Visibility in this ranking can be paid for. Payment moves a vendor's position within the
shortlist; it never adds a vendor, and it never changes a word of the review. The largest vendors in LLM API providers
cannot hold places 1 to 3. Places 1 to 3 go to challengers, vendors outside the best-known brands in a category,
wherever the category has them; the established names follow from place 4 in their ranked order. How it works: placement disclosure ·
editorial process.
The 12 tools, reviewed
#1 Scaleway Generative APIs
Serverless open-weight model endpoints from a Paris data center · France · scaleway.com
Zero retention by default Paris-hosted Free tier
Scaleway is the strongest answer here for a buyer whose first question is where the prompt goes. Its data-privacy page says a zero-retention policy applies by default, that the content of inputs and outputs is not read or reused, and that data is not used to train base models.
- Pricing: Usage-based. Billed per token on serverless endpoints with a free tier; dedicated deployments are available when a team wants isolation. Free plan: free plan.
- Best for: EU companies with data-residency duties
- Strengths: OpenAI-compatible Chat Completions and Responses APIs; Serverless endpoints in a Paris data center; Dedicated deployments.
Where it falls short
The catalog is a curated set of open-weight models, so a team that needs the newest closed models from OpenAI or Anthropic will not find them.
Wrong for
A team that must use a particular closed frontier model, or one that wants a gateway across many providers.
Visit Scaleway Generative APIs →
#2 OVHcloud AI Endpoints
Serverless open-model API from a French cloud provider · France · ovhcloud.com
French cloud No stored user data OpenAI specification
OVHcloud suits a company that already runs infrastructure with it and wants models inside the same account. The docs describe AI Endpoints as serverless and say user data is not stored, and that its LLM APIs follow the OpenAI specification, so existing client code works. The catalog lists open models such as gpt-oss, Llama and Qwen alongside embedding, speech and image models.
- Pricing: Usage-based. Billed on a Public Cloud project with a payment method; anonymous use is limited to 2 requests per minute per IP and model. Free plan: free plan.
- Best for: EU teams already on OVHcloud
- Strengths: OpenAI-specification LLM APIs; Playground in the console; Embedding models such as BGE.
Where it falls short
Authenticated limits are 400 requests per minute per project and model, and keys from projects in Discovery mode without a payment method cannot use the service. The playground caps output at 1,024 tokens.
Wrong for
A team that needs a wide closed-model catalog or large rate limits on day one.
Visit OVHcloud AI Endpoints →
#3 OpenRouter
A single API in front of 500+ models from 80+ providers · United States · openrouter.ai
Many models, one key Opt-in prompt logging EU in-region routing
OpenRouter takes third place because it removes the commitment that hurts most in this category: being tied to one model owner. The pricing page lists more than 500 models behind one key, and the standard plan adds routing preferences, budgets and caching.
- Pricing: Usage-based + platform fee. Pay as you go with a platform fee of 5.5% on the standard plan and 8% on Business. Free plan: free plan.
- Best for: Teams comparing models or needing failover
- Strengths: OpenAI-compatible endpoint; 500+ models from 80+ providers; Automatic fallbacks and provider selection.
Where it falls short
The fee on top of model cost grows with spend, 5.5% on standard and 8% on Business.
Wrong for
A company that must contract directly with its model maker, or one sending regulated personal data without paying for in-region routing.
Visit OpenRouter →
#4 Together AI
Open-weight model hosting with fine-tuning and dedicated capacity · United States · together.ai
Open-weight catalog Zero-retention switch Fine-tuning included
Together sits fourth because it is the plainest option for a team that wants open-weight models and a clean exit. Its docs describe an API compatible with the OpenAI REST API and SDKs across chat, completions, vision, image generation, speech and embeddings, so switching in takes a changed base URL.
- Pricing: Usage-based. Billed per million tokens with published per-model prices, cached-token discounts on some models, and dedicated capacity sold separately. Free plan: none.
- Best for: Developers on open-weight models
- Strengths: OpenAI-compatible REST API; Chat, vision, image, speech and embedding models; Cached-token pricing on selected models.
Where it falls short
The pages we read did not state where Together's inference runs, so a buyer with residency duties must ask.
Wrong for
A European company that needs a stated hosting country, or a non-technical team that wants a chat interface and no code.
Visit Together AI →
#5 OpenAI Platform
The maker's own API for GPT models, audio and images · United States · platform.openai.com
Reference API EU data residency Zero-retention eligible
As the vendor whose API format became the standard, OpenAI is a safe default for a team that wants its own models and wide tooling support, but a large incumbent cannot take a top-three place. Its data-controls page says API data is not used to train models unless the customer opts in.
- Pricing: Usage-based. Billed per token with separate input and output rates for each model; enterprise terms add residency and retention options. Free plan: none.
- Best for: Teams wanting the vendor's own models
- Strengths: Responses and Chat Completions endpoints; Embeddings, audio, image and moderation endpoints; Realtime API.
Where it falls short
Everything depends on one maker: model versions retire on its schedule, and a prompt tuned to one model rarely transfers unchanged.
Wrong for
A company whose legal team requires an EU-only supplier, or one that wants to change models freely.
Visit OpenAI Platform →
#6 Anthropic Claude API
The maker's own API for Claude models · United States · anthropic.com
Own models US-only inference option Zero-retention arrangement
Anthropic sits at sixth because its terms are short and direct: they say Anthropic may not train models on customer content from the services. The data-residency page lets a request be pinned with inference_geo to the US or left global, and workspaces can restrict which geographies are allowed.
- Pricing: Usage-based. Billed per token; US-only inference is priced at 1.1 times the standard rate on Claude 4.6 and later models. Free plan: none.
- Best for: Teams building on Claude models
- Strengths: Messages API; inference_geo setting (global or US); Workspace-level geo restrictions.
Where it falls short
The only geographies documented are global and US, and the only workspace geography is the US, so a buyer who needs processing inside the EU cannot get it from the first-party API on these pages.
Wrong for
A European company that must keep inference inside the EU, or a team wanting open-weight models it could later self-host. Mistral or Scaleway are the places to start.
Visit Anthropic Claude API →
#7 Fireworks AI
Fast open-model inference with prepaid credits · United States · fireworks.ai
Zero retention for open models Prepaid credits OpenAI-format calls
Fireworks earns a mid-table place on one strong sentence: its docs say it does not log or store prompt or generation data for any open model without explicit opt-in, and that data exists only in volatile memory for the length of the request. The privacy notice repeats that inputs are not used to train models without opt-in.
- Pricing: Usage-based (prepaid). Prepaid credits deducted per token, with Standard, Priority and Fast serving paths and a monthly spend limit option. Free plan: none.
- Best for: Latency-sensitive products on open models
- Strengths: OpenAI-compatible endpoint; Standard, Priority and Fast serving paths; Prepaid credits with auto reload.
Where it falls short
The zero-retention default covers open models only; the Responses API stores conversation data when store is true, which is its default.
Wrong for
A buyer who needs a closed frontier model or a stated hosting region in Europe.
Visit Fireworks AI →
#8 Groq
Very fast inference on custom hardware with a free plan · United States · groq.com
Fast inference Free plan No default retention
Groq's pitch is speed, and the docs back the privacy side: by default it does not retain customer data for inference requests, keeping only usage metadata. It lists text generation, transcription, speech output and image recognition on one platform, with prompt caching and structured outputs.
- Pricing: Usage-based. A free plan with rate limits and pay-as-you-go billing per token on paid usage, with batch jobs available. Free plan: free plan.
- Best for: Voice and real-time features
- Strengths: OpenAI-compatible base URL; Text, speech-to-text, text-to-speech and OCR models; Prompt caching.
Where it falls short
The model list is smaller than the gateways and cloud platforms, and some OpenAI features are unsupported. Inputs and outputs may be logged for up to 30 days when misuse triggers it, unless the customer opts out.
Wrong for
A buyer who needs the newest closed models or EU-based contracting.
Visit Groq →
#9 Mistral AI
French model maker with EU-hosted API and open-weight models · France · mistral.ai
EU-hosted by default Own open-weight models Batch discount
Mistral is a rare case of a model maker and a European contracting party in one. The privacy policy names a French company registered in Paris. Its help center states that data is hosted in the European Union by default, with a US API endpoint for those who choose it.
- Pricing: Usage-based + plans. A free plan, paid plans with monthly API credits, and pay-as-you-go credits beyond them. Free plan: free plan.
- Best for: EU teams wanting a European model maker
- Strengths: Chat and agent APIs; Open-weight and commercial models; OCR and speech transcription models.
Where it falls short
Abuse monitoring runs on the API unless zero data retention is activated, and the help center says data can be temporarily transferred outside the EU depending on the feature, to the sub-processors in its Trust Center.
Wrong for
A team that wants the broadest model choice behind one key, or one that insists on a specific closed model.
Visit Mistral AI →
#10 Google Gemini API
Google's own Gemini models via a free and paid API · United States · ai.google.dev
Free tier Context caching Batch discount
Google's API is the easiest place to start for free: the pricing page lists a free tier with free input and output tokens, and a paid tier with higher limits, context caching and batch pricing at half cost. The terms draw a hard line between tiers: on paid services Google says it does not use prompts or responses to improve its products, while the unpaid tier does.
- Pricing: Usage-based. A free tier of limited models, and a paid tier billed per million tokens with context caching and a 50 percent batch discount. Free plan: free plan.
- Best for: Prototypes and Google Cloud shops
- Strengths: Gemini models via REST and SDKs; OpenAI-compatible endpoint (beta); Context caching on paid tier.
Where it falls short
On the free tier, submitted content is used to improve Google products, and the terms limit use for audiences in the EEA, Switzerland and the UK to paid services only.
Wrong for
A European company sending personal data on a free key, or one needing a vendor other than a big platform.
Visit Google Gemini API →
#11 Cohere
Enterprise language, embedding and rerank models · Canada · cohere.com
Embeddings and rerank Trial key Canadian vendor
Cohere is the retrieval specialist of the list: chat models alongside embeddings, which fits a company building search over its own documents. A trial key is free but limited, and production keys bill per token, with input and output priced apart. A compatibility API at api.cohere.ai/compatibility/v1 covers chat completions, embeddings and audio transcription for the OpenAI client libraries.
- Pricing: Usage-based. A free trial key with limits, and production keys billed per token with different input and output rates. Free plan: free trial.
- Best for: RAG and search over company documents
- Strengths: Chat models; Embedding models; OpenAI compatibility API.
Where it falls short
The privacy policy says inputs and outputs on the platform are generally retained 30 days for enterprise users, and that trial and research inputs may be used for improvement after de-identification.
Wrong for
A team that needs zero retention without an enterprise contract, or one that wants the widest open-model choice.
Visit Cohere →
#12 Amazon Bedrock
Managed access to many makers' models inside AWS · United States · aws.amazon.com
AWS account Per-Region retention Third-party models
Bedrock suits a company whose procurement, identity and logging already live in AWS. Its documentation says model providers have no access to the accounts where models run, and therefore not to customer prompts or completions.
- Pricing: Usage-based. Billed through AWS per token by model and Region; the retention mode is set per Region at account or project level. Free plan: none.
- Best for: AWS shops needing one bill
- Strengths: Models from several makers; Messages, Chat Completions and Responses APIs; Retention modes: none, default, aws_review.
Where it falls short
Some models require retention for human review within the AWS boundary, up to 30 days, and zero retention for them needs approval through the AWS account manager. The setting is per Region and does not carry over.
Wrong for
A small team without AWS experience, or one that wants the maker's newest model on release day.
Visit Amazon Bedrock →
Questions and answers
What is the best LLM API provider in 2026?
Scaleway Generative APIs ranks first of 12, best for eU companies with data-residency duties. OVHcloud AI Endpoints is second (eU teams already on OVHcloud) and OpenRouter third (teams comparing models or needing failover). Places 1 to 3 go to challengers, vendors outside the best-known brands, wherever the category has them.
Is there a European alternative to the OpenAI API?
Yes, three in this list contract through French companies: Scaleway, Mistral AI and OVHcloud. Scaleway hosts its serverless models in a Paris data center and applies zero retention by default.
Can I switch providers without rewriting my code?
Often, for the basic chat call. OpenRouter, Together AI, Fireworks AI, Groq, Scaleway, OVHcloud, Cohere and Google all document an OpenAI-style endpoint where you change the base URL, key and model name.
Do these providers train on my prompts?
The pages we read say no by default for most, with exceptions worth knowing. OpenAI says API data is not used for training unless you opt in. Anthropic's terms say it may not train on customer content from the services.
How long do providers keep my requests?
It ranges from nothing to 30 days. Scaleway and Groq keep no inference content by default, with narrow misuse exceptions of up to two weeks and 30 days.
How is an LLM API priced?
By the token, with input and output counted and priced separately.
Which providers have a free tier?
OpenRouter offers more than 25 free models at 50 requests a day.
When does a gateway like OpenRouter make sense?
A gateway fits when you compare models often, want an automatic fallback during a provider outage, or prefer one invoice for many vendors.
Can I keep processing inside the EU?
Some can. Scaleway serves serverless models from Paris, Mistral hosts in the EU by default, OpenAI offers European storage and processing to eligible customers, and OpenRouter offers EU in-region routing on Business and Enterprise plans.
Should I use the model maker or a cloud platform like Bedrock?
The maker gets new models first and sells the clearest terms for its own models. A cloud platform makes sense when your company already buys, authenticates and logs everything in that cloud.
What breaks when a provider retires a model?
The model name in your code starts returning errors, or a replacement answers differently, so prompts tuned for the old model degrade. Makers such as OpenAI, Anthropic and Cohere retire their own versions on their own schedules.
