---
title: "Albert API free inference"
description: "No-cost research and development inference across 10 models; not unrestricted production use."
canonical_url: "https://freeinferencing.com/provider/albert_api_france/"
md_url: "https://freeinferencing.com/provider/albert_api_france.md"
last_updated: "2026-09-19"
---

# Albert API

> No-cost research and development inference across 10 models; not unrestricted production use.

## Classification

- **Directory:** Current
- **Free access:** Research / development
- **Status:** Restricted access
- **Confidence:** High
- **Payment card:** Unknown
- **Account:** Required
- **Equivalent paid value:** At least $6.62/mo
- **API endpoint:** `https://albert.api.etalab.gouv.fr/v1`

## Models mentioned

- `openai/gpt-oss-120b`
- `mistralai/Mistral-Small-3.2-24B-Instruct-2506`
- `mistralai/Ministral-3-8B-Instruct-2512`
- `Qwen/Qwen3-Coder-30B-A3B-Instruct`
- `deepseek-ai/DeepSeek-V4-Flash`
- `openai/whisper-large-v3`
- `BAAI/bge-m3`
- `Qwen/Qwen3-VL-Embedding-8B`
- `BAAI/bge-reranker-v2-m3`
- `lightonai/LightOnOCR-2-1B`

## Limits and terms

```yaml
vector_storage_tokens: 300000
experiment_model_limits:
  - id: openai/gpt-oss-120b
    rpm: 10
    rpd: 1000
    tpm: 128000
    tpd: 1280000
  - id: mistralai/Mistral-Small-3.2-24B-Instruct-2506
    rpm: 50
    rpd: 1000
    tpm: 128000
    tpd: 2460000
  - id: mistralai/Ministral-3-8B-Instruct-2512
    rpm: 50
    rpd: 1000
    tpm: 128000
    tpd: 2460000
  - id: Qwen/Qwen3-Coder-30B-A3B-Instruct
    rpm: 50
    rpd: 1000
    tpm: 128000
    tpd: 2460000
  - id: deepseek-ai/DeepSeek-V4-Flash
    rpm: 50
    rpd: unlimited
    tpm: 246000
    tpd: unlimited
  - id: openai/whisper-large-v3
    rpm: 50
    rpd: 1000
  - id: BAAI/bge-m3
    rpm: 500
    rpd: 50000
  - id: Qwen/Qwen3-VL-Embedding-8B
    rpm: 50
    rpd: 1000
  - id: BAAI/bge-reranker-v2-m3
    rpm: 500
    rpd: 50000
  - id: lightonai/LightOnOCR-2-1B
    rpm: 50
    rpd: 1000
    tpm: 128000
    tpd: 2460000
```

## What happens to your prompts?

**Private.** Albert says conversation traces are not retained, request data is not sent to model vendors, and data is not used for vendor training on its sovereign self-hosted stack.

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: Albert experimental access on sovereign self-hosted routes for
    eligible French central-government users.
  prompt_retention: DINUM says no conversation traces are retained and request
    data is not sent to the Internet.
  response_retention: Conversation traces encompassing exchanges are not retained.
  ordinary_logging: Non-content request/account metadata fields and retention are
    not separately enumerated.
  model_training: User data is neither sent to model vendors nor used for their model training.
  product_improvement: No content-based improvement right is disclosed.
  human_or_operator_access: Persistent review is constrained by the no-trace
    statement; transient operational access is not described.
  subprocessors_and_routing: Models run on sovereign SecNumCloud-qualified
    Outscale infrastructure in France and data is not sent to model vendors.
  deletion_controls: No ordinary conversation copy should remain; metadata
    deletion controls are not documented.
```

## Eligibility

```yaml
account_required: true
eligible_users: French central-government civil servants
territorial_or_local_authorities_eligible: false
production_access: Partner or supported project; cofunding may apply.
```

## API compatibility and modalities

- **Compatibility:** OpenAI Compatible
- **Modalities:** Embeddings, Reranking, Speech / audio
- **Geography:** France

## Before you build with Albert API

### 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. “Research / development” should be interpreted together with the Current directory placement, High confidence, Unknown payment-card status, and the plan-specific sources below.

### Resolve the live model route

The snapshot records 10 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 Unknown, 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 **Private** because Albert says conversation traces are not retained, request data is not sent to model vendors, and data is not used for vendor training on its sovereign self-hosted stack. 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 7 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

- [Pricing and limits](https://ia.numerique.gouv.fr/outils-ia/albert-api/tarifs-et-limites/): Official Pricing
- [Models](https://ia.numerique.gouv.fr/outils-ia/albert-api/mod%C3%A8les/): Official Catalog
- [Swagger](https://albert.api.etalab.gouv.fr/swagger): Official API Reference
- [Territorial authorities](https://ia.numerique.gouv.fr/collectivit%C3%A9s-territoriales/): Official Eligibility
- [Secure infrastructure](https://ia.numerique.gouv.fr/outils-ia/albert-api/infrastructure-s%C3%A9curis%C3%A9e/): Official Security
- [GPT-OSS-120B endpoints](https://openrouter.ai/api/v1/models/openai/gpt-oss-120b/endpoints): Router Pricing
- [Albert API](https://ia.numerique.gouv.fr/outils-ia/albert-api/): Official Product

## Sitemap

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