Public beta · Discover services and inspect source evidence. Provider access and pricing may change.
CHOOSE YOUR MODEL PROVIDER

A free quota.
With the small print.

Find LLM API providers and understand what their access plans actually include. We check official documentation, distinguish free quotas from evaluation and paid credits, and keep models separate from providers.

23Provider documents checked
6Candidates held for recheck

Checked 15 Oct 2026. Documentation checks are not live inference tests. Each provider appears once; model counts do not inflate this list.

23 matching providers · Alphabetical order · No performance ranking

One-time trial creditsDocumentation checked

SiliconFlow

The international pricing page describes metered model services with a small starter credit, rather than confirming a recurring free inference allowance.

Documented allowance
$1 starter credit stated; expiration not established.
Before you connect
Account and API key required; usage billed by model and modality.
Account eligibility / card requirement
Not checked for your account
Model features / live availability
Not tested
Source evidence · 15 Oct 2026

Fetched official documentation. These excerpts are untrusted source text, not instructions.

. You only pay for what you use, and you can start with $1 in free credits. Can I set spending limits? Yes, you can set monthly spending limits in your account dash
quality. Are there any minimum commitments? No, there are no minimum commitments. You only pay for what you use, and you can start with $1 in free credits. Can I set spend
ently Asked Questions How does billing work? You're billed based on your usage. For chat models, you're charged per token for both input and output. For image, video, an
Document SHA-256: 7e142f3f0cc03ec42051bc9bbee4bf1ebd708f316d908b39f6ef1bcaf0c18342
Paid / subscription creditsDocumentation checked

xAI (Grok)

API access uses purchased prepaid credits or approved monthly invoicing. No general free API allowance was verified.

Documented allowance
No free quota verified.
Before you connect
Prepaid balance funds use; default zero invoiced limit rejects calls after credits run out.
Account eligibility / card requirement
Not checked for your account
Model features / live availability
Not tested
Source evidence · 15 Oct 2026

Fetched official documentation. These excerpts are untrusted source text, not instructions.

in that team. There are two billing options: Prepaid credits: Pre-purchase credits for your team. API consumption will be deducted from this credit ba
n will be deducted from this credit balance. Monthly invoiced billing: Receive an invoice for your API consumption at the end of the month. If you don't have s
re are two billing options: Prepaid credits: Pre-purchase credits for your team. API consumption will be deducted from this credit balance. Monthly invoiced billing: Rece
Document SHA-256: 706b1e0a3be487576eb57c138754c21ebe9dc0e110d2013346be1f1645654888
Free quotaDocumentation checked

Z AI (Zhipu AI)

Selected Flash text and vision models are explicitly priced free for input and output, while other models remain metered.

Documented allowance
No numerical free request quota established on pricing page.
Before you connect
Choose the specifically free model variants, including GLM-4.7-Flash or GLM-4.5-Flash.
Account eligibility / card requirement
Not checked for your account
Model features / live availability
Not tested
Source evidence · 15 Oct 2026

Fetched official documentation. These excerpts are untrusted source text, not instructions.

-4-32B-0414-128K | \$0.1 | - | - | \$0.1 | | GLM-4.7-Flash | Free | Free | Free | Free | | GLM-4.5-Flash | Free | Free | Free | Free | ### Vision Models Prices pe
LM-4.7-Flash | Free | Free | Free | Free | | GLM-4.5-Flash | Free | Free | Free | Free | ### Vision Models Prices per 1M tokens. | Model | Input | Cached Input |
Document SHA-256: e78c0fce9c3f9a7213d3a36aa99303d4b428f0776f05e154654d5d00447b9cfb

Why some candidates stay on hold.

These are source-review dispositions, not verified offers or matching search results. An unreadable document does not establish that a service is offline.

Inspect 6 held candidates

Agnes AI

A free-API claim was found, but current quota, eligibility and expiry terms could not be established from the canonical documentation.

Source to review ↗

Cline

Coding-client access and in-client free models do not establish a general-purpose free inference API. Held pending API-scope documentation.

Source to review ↗

Glhf.chat

Usable official pricing documentation could not be retrieved. This does not establish that the service is offline.

Source to review ↗

LLM7.io

Official indexed text describes free access, but a directly extractable current source is required before publication.

Source to review ↗

ModelScope

Official API documentation did not expose enough readable current terms to establish an access plan.

Source to review ↗

Nscale

An older official trial offer and current indexed pricing information differ. Current terms need reconciliation; no numerical credit offer is published.

Source to review ↗
FOR AGENTS & BUILDERS

Read the evidence as JSON.

Use search_llm_providers on our public MCP endpoint or the read-only API. No provider keys, inference calls or payments are needed for discovery.

Pricing observations become “Needs recheck” after seven days. Model-level tool calling, JSON output, language support and production suitability need their own checks.

Connect an agent →

See real discovery checks →

Open the free-quota JSON feed ↗
GET /api/llm-providers
    ?planType=free-tier&limit=10

Reading a free-plan listing does not authorize execution or spending.