Pricing

What Frontière AI costs: per token, prepaid, margin included

Frontière AI charges per token, with the margin already included, and no subscription. You top up a prepaid balance from €10 and every successful call draws it down; when the balance reaches zero, calls stop. The prices below are what you actually pay, shown at 100,000 tokens — the amount debited from your balance when your prompts consume that many.

All prices are per 100,000 tokens, in EUR, margin included.

Top up from €10
Pay per token
No subscription
Calls stop at zero

Prepaid, no subscription

There is no monthly plan and no card on file. You top up once (from €10) and use the balance until it runs out — no invoice at the end of the month, no surprise when attention drops. If the balance reaches zero, calls return HTTP 402 and nothing else happens.

Chat & reasoning models

Every chat model is billed by input and output tokens at its own rate. Reasoning models consume output tokens (at the output rate) while thinking, before any visible text.

ModelHosted viaPrice /100k inPrice /100k out
Qwen3 235B (instruct)qwen3-235bEU sovereign · scaleway€0.105€0.315
Qwen3.5 397B (multimodal)qwen3.5-397bEU sovereign · scaleway€0.084€0.504
GLM-5.2 (Zhipu/Z.ai)glm-5.2EU sovereign · scaleway€0.252€0.77
DeepSeek V4 Flash 0731 (1M context)deepseek-v4-flash-0731EU sovereign · scaleway€0.056€0.112
Llama 3.3 70Bllama-3.3-70bEU sovereign · ovhcloud€0.0898€0.0898
Qwen3.6 27B (multimodal)qwen3.6-27bEU sovereign · ovhcloud€0.0574€0.3878
Qwen3.5 9B (fast, budget)qwen3.5-9bEU sovereign · ovhcloud€0.014€0.0224
Qwen3 32Bqwen3-32bEU sovereign · ovhcloud€0.0112€0.0308
Qwen3 Coder 30Bqwen3-coder-30bEU sovereign · ovhcloud€0.0084€0.0322
Qwen2.5-VL 72B (vision)qwen2.5-vl-72bEU sovereign · ovhcloud€0.1232€0.1232
GPT-OSS 120B (OpenAI)gpt-oss-120bEU sovereign · ovhcloud€0.0112€0.0574
GPT-OSS 20B (OpenAI)gpt-oss-20bEU sovereign · ovhcloud€0.0056€0.0224
Mistral Small 3.2 24Bmistral-small-3.2-24bEU sovereign · ovhcloud€0.0126€0.0378
Kimi K3 (2.8T parameters, 1M context)kimi-k3fast access · modal€0.3654€1.8242
Muse Spark 1.1 (1M context)muse-spark-1.1fast access · openrouter€0.1512€0.5138
Muse Spark 1.2 (1M context)muse-spark-1.2fast access · openrouter€0.1512€0.5138
GLM-5.3 Flash (Zhipu/Z.ai)glm-5.3-flashfast access · openrouter€0.0098€0.0308
Qwen3.8 Max (2.4T, 1M context)qwen3.8-maxfast access · openrouter€0.2422€0.7252
Qwen3.8 27B (multimodal)qwen3.8-27bEU sovereign · ovhcloud€0.056€0.378
Qwen3.8 Flash (Qwen)qwen3.8-flashfast access · openrouter€0.0182€0.0574
DeepSeek R1 (671B MoE)deepseek-r1fast access · openrouter€0.0854€0.3024
DeepSeek V4 Pro (345B MoE)deepseek-v4-profast access · openrouter€0.1064€0.21
DeepSeek R1 (Distill Qwen 32B)deepseek-r1-distill-qwen-32bfast access · openrouter€0.0154€0.0616
DeepSeek R1 (Distill Qwen 14B)deepseek-r1-distill-qwen-14bfast access · openrouter€0.0098€0.0252
GLM-5.3 (Zhipu/Z.ai)glm-5.3fast access · openrouter€0.1694€0.532
Gemma 3 27B (Google)gemma-3-27bfast access · openrouter€0.0098€0.0546
DeepSeek V4.1 Flash (552B MoE, 1M context)deepseek-v4.1-flashfast access · modal€0.0182€0.0728

Embedding models

Embeddings are billed on input tokens only — an embedding produces no output tokens, so there is no output rate.

ModelDimensionsContextPrice /100k in
BGE-M3 (multilingual)bge-m310248k€0.0013no output rate
BGE Multilingual Gemma2bge-multilingual-gemma235848k€0.0013no output rate
Qwen3 Embedding 8Bqwen3-embedding-8b409641k€0.014no output rate

Every figure above is the client price — the provider cost passed through Frontière AI's margin — at the 100k display unit. This is the exact amount debited from your balance.

A curated selection, priced from verified costs

Each model entered the catalog only after we verified who serves it and at what real cost, through the provider's own API. The price you pay is always that verified cost plus the margin — the same function the billing engine uses, never a number retyped by hand on a page.

FAQ

Is there a free tier or trial period?

No. Frontière AI is prepaid only — there is no free tier and no trial period. You top up from €10 and pay per token from your balance.

How is a call billed exactly?

Token-exact, from the usage object the provider reports for your call: prompt tokens at the model's input rate, completion tokens (reasoning included) at the output rate. When a provider serves part of your prompt from its cache and reports it, those tokens are billed at the model's cheaper cache rate.

Can I top up any amount?

From €10 upward. There is no subscription and no card kept on file — you decide how much to prepay and stop whenever you want.

Why do I pay more than the provider's list price?

Frontière AI routes to OVHcloud, Scaleway or our own EU servers and bills a margin on each call — that is how the service is funded. The price shown on every page already includes it, so there is no hidden surcharge later.

Where are the prices shown in euros per 100k tokens?

That is the display unit for every human-facing page. The machine-readable catalog (GET /api/v1/models) and the JSON-LD express the same tariff at the market's larger reference scale, so the figure reads differently but the price is unchanged.

Know what you'll pay before you build

Top up €10, change two lines in your existing client, and call any live model in minutes.

Create an account