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
AI21 Labs
AI21 offers a time-limited API trial followed by usage-based paid inference.
Documented allowance
$10 trial credits valid for 7 days.
Before you connect
No credit card needed for trial; usage pricing applies afterward.
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.
lk to a training expert Pricing Start with a free trial, no credit card required, then pay based on usage. See usage pricing for Foundation Model
model APIs & SDK Unlimited seats Free Trial $10 credits for 7 days. No credit card needed Start Now for FREE Custom Plan For companies looking to scale and t
ted seats Free Trial $10 credits for 7 days. No credit card needed Start Now for FREE Custom Plan For companies looking to scale and those that require cust
Aion advertises a recurring daily allowance for its hosted API, agent jobs and browser chat.
Documented allowance
A daily credit allowance is documented. The pricing page does not state a universal token quota.
Before you connect
Free is the default on signup; no card required. Paid tiers depend on lifetime credit top-ups.
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.
per token with pricing that varies by model. Free Tier Get started $0 A daily credit allowance to try agent jobs, the API, and browser chat. No
at varies by model. Free Tier Get started $0 A daily credit allowance to try agent jobs, the API, and browser chat. No card required. Sign Up Free Prepaid Cred
o try agent jobs, the API, and browser chat. No card required. Sign Up Free Prepaid Credit balance Pay as you go Load credits and spend them on agent jo
First activation grants temporary per-model inference quota for eligible international models in Singapore. This is a new-user trial rather than a recurring allowance.
Documented allowance
Valid 90 days; model-specific quota shown in console.
Before you connect
Account information and service activation required. Only real-time inference is covered; Free Quota Only must be enabled to stop after exhaustion.
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.
Free quota for new users_Alibaba Cloud Model Studio(Model Studio) - Alibaba Cloud Model Studio - Alibaba Cloud Doc
a pay-as-you-go basis. Rules Validity period The free quota is valid for 90 days, starting from the date you activate Alibaba Cloud Model Studio, the model is released, o
trial. Worry-free mode (Free Quota Only) is disabled by default; enable it in the console if needed. Users who activated before September 15 but have not
Current pricing offers a one-time promotional inference credit, followed by separately purchased PayGo credits.
Documented allowance
$5 promotional credit, expiring 30 days after activation.
Before you connect
A valid payment method is required to receive the promotion. Usage pauses on exhaustion or expiry unless PayGo credits are separately purchased; the promotion does not automatically enroll the account in paid usage.
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.
t. * Add a valid payment method to receive a one-time $5 promotional credit. The credit expires 30 days after activation. You will not be charged or automatically en
a one-time $5 promotional credit. The credit expires 30 days after activation. You will not be charged or automatically enrolled in paid usage. API and Playground acce
r production use. Available by agreement. * Add a valid payment method to receive a one-time $5 promotional credit. The credit expires 30 days after activation.
Current public pricing describes metered hosted inference and optional paid monthly plans.
Documented allowance
No recurring free API allowance verified.
Before you connect
Pay per token; optional subscriptions bundle daily request quotas. Private deployment has separate GPU and deployment charges.
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.
odels Private Chutes Plans FAQ Model pricing Pay per token. No subscription, no minimum, no markup. All featured models run on confidential TEE compute. Estimate your cost Pick a workload.
A daily free compute allocation is documented. Model costs vary; some models require a paid billing method.
Documented allowance
10,000 Neurons per day across eligible models; this is compute usage, not 10,000 requests.
Before you connect
Paid Workers usage above the allocation is charged. Some models require Workers Paid or prepaid credits.
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.
e allocation allows anyone to use a total of 10,000 Neurons per day at no charge . To use more than 10,000 Neurons per day, you need to sign up for the Worke
Neurons per day $0.011 / 1,000 Neurons Note Some models require a paid billing method. This applies to @cf/moonshotai/kimi-k2.6 , @cf/moonshotai/kimi-k2.7-code , @cf/zai-org/g
Free evaluation keys and paid production keys are different access tiers.
Documented allowance
Trial keys are limited to 1,000 API calls a month, with endpoint-specific rate limits.
Before you connect
The free evaluation tier does not establish free production access. Newer model variants can have additional restrictions.
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.
n keys. Cohere offers two kinds of API keys: evaluation keys (free but limited in usage), and production keys (paid and much less limited in usage). You can create a trial or pro
uation keys (free but limited in usage), and production keys (paid and much less limited in usage). You can create a trial or production key on [the API key
on newer Chat model variants) are limited to 1,000 API calls a month. ## Chat API (per model) | Model | Trial rate limit | Production rate limit | | ---------
Metered API use deducts fees from topped-up or granted balance. A generally available recurring free API tier is not established by this pricing page.
Documented allowance
No free quota verified.
Before you connect
Token billing; granted balance is consumed first if present.
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.
Models & Pricing | DeepSeek API Docs Skip to main content DeepSeek API Docs Resources Integrations API Sta
ts, please refer to Rate Limit & Isolation . Deduction Rules The expense = number of tokens × price. The corresponding fees will be directly deducte
ing fees will be directly deducted from your topped-up balance or granted balance, with a preference for using the granted balance first when both balances are available.
The pricing table includes free-tier access for selected models and operations. It does not make every Gemini model free.
Documented allowance
Model and project limits apply. Exact remaining quota requires checking the provider account.
Before you connect
Free-tier pricing rows disclose use of data to improve products. Check the provider terms, model row and regional eligibility before sending data.
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.
Note: Gemini 4 Argon is not available on the Free tier or on the Google AI Pro plan. Standard Free Tier Paid Tier, per 1M tokens in USD Input pr
Gemini Developer API pricing Start building free of charge with generous limits, then scale up with prepaid and pay-as-you-go pricing for your produ
Google AI Studio access check_circle Content used to improve our products * Get started for Free Paid For production applications that require higher volumes and a
A free plan is documented with separate per-model request and token limits.
Documented allowance
Limits vary by model and organization. Request limits and token limits can be reached independently.
Before you connect
The current account limits are authoritative. Reaching a limit returns HTTP 429; an upgrade has separate terms.
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.
r select workloads and enterprise use cases. Free Plan Limits Developer Plan Limits MODEL ID RPM RPD TPM TPD ASH ASD canopylabs/orpheus-arabic-saudi 10
s your rate limits. Rate limits apply at the organization level, not individual users. You can hit any limit type depending on which threshold you reach
en you exceed rate limits, our API returns a 429 Too Many Requests HTTP status code. Note : retry-after is only set if you hit the rate limit and status cod
The current Inference Providers documentation requires free accounts to purchase credits or upgrade. Included monthly credits belong to paid subscriptions.
Documented allowance
No included credits for free users. PRO, Team and Enterprise subscriptions include monthly compute credits.
Before you connect
This record is not a free inference offer. Provider routing, purchased credits and subscription billing have separate costs.
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.
hly credits to use with Inference Providers. Free users can use Inference Providers by purchasing credits, or by upgrading to [PRO](https://huggingface.co/subscribe/pro): | Account Type | Monthly
om Hugging Face. ## Included Monthly Credits PRO users and Team or Enterprise organizations receive monthly credits to use with Inference Providers. Free users can use Inference Providers by purchasing cre
Although Kilo includes a coding client, its separately documented AI Gateway exposes free hosted models through an API.
Documented allowance
Free models: 200 requests/hour/IP, for authenticated and anonymous requests.
Before you connect
Anonymous access is limited to free models. Upstream free-model availability and restrictions vary; some models require data collection.
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.
restrictions, and per-user spending limits. Anonymous access The gateway allows unauthenticated access for free models only. Anonymous requests are id
limits. Anonymous access The gateway allows unauthenticated access for free models only. Anonymous requests are identified by IP address and are subject to rate limiting (200 re
IP address and are subject to rate limiting (200 requests per hour per IP). Free models include models tagged with :free in their model ID, such as minimax/minimax
Default Free mode is documented with the lowest API limits, intended for evaluation and prototyping.
Documented allowance
Requests per second, tokens per minute and tokens per month are limited. Exact limits depend on the account and model.
Before you connect
Free-mode evaluation and paid API usage are distinct. API limits are organization-wide and separate from the Vibe coding-plan budget. Inspect the current account limits before use.
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.
n cap. A 429 means you exceeded one of them. Free mode (the default) has the lowest limits, intended for evaluation and prototyping. 🔎 See your current limits, usage, and tier on the Limits page of the Admin panel. How li
limits depend on your plan and usage tier : Free mode (default) : limited limits for testing and prototyping. Pay-as-you-go : unlocks Tier 1 and above. With pay-as-you-go, tiers upgrade automatically
Current Token Factory billing documentation grants a short initial trial credit and requires a bank card during onboarding.
Documented allowance
$1 trial credit valid 30 days.
Before you connect
Billing account setup and bank card mandatory. Subsequent consumption uses paid billing.
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.
create a billing account during onboarding. Billing setup is mandatory—you cannot complete onboarding without it. Setting up a billing account requires a bank c
ing without it. Setting up a billing account requires a bank card. You can view and update your billing details at any time on the Billing page. Upon first
lling page. Upon first sign-up, you receive \$1 in trial credit, valid for 30 days. * ## Payment methods ### Bank card If your payment method is a bank card, you can manual
Developer Program members receive hosted NIM API access for prototyping and testing.
Documented allowance
The inspected FAQ does not give a hosted API request or token allowance.
Before you connect
Developer membership is required. Hosted developer access is for research, prototyping, development and testing; the separate 90-day enterprise trial must not be confused with a recurring API quota.
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.
Members of the NVIDIA Developer Program have free access to NIM API endpoints for prototyping, and to downloadable NIM microservices for research, application development, and experim
through the NVIDIA Developer Program is for prototyping, research, development and testing purposes only and does not include enterprise features or support. What does “production” mean? Product
Free accounts receive starter cloud usage that refreshes monthly, with purchased usage credits available separately.
Documented allowance
The Free starter credit amount is unspecified. Free includes one concurrent request and access to a smaller starter model selection.
Before you connect
Free usage resets monthly from signup. Buying credits unlocks all models. Unused included usage does not roll over. Unlimited local execution uses the user's hardware and is separate from cloud access.
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.
usage credits. Includes: Run models locally Starter usage credits included Includes access to starter models Add credits to unlock all models No service fees Downlo
cription started, including on annual plans. On the Free plan, usage resets monthly from the date you signed up. Does unused included usage roll over to the next month? No.
ed multiple requests running simultaneously. Free includes 1 concurrent request, Pro 3, and Max and Team 10. Requests beyond your plan's concurrency limit are queued and
Zen documentation redirects to OpenCode Console, which lists temporary free models alongside its prepaid inference offering.
Documented allowance
Selected models are temporarily free; no universal request or token quota is published in this source.
Before you connect
The general Console setup instructs users to add billing details and credits. Free model availability is temporary and model-specific; some free providers can use collected data to improve models. Auto-reload may purchase credits unless disabled.
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.
tion); we don’t charge anything beyond that. Free models DeepSeek V4.1 Flash Free is free on OpenCode for a limited time. Its provider follows a z
hat. Free models DeepSeek V4.1 Flash Free is free on OpenCode for a limited time. Its provider follows a zero-retention policy and does not use your data for model traini
question types and response fields. Pricing Console uses pay-as-you-go pricing. Below are the prices per 1M tokens . Model Input Output Cached Read Cached Write Big Pic
Free model variants are documented separately from paid models and paid credit purchases.
Documented allowance
Free models have low rate limits; the purchased-credit tier can change the allowance. Check the current limits page.
Before you connect
Provider privacy settings and model availability apply. Credit purchases and automatic top-ups are separate paid actions.
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.
on](/docs/api_reference/authentication). For free models, rate limits are determined by the credits that you have purchased. If you have purchased
) available on OpenRouter. These models have low rate limits ({FREE_MODEL_NO_CREDITS_RPD} requests per day total) and are usually not suitable for pro
RPD} requests per day total) and are usually not suitable for production use. If you have purchased at least {FREE_MODEL_CREDITS_THRESHOLD} credits, the free models w
The service documents free model testing in a sandbox or through the API alongside token-billed production usage.
Documented allowance
Free model testing is documented. No ongoing free authenticated token allowance is established by this source.
Before you connect
Treat the free offer as model testing. Authenticated API use has token-based billing. Public Cloud promotional vouchers have separate eligibility and terms and are not evidence of an ongoing free quota.
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.
sparent model version management. Playground Test all our models for free in a sandbox or via the API. Our integrations The AI Endpoints ecosystem is expanding as it adds new native integratio
wide selection of generative AI models with token-based billing. View the catalogue of models View prices Benefits Benefits Functionality Functionality I
Accounts without a linked payment method receive a recurring, restricted API tier on listed models. Linking payment moves the account to Developer.
Documented allowance
Listed free models: 20 requests/minute, 20 requests/day and 200,000 tokens/day per model.
Before you connect
Only models in free table; preview models are restricted to evaluation and experimentation.
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.
a few different rate limit tier offerings: * Free Tier: Applied when there is no payment method linked with your account * Developer Tier: Applied when a payment method is linked with your account For higher ra
equests per minute * RPD: Requests per day * TPD: Tokens per day (Free tier only) ## Basics * A request is defined by a call to the SambaNova API * You can hit either limi
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.
An older official trial offer and current indexed pricing information differ. Current terms need reconciliation; no numerical credit offer is published.
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.