Models · Meta

Llama 3.3 70B, run in Paris by Scaleway.

Llama 3.3 70B is an open-weight model by Meta that works with text, released under the Llama 3.3 Community License. On Evanesca, Scaleway runs it in Paris: your prompts are processed in France, and Evanesca keeps no copy of them. If Scaleway does not answer, OVHcloud takes over, in Europe too.

Checked on 20 Oct 2026

Llama 3.3 70B

by Meta · Llama 3.3 Community License

Paris, France Checks 5/6

Input / M: €1.512
Output / M: €1.512
Quick question: €0.0011

Prices per million tokens, VAT included. Quick question: 300 tokens in, 400 out.

The model at a glance

Maker: Meta
Licence: Llama 3.3 Community License
Size: 70B parameters
Context: Not verified yet
Type: Text
Tool calling: Yes measured by a real call
Reasoning: —
Run by: Scaleway Scaleway SAS, Paris — iliad group, no US parent Fallback: OVHcloud
Where it runs: Paris, France
Checks: 5/6 · Security ✕ Passed: Licence, Provenance, GDPR, Benchmarks and Live test
Price: €1.512 per million input tokens · €1.512 per million output tokens VAT included; reasoning tokens count as output
Open weights: Yes published by the maker: an operator can run the model
Model card: huggingface.co/meta-llama/Llama-3.3-70B-Instruct

Where your prompts go

Here is the route of a message sent to Llama 3.3 70B, end to end. No call to the model leaves Europe: not as a backup, not when servers are busy.

From your browser to EvanescaEvanesca passes your message straight on to Scaleway. It stores neither the prompt nor the answer: both stay in memory only while the answer is written.
Scaleway, ParisScaleway runs Llama 3.3 70B in Paris, France. It is a French company with no US parent: out of the CLOUD Act's direct reach. Scaleway may keep and read requests that cause errors or look abusive, for up to 14 days (Scaleway's data privacy page).
Back to you, with its passportThe answer comes back with its passport: model, operator, country, and what was kept. Your history lives in your browser; about this message, Evanesca keeps only billing data — tokens and cost.

What it costs

€1.512 per million input tokens and €1.512 per million output tokens, VAT included. Three typical exchanges on Llama 3.3 70B:

COST OF AN EXCHANGE · VAT INCLUDED
Example	Tokens in	Tokens out	Cost
A quick question	300	400	€0.0011
A long document to summarise	15,000	800	€0.0239
A message late in a long conversation	40,000	2,000	€0.0635

€2 of credit covers about 1,800 quick questions on this model. Reasoning tokens count as output, so a model that thinks first can cost more than these examples. The exact cost of each answer shows under it. All prices.

Licence

The official model card is the reference.

Similar models

Same maker first, then the same type.

Germany (AKI.IO)

GLM-5.3

Zhipu / Z.ai · Text · checks 6/6

€3.024 · €9.24 / M tokens

Paris, France

DeepSeek V4 Flash

DeepSeek · Text · checks 6/6

€0.672 · €1.344 / M tokens

Paris, France

GLM-5.2

Zhipu / Z.ai · Text · checks 6/6

€3.024 · €9.24 / M tokens

Paris, France

GPT-OSS 120B

OpenAI · Text · checks 5/6

€0.252 · €1.008 / M tokens

Paris, France

Qwen3 235B

Qwen · Text · checks 5/6

€1.26 · €3.78 / M tokens

Every model, with its operator and where it runs

Frequently asked questions

Where does Llama 3.3 70B run on Evanesca?

In Paris, France, on Scaleway's servers. Scaleway is a French company with no US parent, so your prompts stay out of the CLOUD Act's direct reach. If Scaleway does not answer, OVHcloud takes over, in France too. No call to the model leaves Europe: not as a backup, not when servers are busy.

Does Evanesca keep what I send to Llama 3.3 70B?

No. The prompt and the answer stay in memory only while the answer is written, and your history lives in your browser; about your messages, Evanesca keeps only billing data — tokens and cost. Scaleway may keep and read requests that cause errors or look abusive, for up to 14 days (Scaleway's data privacy page).

How much does Llama 3.3 70B cost?

€1.512 per million input tokens and €1.512 per million output tokens, VAT included. A quick question — 300 tokens in, 400 out — costs about €0.0011. There is no subscription: credit starts at €2.

Can Llama 3.3 70B call tools?

Yes: a real call through Scaleway returned proper tool calls (function calling).

Which licence is Llama 3.3 70B under?

Which checks has Llama 3.3 70B passed?

5 of 6: Licence, Provenance, GDPR, Benchmarks and Live test. Missing: Security — not checked yet, or checked without meeting the pass mark. Its passport shows the same stamps; how each check works.

Does Meta see what I type?

No. Meta published the weights, and Scaleway runs them in France: your prompts go to Scaleway's servers, not to Meta.