# Anthropic

> Use your own Anthropic API key with ShopAssist, and the options for EU processing of Claude models.

Source: https://shopassist.coec.dk/docs/ai/anthropic · Updated 2026-10-01

## Create a key [#create-key]

As of October 2026, in the Anthropic Console:

1. Open **console.anthropic.com → Settings → Workspaces** and create a workspace for ShopAssist (optional, for separate limits).
2. Open **API keys → Create key**, choose the workspace and copy the key (`sk-ant-…`).
3. Set up billing under **Plans & billing** and a spend limit.

## Account tier [#tier]

Any paid API plan. Low tiers have strict rate limits; ShopAssist reports `rate_limited` when you hit them.

## Recommended models [#models]

| Model | Id | Tier | Context window | Images | Processing |
| --- | --- | --- | --- | --- | --- |
| Claude Haiku 4.5 | `claude-haiku-4-5` | Premium | 200,000 tokens | Yes | global/US |
| Claude Opus 5.5 | `claude-opus-5-5` | Premium | 200,000 tokens | Yes | global/US |
| Claude Sonnet 5 | `claude-sonnet-5` | Premium | 200,000 tokens | Yes | global/US |

## Fields [#fields]

| Field   | Notes                                                |
| ------- | ---------------------------------------------------- |
| API key | `sk-ant-…`                                           |
| Model   | A model from the list or any current `claude-` model |

## Data location [#data-location]

> **Data location:** Anthropic's API processes data globally or in the US; there's no EU option. For EU processing use Claude on Google Vertex AI (EU) or Amazon Bedrock (EU) under your own cloud account.

## Connection test [#probe]

| Check | Required | What it tests | On failure |
| --- | --- | --- | --- |
| `auth` | Yes | The key is accepted (lists models or sends a tiny request) | `auth_failed`, `insufficient_quota`, `gemini_free_tier`, `endpoint_blocked`, `provider_unavailable`, `model_not_found` |
| `tools` | Yes | The model calls a tool with valid arguments and continues after the result | `tools_unsupported`: the model can't run the shopping tools |
| `ttft` | No (degraded) | The first answer event arrives within 8 seconds | `ttft_slow`: works, but shoppers wait |
| `parallel_tools` | No | Two tools are called in one step | `parallel_tools_unsupported`: slightly slower answers |
| `vision` | No | The model names the colour of a test image | `vision_unsupported`: visual search is off |
| `context` | Self-hosted only | A fact at the start of an 8,000-token prompt is recalled | `context_too_small`: the endpoint truncates prompts |

## Cost [#cost]

Estimate based on list prices on 2026-09-28; your provider bills you directly.

| Provider | Model | USD per 1,000 conversations | ≈ EUR per 1,000 conversations |
| --- | --- | --- | --- |
| Azure OpenAI | GPT-6 Luna | $3.61 | €3.10 |
| Mistral | Mistral Small 4 | $4.71 | €4.05 |
| OpenAI | GPT-5.6 Luna | $7.62 | €6.55 |
| Google Gemini | Gemini 3.1 Flash-Lite | $8.85 | €7.61 |
| OpenAI | GPT-5 mini | $9.85 | €8.47 |
| Google Gemini | Gemini 3.5 Flash-Lite | $12.02 | €10.34 |
| Mistral | Mistral Large 3 | $14.70 | €12.64 |
| OpenAI | GPT-5.4 mini | $26.55 | €22.83 |
| Anthropic | Claude Haiku 4.5 | $36.10 | €31.05 |
| Anthropic | Claude Sonnet 5 | $72.20 | €62.09 |

## Troubleshooting [#troubleshooting]

* **401 / `auth_failed`:** the key was disabled; create a new one.
* **`insufficient_quota`:** add credit or raise the spend limit in **Plans & billing**.
* **`rate_limited`:** request a higher tier, or add a [fallback](/docs/ai/byok#fallback).
* **`model_not_found`:** check the model id; older Claude models are retired on Anthropic's schedule.