Summary: card or no card
| Provider | Card for the free tier? | What the provider says |
|---|---|---|
| Google AI Studio (Gemini) | No card in the signup steps | AI Studio makes a default Google Cloud project and an API key after you accept the terms. Some projects are not eligible for the free tier. |
| Groq | No card in the signup steps | Groq asks for a payment method only when you upgrade from the Free tier to the Developer tier. |
| OpenRouter | No card for :free models | Free models allow 50 requests per day. After you buy 10 credits, the cap is 1,000 per day. |
| Cohere | Not stated | Trial keys are free and rate limited. They are not permitted for production or commercial use. |
| NVIDIA API Catalog | Not stated | Developer Program members get free access to NIM API endpoints for prototyping. |
| OVHcloud AI Endpoints | No account for anonymous use | Anonymous use allows 2 requests per minute. An API key needs a Public Cloud project with a payment method. |
| Kilo Gateway | No account for free models | Anonymous calls to free models are limited to 200 requests per hour for each IP address. |
| Mistral | Billing is needed for the API | Mistral's documentation says that free mode does not include API access. |
Google AI Studio: free Gemini key
Google AI Studio is the fastest way to get a free key. Sign in with a Google account and accept the terms. AI Studio then makes a default Google Cloud project and an API key. You must be 18 years or older.
Some projects show Free tier unavailable. Requests from these projects return 403 PERMISSION_DENIED. Google says that a new key in the same project does not fix this. The only fix is to link a billing account and use the paid tier.
On the free tier, Google can use your prompts and responses to improve its products. Human reviewers can read them. Read free LLM API data training before you send private data.
| Model | Free on | Context | Free limits (best offer) | Tools | Vision |
|---|---|---|---|---|---|
| Gemini 3.8 Flash | Google AI Studio | 1M | Recurring provider quota | Yes | Yes |
| Gemini Flash (latest alias) | Google AI Studio | - | 10 req/min 20 req/day 250,000 tokens/min ~3M | Yes | Yes |
| Gemini 3.7 Flash | Google AI Studio | 1M | 10 req/min 20 req/day 250,000 tokens/min ~3M | Yes | Yes |
| Gemini 3.6 Flash | Google AI Studio | 1M | 10 req/min 20 req/day 250,000 tokens/min ~3M | Yes | Yes |
| Gemini 3.5 Flash | Google AI Studio | 1M | 10 req/min 20 req/day 250,000 tokens/min ~3M | Yes | Yes |
| Gemini 3.8 Live | Google AI Studio | - | 10 req/min 20 req/day 250,000 tokens/min ~3M | Yes | Yes |
| Gemini 3.8 Live Extended Thinking | Google AI Studio | - | 10 req/min 20 req/day 250,000 tokens/min ~3M | Yes | Yes |
| Gemini 3.8 Flash TTS | Google AI Studio | - | Ongoing AI Studio free-tier quota; account limits apply | No | No |
Showing 8 of 21 matching free models. See all models.
Live data from the FreeLLMAPI catalog (version 2026.11.19, checked 19 November 2026). Free limits change often. The catalog is checked every day.
Groq: free key with fast inference
Make an account on the GroqCloud console and create a key on the API Keys page. Groq's billing FAQ says that you need a valid payment method only to upgrade to the Developer tier. Limits apply to the whole organization.
| Model | Free on | Context | Free limits (best offer) | Tools | Vision |
|---|---|---|---|---|---|
| Qwen3.8 27B | Groq | 262K | 30 req/min 250 req/day 70,000 tokens/min ~6M | Yes | Yes |
| GPT-OSS 120B | Groq | 131K | 30 req/min 1,000 req/day 8,000 tokens/min 200,000 tokens/day ~6M | Yes | No |
| GPT-OSS 20B | Groq | 131K | 30 req/min 1,000 req/day 8,000 tokens/min 200,000 tokens/day ~6M | Yes | No |
| GPT-OSS Safeguard 20B | Groq | 131K | 30 req/min 1,000 req/day 8,000 tokens/min 200,000 tokens/day ~6M | Yes | No |
| ALLaM 2 7B | Groq | 4K | 30 req/min 1,000 req/day 6,000 tokens/min 500,000 tokens/day ~15M | No | No |
| Llama Prompt Guard 2 22M | Groq | 512 | 30 req/min 14,400 req/day 15,000 tokens/min 14.4K rpd | No | No |
| Llama Prompt Guard 2 86M | Groq | 512 | 30 req/min 14,400 req/day 15,000 tokens/min 14.4K rpd | No | No |
Live data from the FreeLLMAPI catalog (version 2026.11.19, checked 19 November 2026). Free limits change often. The catalog is checked every day.
NVIDIA, OpenRouter and Zhipu
- NVIDIA API Catalog: join the NVIDIA Developer Program and create a key on build.nvidia.com. The trial terms allow use for limited trial purposes only, not in production.
- OpenRouter: models with the
:freesuffix cost nothing. The free cap is shared by all free models on the account. - Z.ai (Zhipu): the Z.ai pricing page lists GLM-4.7-Flash, GLM-4.5-Flash and GLM-4.6V-Flash as free. We did not find a statement about cards.
| Model | Free on | Context | Free limits (best offer) | Tools | Vision |
|---|---|---|---|---|---|
| GLM 5.3 Flash | NVIDIA NIM | 1M | 40 req/min 40 RPM | Yes | No |
| Dots3 Note Preview | OpenRouter | 512K | 20 req/min 50 req/day 50 req/day account-wide (1,000 after a $10 purchase) | Yes | Yes |
| Nemotron 3 Ultra 550B | NVIDIA NIM, OpenRouter | 1M | 20 req/min 50 req/day 50 req/day account-wide (1,000 after a $10 purchase) | Yes | No |
| Muse Glimmer 30B | NVIDIA NIM | 131K | 40 req/min 40 RPM | Yes | Yes |
| GLM-4.7 Flash | Zhipu AI | 131K | 1,000,000 tokens/day ~30M | Yes | No |
| Poolside Laguna XS 2.1 | NVIDIA NIM | 262K | 40 req/min 40 RPM | Yes | No |
| Nemotron 3 Super 120B | NVIDIA NIM | 262K | 40 req/min 40 RPM | Yes | No |
| Nemotron 3.5 Lightning | OpenRouter | 1M | 20 req/min 50 req/day 50 req/day account-wide (1,000 after a $10 purchase) | Yes | No |
| Nemotron 3.5 Lightning 30B A3B | NVIDIA NIM | 1M | 40 req/min 40 RPM | Yes | No |
| North Mini Code | OpenRouter | 256K | 20 req/min 50 req/day ~6M | Yes | No |
Showing 10 of 14 matching free models. See all models.
Live data from the FreeLLMAPI catalog (version 2026.11.19, checked 19 November 2026). Free limits change often. The catalog is checked every day.
Providers that need billing for the API
- Mistral: the usage limits page says: "Free mode includes a monthly usage budget for trying Vibe and Studio. It doesn't include API access." To create API keys, you must activate billing and pay as you go.
- OVHcloud with a key: an API key needs a Public Cloud project with a payment method. Anonymous use without a key does not need an account.
- Cloudflare Workers AI: the Workers Free plan includes 10,000 neurons per day. Cloudflare's developer pages do not say whether the free plan needs a card. We could not confirm it.
- Scaleway Generative APIs: the free tier covers the first 1,000,000 tokens. After that, Scaleway charges per million tokens.
Use the no-card keys together
Each free key has a small quota. FreeLLMAPI puts the keys behind one OpenAI-compatible endpoint on your computer. When one provider sends a 429 error, the router sends the request to the next provider. Your keys stay on your computer, encrypted in a local database.
- Install FreeLLMAPI:
curl -fsSL https://freellmapi.co/install.sh | bash. - Open
http://localhost:3001. - Add your Google, Groq, NVIDIA and OpenRouter keys on the Keys page.
- Copy the unified key from the same page.
- Set your client base URL to
http://localhost:3001/v1and the model toauto.
Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(base_url="http://localhost:3001/v1", api_key="<unified-key>")
resp = client.chat.completions.create(
model="auto",
messages=[{"role": "user", "content": "Say hello"}],
)
print(resp.choices[0].message.content)The catalog also has keyless rows for some providers, for example OVHcloud and Kilo. These rows work with no account and no key. They have low limits, so use them as extra capacity only.
Frequently asked questions
Which LLM API is free without a credit card?
Google AI Studio, Groq and the free models on OpenRouter give a key without a card in their signup steps. OVHcloud and Kilo also allow some anonymous calls with no account.
Does the Gemini API need a credit card?
No card is part of the AI Studio key steps. Some Google Cloud projects are not eligible for the free tier. For those projects, Google requires a billing account and the paid tier.
Is the Mistral API free without a card?
Not as of 20 November 2026. Mistral's documentation says that free mode does not include API access. API keys need billing activation and pay-as-you-go.
Is the Groq API free without a credit card?
Yes. Groq asks for a payment method only when you upgrade from the Free tier to the Developer tier. The free tier has rate limits for each model.
Can I use a free API key in a commercial product?
It depends on the provider. Cohere trial keys and NVIDIA trial access do not allow production use. Read each provider's terms before you ship.
Related guides
- how to get a free llm api key
- LLM API without signup
- Free LLM API rate limits
- Free LLM API for commercial use
- free gemini api
- free groq api
Sources
- Google AI Studio: API keys (checked 20 November 2026)
- Google AI Studio: Troubleshooting (checked 20 November 2026)
- GroqCloud: Billing FAQs (checked 20 November 2026)
- OpenRouter: API rate limits (checked 20 November 2026)
- Cohere: Pricing (checked 20 November 2026)
- NVIDIA NIM FAQ (checked 20 November 2026)
- OVHcloud: AI Endpoints getting started (checked 20 November 2026)
- Kilo Gateway: Authentication (checked 20 November 2026)
- Mistral docs: Usage and limits (checked 20 November 2026)
- Z.ai: Pricing (checked 20 November 2026)
- Scaleway Generative APIs: FAQ (checked 20 November 2026)