# EU LLM API prices compared

URL: https://munito.ai/compare/prices

The posted per-token prices of the EU and global open-model APIs, side by side, for the models that more than one of them serves. With the traps that make a rate card misleading.

This page puts the posted prices of the open-model APIs side by side, for the models that more than one of them serves. It names the currency each vendor quotes in, and it does not convert: an exchange rate moves, and a converted price reads as a promise.

Checked on 2026-11-07. Every vendor changes prices, so treat this as a starting point and confirm at the source before you plan a budget. Every source is linked at the foot of this page.

## DeepSeek-V4.1-Flash-1017

Per million tokens, input / cached input / output.

| Provider    | Price                     | Currency | Region        |
| ----------- | ------------------------- | -------- | ------------- |
| Munito AI   | 0.30 / 0.006 / 1.20 | USD | EU |
| Together AI | 0.30 / 0.006 / 1.20       | USD      | Not stated    |
| Fireworks   | 0.30 / — / 1.20           | USD      | Not stated    |
| Scaleway    | 0.60 / 0.12 / 1.80        | EUR      | Paris         |
| Mistral AI  | Not published             | —        | Not stated    |

Four platforms, one model, and the three that publish a figure in dollars publish the same figure. The difference is not the rate. It is whether the vendor will tell you which region ran the request.

## GLM-5.3-Flash

| Provider    | Price                  | Currency | Region        |
| ----------- | ---------------------- | -------- | ------------- |
| Munito AI   | 0.15 / 0.03 / 0.50 | USD | EU |
| Together AI | 0.15 / 0.03 / 0.50     | USD      | Not stated    |
| Fireworks   | 0.15 / — / 0.50        | USD      | Not stated    |
| Mistral AI  | Not published          | —        | Not stated    |

The same pattern: an identical rate, and a different answer on location.

## Qwen3.8-27B

| Provider  | Price                 | Currency | Region   |
| --------- | --------------------- | -------- | -------- |
| Munito AI | 0.20 / 0.11 / 2.70 | USD | EU |
| Blade     | 0.136 / — / 1.83      | EUR      | Europe   |
| OVHcloud  | 0.40 / — / 2.70       | EUR      | EU       |
| Scaleway  | 0.60 / — / 3.30       | EUR      | Paris    |

Blade's figure is a floor, not a price. Its rate card is explicit that an eligible model "follows its GPU class's hourly schedule" and can rise above the list rate; its published ceiling for this model is €0.21 / €2.76. Against that ceiling our fixed price is lower on both input and output.

## DeepSeek-V4-Flash

| Provider  | Price                 | Currency | Region   |
| --------- | --------------------- | -------- | -------- |
| Munito AI | 0.11 / 0.022 / 0.28 | USD | EU |
| Scaleway  | 0.40 / — / 0.80       | EUR      | Paris    |

## gpt-oss-120b, which we do not serve

| Provider    | Price            | Currency | Region     |
| ----------- | ---------------- | -------- | ---------- |
| OVHcloud    | 0.08 / 0.40      | EUR      | EU         |
| Together AI | 0.15 / 0.60      | USD      | Not stated |
| Fireworks   | 0.15 / 0.60      | USD      | Not stated |

A comparison page that only lists races you win is an advertisement. OVHcloud is the cheapest EU route to gpt-oss-120b, and our public catalogue does not carry that model at all. If it is the model you want, buy it there.

## Reading a rate card without being misled

**A list price is not a bill.** Four things move the number you actually pay, and none of them is on the headline row.

- **Cached input.** A long system prompt, repeated on every request, is most of the input bill. The cached rate on DeepSeek-V4.1-Flash-1017 is $0.006 per million tokens here, two orders of magnitude under the uncached rate. A vendor without a cached price is quoting you the expensive path.
- **The output ratio.** Output costs three to ten times input. A summariser and a reasoning agent on the same model have different economics, so price your own mix rather than the midpoint.
- **A floor is not a price.** A dynamic rate card quotes the cheapest hour. Ask for the ceiling, and for the history of what the rate actually was.
- **The currency.** EUR before tax and USD after are different numbers. We quote USD; Scaleway, OVHcloud and Blade quote EUR.

**A region costs nothing extra on an open model.** That is the single most useful finding on this page. On the two models where four platforms compete, the EU price and the unnamed-region price are identical. If a vendor charges a premium or a multiplier for a named region, that is a commercial choice, not a cost.

## Beyond the token

Three things in a bill are not tokens at all, and they are where budgets go wrong.

- **OCR.** We bill PDFs and images per page, at $0.0044 for the automatic model and $0.0022 for the fast path. Most rivals run OCR through a vision model and bill per token, which makes a document budget a guess. Mistral bills per 1,000 pages.
- **A flat fee.** Helmcode sells an API key, not tokens, from €399 a month. Above roughly a billion tokens a month on two models that is cheaper than any metre; below it, much more expensive. See the [Helmcode comparison](https://munito.ai/compare/helmcode).
- **GPUs by the hour.** Together AI lists an HGX H100 at $5.49 an hour and an HGX B200 at $8.99. That is a different product from an API, and the right one if you train.

## Where to go next

- [Our own prices, per model and per tier](https://docs.munito.ai/pricing)
- [The models we serve, with the price of each](https://docs.munito.ai/models)
- The comparisons in detail: [Scaleway](https://munito.ai/compare/scaleway), [OVHcloud](https://munito.ai/compare/ovhcloud), [Mistral AI](https://munito.ai/compare/mistral), [Blade](https://munito.ai/compare/blade), [Together AI](https://munito.ai/compare/together-ai), [Fireworks AI](https://munito.ai/compare/fireworks-ai), [Helmcode](https://munito.ai/compare/helmcode), [Nebius](https://munito.ai/compare/nebius)

## Sources

Checked on 2026-11-07: [OVHcloud AI Endpoints catalogue](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/), [Blade rate card](https://blade.sh/models/pricing/), [Blade hourly pricing](https://blade.sh/docs/hourly-inference-pricing/), [Together AI pricing](https://www.together.ai/pricing), [Fireworks AI pricing](https://fireworks.ai/pricing), [Helmcode pricing](https://helmcode.com/pricing), [Mistral AI pricing](https://mistral.ai/pricing), [Scaleway Generative APIs FAQ](https://www.scaleway.com/en/docs/generative-apis/faq/).

Scaleway's price page refuses an automated read, so its figures were recorded on 2026-10-22 from [its pricing page](https://www.scaleway.com/en/pricing/model-as-a-service/).

Munito AI prices apply from 2026-11-04 and come from [the model catalogue](https://docs.munito.ai/models).