---
title: "Ollama Cloud free inference"
description: "credits refresh on a published schedule. See verified limits, model IDs, privacy terms, and primary sources for Ollama Cloud."
canonical_url: "https://freeinferencing.com/provider/ollama_cloud/"
md_url: "https://freeinferencing.com/provider/ollama_cloud.md"
last_updated: "2026-09-19"
---

# Ollama Cloud

> credits refresh on a published schedule.

## Classification

- **Directory:** Current
- **Free access:** Monthly credits
- **Status:** Available now
- **Confidence:** High
- **Payment card:** No
- **Account:** Required
- **Equivalent paid value:** Not quantifiable
- **API endpoint:** `https://ollama.com/api`

## Models mentioned

- `kimi-k3`
- `minimax-m2.7`
- `mistral-large-3:675b`
- `glm-5.3-flash`
- `gpt-oss:120b`
- `nemotron-3-nano:30b`
- `minimax-m3`
- `qwen3.5:397b`
- `nemotron-3-ultra`
- `kimi-k2.6`
- `glm-5.3`
- `glm-5.2`
- `kimi-k2.7-code`
- `deepseek-v4-pro:0813`
- `deepseek-v4-flash:0731`
- `deepseek-v4.1-flash`
- `gemma4:31b`
- `glm-5.1`
- `gpt-oss:20b`
- `nemotron-3-super`

## Limits and terms

```yaml
concurrent_cloud_models: 1
recurring_starter_credit_amount: not_public
recurrence: monthly
reset: Monthly from the date the user signed up.
rollover: false
accounting: Token-priced usage consumes included credit; purchased credits
  unlock all cloud models after the included balance is exhausted.
transition: The former 5-hour session and weekly limits no longer apply.
```

## What happens to your prompts?

**Partially private.** Ollama says prompt and response data is never logged or trained on and requires no-logging, no-training, zero-data-retention partners, but partner selection, regional routing, human-access detail, and deletion controls are not fully enumerated for every starter model.

Privacy is audited separately from price. Review the current governing terms before sending sensitive or regulated data.

## Data governance and agreements

```yaml
data_governance:
  review_status: partial
  plan_scope: Ollama-hosted cloud models using the recurring monthly Starter
    credit on the Free plan; available routes and partner deployments can vary.
  prompt_retention: Ollama's current pricing disclosure says prompt data is never logged.
  response_retention: Ollama's current pricing disclosure says response data is never logged.
  ordinary_logging: Account, subscription, billing, security, and aggregate usage
    metadata may be processed; the public cloud disclosures do not enumerate
    every metadata field or retention period.
  model_training: Ollama says prompts and responses are never used for training
    and requires model partners to provide no-training terms.
  product_improvement: The reviewed Cloud disclosures do not grant a broad right
    to use prompt or response content for product improvement.
  human_or_operator_access: Prompt and response content is not retained for later
    operator review under the published no-logging rule; transient processing
    and account/usage administration still occur.
  subprocessors_and_routing: Ollama says it primarily uses dedicated compute in
    the United States and European Union, with Singapore currently limited to
    Qwen models, and requires model partners to provide no logging, no training,
    and zero data retention.
  deletion_controls: There is no retained prompt or response record to delete
    under the published content rule; account and usage-metadata deletion
    controls and retention schedules are not fully documented on the reviewed
    Cloud pages.
  caveat: The content guarantees are strong, but partner selection, model-specific
    regions, transient human-access controls, and account/usage-metadata
    handling are not enumerated for every Starter route, so the conservative
    classification remains partially_private.
```

## Eligibility

```yaml
account_required: true
payment_method_required: not_explicitly_documented
```

## API compatibility and modalities

- **Compatibility:** Ollama Native API
- **Modalities:** Model inference


## Before you build with Ollama Cloud

### Read the classification narrowly

This record describes the bounded offer supported by evidence on 2026-09-19; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every account and region. “Monthly credits” should be interpreted together with the Current directory placement, High confidence, No payment-card status, and the plan-specific sources below.

### Resolve the live model route

The snapshot records 20 model IDs. Match the exact ID against the provider's current catalog before using it in code because zero-price routes, aliases, context limits, and feature support can rotate while an older documentation page remains online.

### Match the quota to the workload shape

Translate the allowance into peak requests per minute, input and output tokens, concurrency, retries, and every daily or monthly ceiling that applies to the intended account. The first limit reached by the workload is the practical ceiling. A large token pool can still fail interactive bursts, and a high request limit can still fail long-context work. Include tool calls and retry traffic, test the largest realistic payload, and treat research, experimental, and community access as conditional on their eligibility and fair-use terms.

### Preserve billing and privacy boundaries

The recorded payment-card requirement is No, and account access is required. Confirm both in the live signup flow, set provider-side budgets when charges are possible, and observe the balance or usage fields after a complete request. The prompt-handling classification is **Partially private** because Ollama says prompt and response data is never logged or trained on and requires no-logging, no-training, zero-data-retention partners, but partner selection, regional routing, human-access detail, and deletion controls are not fully enumerated for every starter model. Re-read the terms for the exact route and plan before sending sensitive, regulated, or proprietary content.

### Follow the evidence, then re-check it

This record links 5 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest and most specific governing document or live catalog when sources disagree. A dated finding can become stale even when the page remains online, so retain the source and snapshot that supported the decision and submit a correction when a provider changes a material term.

### Plan fallback without policy drift

A fallback should preserve modality, context length, streaming, structured output, tools, safety controls, and data terms, not only API syntax. Decide which errors may retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. Rotating aliases and free pools can change behavior without changing the endpoint, so retain the response model field and test at least one substitute route before the primary offer becomes unavailable.

### Monitor the offer as a dependency

Capture the model ID, response model, rate-limit headers, usage fields, latency, HTTP status, and provider request identifier. Watch authorization failure, quota exhaustion, catalog removal, policy revision, and balance movement as separate failure modes. Re-check the live catalog and governing sources on a schedule proportionate to the workload's importance, and keep an owner and exit path for any production dependency on volatile free capacity.

### Test one complete request before scaling

Start with the smallest permitted request using the exact credential, model ID, endpoint, region, and account type intended for deployment. Record the status, headers, usage fields, response model, latency, and dashboard balance movement. Then exercise an invalid model, quota exhaustion, or rate limit so failure is explicit and cannot silently switch to a paid route. Validate streaming, structured output, and tool calls separately because a free model can expose fewer features than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and do not send sensitive data until the observed route matches the reviewed agreement.

## Primary sources

- [Ollama pricing](https://ollama.com/pricing): Official Pricing
- [Transparent token pricing and monthly credits](https://ollama.com/blog/transparent-pricing): Official Announcement
- [Ollama Cloud](https://docs.ollama.com/cloud): Official Docs
- [Hosted cloud catalog](https://ollama.com/api/tags): Live Catalog
- [Ollama primary repository](https://github.com/ollama/ollama): Official Repository

## Sitemap

See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.