and capabilities. With a developer-friendly API and comprehensive documentation, you can integrate AI capabilities into your applications within minutes.

Quick Start Guide

1

Visit https://openrouter.ai/

2

Sign in with Google or GitHub

3

Navigate to Keys section

4

Create a new API key

5

Use with OpenAI SDK (change base_url)

Available Models

Model Name ID Context Capabilities
Apodex 1.1 Mini Free
apodex/apodex-1.1-mini:free
262 000 Context
-
Poolside Laguna XS 2.1 Free
poolside/laguna-xs-2.1:free
256 000 Context
-
Cohere North Mini Code Free
cohere/north-mini-code:free
256 000 Context
-
Qwen3.8 27B Free
qwen/qwen3.8-27b:free
262 000 Context
-
Thinking Machines Inkling Small Free
thinkingmachines/inkling-small:free
1 000 000 Context
-
Thinking Machines Inkling Free
thinkingmachines/inkling:free
1 000 000 Context
-
NVIDIA Nemotron 3 Super Free
nvidia/nemotron-3-super-120b-a12b:free
262 000 Context
-
inclusionAI Ling 3.0 Flash Sante Free
inclusionai/ling-3.0-flash-sante:free
262 000 Context
-
Dots3-Note Preview Free
dots-studio/dots-3-note-preview:free
512 000 Context
-
NVIDIA Nemotron 3.5 Lightning Free
nvidia/nemotron-3.5-lightning:free
1 000 000 Context
-
Poolside Laguna S 2.1 Free
poolside/laguna-s-2.1:free
262 000 Context
-
NVIDIA Nemotron 3 Ultra Free
nvidia/nemotron-3-ultra-550b-a55b:free
1 000 000 Context
-
Google: Gemini 2.0 Flash (free) No Longer Free
google/gemini-2.0-flash-exp:free
1 000 000
-
Google: Gemini 2.0 Pro (free) No Longer Free
google/gemini-2.0-pro-exp-02-05:free
1 000 000
-
Meta: Llama 3.3 70B Instruct (free) No Longer Free
meta-llama/llama-3.3-70b-instruct:free
128 000
-
NVIDIA: Llama 3.1 Nemotron 70B (free) No Longer Free
nvidia/llama-3.1-nemotron-70b-instruct:free
128 000
-
DeepSeek: R1 (free) No Longer Free
deepseek/deepseek-r1:free
128 000
-
DeepSeek: R1 Distill Llama 70B (free) No Longer Free
deepseek/deepseek-r1-distill-llama-70b:free
128 000
-
Mistral: Small 3 (free) No Longer Free
mistralai/mistral-small-24b-instruct-2501:free
32 000
-
Qwen 2.5 7B Instruct (free) No Longer Free
qwen/qwen-2.5-7b-instruct:free
32 000
-
Qwen 2.5 VL 72B Instruct (free) No Longer Free
qwen/qwen-2.5-vl-72b-instruct:free
32 000
-
Microsoft: Phi-3 Medium (free) No Longer Free
microsoft/phi-3-medium-128k-instruct:free
128 000
-
Microsoft: Phi-3 Mini (free) No Longer Free
microsoft/phi-3-mini-128k-instruct:free
128 000
-
DeepSeek: V4 Flash (free) No Longer Free
deepseek/deepseek-v4-flash:free
1 000 000
-
Meta: Llama 4 Maverick (free) No Longer Free
meta-llama/llama-4-maverick:free
128 000
-
Meta: Llama 4 Scout (free) No Longer Free
meta-llama/llama-4-scout:free
128 000
-
OpenAI: gpt-oss-120b (free) No Longer Free
openai/gpt-oss-120b:free
128 000
-
NVIDIA: Nemotron 3 Ultra (free, promo) No Longer Free
nvidia/nemotron-3-ultra:free
1 000 000
-

Integration Examples

Ready-to-use code snippets for your applications.

main.py
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_OPENROUTER_KEY",
    base_url="https://openrouter.ai/api/v1"
)

response = client.chat.completions.create(
    model="apodex/apodex-1.1-mini:free",
    messages=[
        {"role": "user", "content": "What is OpenRouter?"}
    ]
)

print(response.choices[0].message.content)

Free Tier Pricing & Limits

Rate Limit

Requests per minute

20 requests/minute

Daily Quota

Requests per day

50 requests/day (up to 1000 with $10 topup)

Token Limit

Tokens per minute

Shared quota

Monthly Quota

Per month limit

-

Use Cases

Accessing free models from multiple providers

Model comparison and A/B testing

Fallback for high-availability apps

Exploring different model capabilities

Limitations & Considerations

Limits depend on account history/topup

Community key models

Free models have lower priority during peak demand

Some models may become unavailable

Community Hub

Live

Join the discussion, share tips, and rate OpenRouter.

Quick Reactions

Add Discussion

Comments are moderated. Be helpful and respectful.

Recent Activity

0 comments

Ready to Get Started?

Join thousands of developers using OpenRouter

Start Building Now