Free — No Credit Card Required
Free LLM API
Start with free models · Shared limits apply
Try 7 enabled free models. Account limits are shared across free models, with an additional IP guard. When weighted limits are enabled, longer inputs use more daily units; otherwise each request counts once. Current limits are shown below.
Free Models Right Now7
Only enabled free models are listed. Limits are shared across free models for an account, with an additional IP guard. Free tier rules →
| Model | Maker | Shared free allowance | Context | Input modalities | Reset rule | Catalogue snapshot (UTC) | Last 24h probe success |
|---|---|---|---|---|---|---|---|
| Qwen3.7 Flash qwen/qwen3.7-flash | Qwen | No credit: 10 RPM and 60 weighted units/day. With credit: 20 RPM and 120 weighted units/day. Shared across free models. | 1,000,000 tokens | text, image, video | Daily; resets at 00:00 UTC | 2026-10-19 17:44 UTC | 100% 23/23 2026-10-19 19 UTC |
| Glyph Cluster stealth/glyph-cluster | stealth | No credit: 10 RPM and 60 weighted units/day. With credit: 20 RPM and 120 weighted units/day. Shared across free models. | 256,000 tokens | text | Daily; resets at 00:00 UTC | 2026-10-19 17:44 UTC | Insufficient samples |
| Cat Jam stealth/cat-jam | stealth | No credit: 10 RPM and 60 weighted units/day. With credit: 20 RPM and 120 weighted units/day. Shared across free models. | 1,048,576 tokens | text | Daily; resets at 00:00 UTC | 2026-10-19 17:44 UTC | Insufficient samples |
| Beam reflection/beam | reflection | No credit: 10 RPM and 60 weighted units/day. With credit: 20 RPM and 120 weighted units/day. Shared across free models. | 1,048,576 tokens | text | Daily; resets at 00:00 UTC | 2026-10-19 17:44 UTC | Insufficient samples |
| Nemotron 3.5 Lightning Free nvidia/nemotron-3.5-lightning-free | NVIDIA | No credit: 10 RPM and 60 weighted units/day. With credit: 20 RPM and 120 weighted units/day. Shared across free models. | 1,000,000 tokens | text | Daily; resets at 00:00 UTC | 2026-10-19 17:44 UTC | Insufficient samples |
| Beam Free reflection/beam-free | reflection | No credit: 10 RPM and 60 weighted units/day. With credit: 20 RPM and 120 weighted units/day. Shared across free models. | 1,048,576 tokens | text | Daily; resets at 00:00 UTC | 2026-10-19 17:44 UTC | Insufficient samples |
| DeepSeek V4 Flash 0731 (Free) deepseek/deepseek-v4-flash-0731free | DeepSeek | No credit: 10 RPM and 60 weighted units/day. With credit: 20 RPM and 120 weighted units/day. Shared across free models. | 1,048,576 tokens | text | Daily; resets at 00:00 UTC | 2026-10-19 17:44 UTC | 91% 21/23 2026-10-19 19 UTC |
This is the public catalogue snapshot time, not an individual model verification time.
Hourly probe outcomes; percentage uses only sampled hours. Sample coverage is shown as successes / attempts, with the latest sampled hour in UTC.
Free Tier Limits
Accounts without credit
10 RPM · 60 weighted units/dayAccounts with credit
20 RPM · 120 weighted units/daySite-wide free RPM cap
20 RPMConcurrent free requests per account
2No credit: 10 RPM and 60 weighted units/day. With credit: 20 RPM and 120 weighted units/day. Shared across free models. Daily; resets at 00:00 UTC. Free tier rules →
Why BazaarLink Free Tier
Free AI API Key
Sign up and get a free key in under 60 seconds. No credit card, no waitlist.
Choose a listed model
Use a model ID shown in the live table below.
OpenAI-Compatible
Same request format as OpenAI. Change base_url and you're done — no SDK changes.
All Major Models
GPT, Claude, Gemini, DeepSeek, Llama, Qwen and more through one endpoint.
No Lock-In
Standard OpenAI API format. Migrate in or out anytime with no code changes.
Quickstart — Free LLM API
Step 1 — Get your free API key
Choose Sign up, then Create an API key.
# Keep the API key in an environment variable:
export BAZAARLINK_API_KEY="your-api-key"
export OPENAI_BASE_URL=https://api.bazaarlink.ai/v1
export BAZAARLINK_API_KEY="your-api-key"
export OPENAI_BASE_URL=https://api.bazaarlink.ai/v1
Step 2 — Call the free LLM API (Python)
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.bazaarlink.ai/v1",
api_key=os.environ["BAZAARLINK_API_KEY"],
)
response = client.chat.completions.create(
model="qwen/qwen3.7-flash",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
from openai import OpenAI
client = OpenAI(
base_url="https://api.bazaarlink.ai/v1",
api_key=os.environ["BAZAARLINK_API_KEY"],
)
response = client.chat.completions.create(
model="qwen/qwen3.7-flash",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
Step 2 — Call the free LLM API (TypeScript / Node.js)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.bazaarlink.ai/v1",
apiKey: process.env.BAZAARLINK_API_KEY!,
});
const response = await client.chat.completions.create({
model: "qwen/qwen3.7-flash",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
const client = new OpenAI({
baseURL: "https://api.bazaarlink.ai/v1",
apiKey: process.env.BAZAARLINK_API_KEY!,
});
const response = await client.chat.completions.create({
model: "qwen/qwen3.7-flash",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
Works With Your Existing Stack
BazaarLink is a drop-in free OpenAI-compatible API. Set base_url and swap your key — everything else stays the same.
LangChainLlamaIndexCrewAIAutoGenLiteLLMOpenAI SDK (Python)OpenAI SDK (Node)DifyLobeChatOpenWebUI
Free AI API — FAQ
Is the free AI API unlimited?
No. The shared allowance is 10/20 RPM and 60/120 weighted units per day for no-credit/credited accounts. Limits apply across free models.
How is the daily free allowance measured?
The daily allowance resets at 00:00 UTC. When weighted use is enabled, longer input prompts use more units; otherwise each request counts once. The live table shows the current tier limits.
What happens after a free limit is reached?
The request can be rejected with a rate-limit response. Paid use may continue only if paid fallback is enabled for the key and the account has sufficient credit.
Which model should I call?
Choose an enabled model ID from the live table and pass it as the model value in your request.
Is the endpoint OpenAI-compatible?
Yes. Use https://api.bazaarlink.ai/v1 with an API key from your account and a listed free model ID.
From the Blog
Start for Free — No Credit Card
Only enabled free models are listed. Limits are shared across free models for an account, with an additional IP guard.