---
title: "MongoDB Atlas Embedding and Reranking API free inference"
description: "A finite allowance for new accounts; it does not recur."
canonical_url: "https://freeinferencing.com/provider/mongodb_atlas_embedding_reranking/"
md_url: "https://freeinferencing.com/provider/mongodb_atlas_embedding_reranking.md"
last_updated: "2026-10-06"
---

# MongoDB Atlas Embedding and Reranking API

> A finite allowance for new accounts; it does not recur.

## Classification

- **Directory:** Current
- **Free access:** One-time trial
- **Status:** Available now
- **Confidence:** High
- **Payment card:** No
- **Account:** Required
- **Equivalent paid value:** $234.00 once
- **API endpoint:** `https://ai.mongodb.com/v1`

## Models mentioned

- `voyage-4-large`
- `voyage-4`
- `voyage-4-lite`
- `voyage-code-4`
- `voyage-context-4`
- `voyage-finance-2`
- `voyage-law-2`
- `voyage-code-2`
- `rerank-3`
- `rerank-3-lite`
- `voyage-multimodal-3.5`
- `voyage-3-large`
- `voyage-3.5`
- `voyage-3.5-lite`
- `voyage-code-3`
- `voyage-context-3`
- `voyage-multimodal-3`
- `rerank-2`
- `rerank-2-lite`
- `rerank-2.5`
- `rerank-2.5-lite`

## Limits and terms

```yaml
requests_per_minute: 3
tokens_per_minute: 10000
allowance: One-time model-specific token/pixel grants; no published
  replenishment or expiry.
free_token_millions_by_model:
  voyage-4-large: 200
  voyage-4: 200
  voyage-4-lite: 200
  voyage-code-4: 200
  voyage-context-4: 200
  voyage-finance-2: 50
  voyage-law-2: 50
  voyage-code-2: 50
  rerank-3: 200
  rerank-3-lite: 200
multimodal_grant:
  model: voyage-multimodal-3.5
  tokens: 200000000
  pixels: 150000000000
```

## What happens to your prompts?

**Not private.** The governing Cloud Terms permit AI-input training unless an eligible card-backed account opts out; the no-card trial cannot opt out.

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: reviewed
  plan_scope: No-card Atlas embedding/reranking trial; not database auto-embedding
    or paid opt-out access.
  prompt_retention: Direct API inputs are collected for model improvement; public
    documents do not give a fixed content-retention period.
  response_retention: No separate model-output retention period published.
  ordinary_logging: Usage tracked by model key, organization and project.
  model_training: Permitted by default; free-tier accounts are ineligible for the
    training opt-out.
  product_improvement: Direct API input collection supports model improvement.
  human_or_operator_access: DPA requires confidentiality for personnel with
    access; no free-tier no-access promise.
  subprocessors_and_routing: MongoDB Cloud subprocessors; the free unscoped
    endpoint does not guarantee EU-only processing.
  deletion_controls: Privacy/DPA rights apply; disabling future training
    collection requires an eligible payment method.
privacy_caveat: The free no-card tier cannot disable collection for model
  training; an eligible payment method is required to opt out.
agreements:
  terms_of_service: https://www.mongodb.com/legal/terms-and-conditions/cloud
  privacy_policy: https://www.mongodb.com/legal/privacy/privacy-policy
  data_processing_addendum: https://www.mongodb.com/legal/data-processing-agreement
  acceptable_use_policy: https://www.mongodb.com/legal/acceptable-use-policy
```

## Eligibility

```yaml
account_required: true
payment_method_required: false
database_cluster_required: false
regional_endpoint_restriction: US/EU-scoped endpoints require paid usage tier 1;
  the no-card trial uses the unscoped endpoint.
```

## API compatibility and modalities

- **Compatibility:** Voyage Embeddings, Voyage Multimodal Embeddings, Voyage Rerank
- **Modalities:** Embeddings, Reranking


## Before you build with MongoDB Atlas Embedding and Reranking API

### Read the classification narrowly

This record describes the bounded offer supported by evidence on 2026-10-06; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every account and region. “One-time trial” 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 21 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 **Not private** because The governing Cloud Terms permit AI-input training unless an eligible card-backed account opts out; the no-card trial cannot opt out. 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 8 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

- [Atlas Embedding and Reranking API billing](https://www.mongodb.com/docs/voyageai/management/billing/): Official Pricing
- [Atlas model API endpoints and no-card limits](https://www.mongodb.com/docs/voyageai/api-reference/overview/): Official Docs
- [MongoDB Cloud Terms, section 4(d) AI Features](https://www.mongodb.com/legal/terms-and-conditions/cloud): Official Terms
- [Atlas organization model-training opt-out eligibility](https://www.mongodb.com/docs/atlas/tutorial/manage-organization-settings/): Official Docs
- [MongoDB Privacy Policy](https://www.mongodb.com/legal/privacy/privacy-policy): Official Privacy
- [MongoDB Cloud DPA](https://www.mongodb.com/legal/data-processing-agreement): Official Dpa
- [MongoDB Acceptable Use Policy](https://www.mongodb.com/legal/acceptable-use-policy): Official Aup
- [Atlas per-model grants](https://www.mongodb.com/docs/voyageai/management/rate-limits/): Official Docs

## Sitemap

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