GW2 Account Analyzer — Help

← Back to Analyzer

This page explains how to get a free (or low-cost) API key for each AI provider supported by GW2 Account Analyzer.

Google Gemini (Easiest — use your Google account)

Most people already have a Google account, so this is the fastest way to get started.

  1. Go to aistudio.google.com and sign in with your Google account.
  2. Click Get API Key → Create API Key.
  3. Gemini offers a free tier (60 requests/min on Gemini 1.5 Flash).
  4. Select Gemini in the provider dropdown and paste your key.
  5. Recommended: gemini-1.5-flash (free) or gemini-1.5-pro (paid, higher quality).

Groq

Groq is the fastest provider — responses often stream in under 5 seconds.

  1. Go to console.groq.com and sign up with Google or GitHub.
  2. Navigate to API Keys and click Create API Key.
  3. Groq is free during the preview period with generous rate limits.
  4. Select Groq in the provider dropdown and paste your key.
  5. Recommended models: llama-3.3-70b-versatile or mixtral-8x7b-32768.

GLM / Z.ai (Zhipu AI — European platform)

GLM offers generous free-tier credits and fast responses.

  1. Go to bigmodel.cn and register an account.
  2. If you are in Europe, switch to the European platform at z.ai — use the same login.
  3. Navigate to API Keys in the console and create a new key.
  4. New accounts receive free credits valid for 1 month.
  5. In the app, select GLM / Z.ai as the provider and paste your key.
  6. Click Load Models to fetch the current list — recommended models are glm-4-flash (fast, free) and glm-4-plus (higher quality).

Note: The European Z.ai endpoint (api.z.ai) is used automatically. Do not use the CN endpoint if your account is on Z.ai.

Mistral

  1. Go to console.mistral.ai and create an account.
  2. Navigate to API Keys and generate a new key.
  3. New accounts receive €5 free credits.
  4. Select Mistral as the provider and paste your key.
  5. Recommended: mistral-large-latest for best results.

Cerebras

Cerebras runs models on custom wafer-scale chips — extremely fast inference.

  1. Go to cloud.cerebras.ai and sign up.
  2. Navigate to API Keys and create a key.
  3. Cerebras is free during early access with rate limits.
  4. Select Cerebras as the provider and paste your key.
  5. Recommended: llama3.1-70b.

OpenRouter

OpenRouter is a meta-provider that gives you access to 100+ models from one key, including free models.

  1. Go to openrouter.ai and sign in with Google or GitHub.
  2. Navigate to Keys and create a new key.
  3. Many models (including Llama 3, Gemma, Mistral) are completely free on OpenRouter.
  4. Select OpenRouter as the provider and paste your key.
  5. Click Load Models to see all available models — free models show (free) in their name.

Anthropic (Claude)

Claude gives the highest-quality analysis with extended reasoning.

  1. Go to console.anthropic.com and create an account.
  2. Navigate to API Keys in the left sidebar and click Create Key.
  3. New accounts receive $5 of free credits — enough for dozens of analyses.
  4. Copy your key (starts with sk-ant-…) and paste it into the AI API Key field.

Recommended model: Claude Opus 4.6 (selected automatically)

OpenAI

  1. Go to platform.openai.com and create an account.
  2. Navigate to API Keys and click Create new secret key.
  3. New accounts receive $5 of free credits (valid 3 months).
  4. Select OpenAI as the provider and paste your key.
  5. Recommended: gpt-4o for best quality, gpt-4o-mini for lower cost.

Which provider should I choose?

ProviderSpeedQualityCost
Google GeminiFastGoodFree tier (easiest)
GroqVery fastGoodFree (preview)
GLM-4-FlashFastGoodFree credits
OpenRouterVariesVariesFree models available
CerebrasVery fastGoodFree (early access)
MistralMediumVery good€5 free
Anthropic (Claude)MediumExcellent$5 free then paid
OpenAIMediumExcellent$5 free then paid

For first-time users: Google Gemini is the easiest — just sign in with your Google account. Groq is the fastest free option.