Less waiting. More coding.
One API for the best open-weight coding models — auto-upgraded as better ones ship. Simply drop in to Claude Code, Cursor or Codex. Compatible with the Anthropic and OpenAI formats.
Same tools. Better price. Better performance. Your data stays in the EU.
Not sure yet? See our Comparison and Pricing Plans
Three lines. Done.
Same formats, same tools — Claude Code, Cursor, Codex and the rest. Swap the endpoint, not your workspace.
BASE_URL=https://api.melious.ai/v1
API_KEY=sk-mel-...
MODEL_ID=<MODEL_ID>- Works with the OpenAI and Anthropic SDKs — no code changes
- 20+ tools supported out of the box
- Prefer a guided setup? The Melious CLI configures your tools for you.
More tokens. Spend less.
Simply get more for what you pay — see Melious compared to Claude.
| Metric | Claude Max 5x | Melious Basic | Claude Max 20x | Melious Pro | Melious Unlimited 3x |
|---|---|---|---|---|---|
| Price | 99 € | 49 € | 199 € | 149 € | 499 € |
| Tokens | ≈250M | >500M | ≈1B | >2B | Unlimited |
| Speed | 50–100 tok/s | Up to 250 tok/s | 50–100 tok/s | Up to 250 tok/s | Up to 250 tok/s |
| Concurrent requests | Unlimited | Unlimited | Unlimited | Unlimited | 3 |
| Agents allowed | No | Yes | No | Yes | Yes |
Melious figures are read live from our billing and model pricing APIs. Claude figures are based on online public estimations.
Frontier models. Always updated.
What the coding plans include right now. When a better open-weight model ships, it joins the plan you already have.
GLM 5.3
ZAI
- Context
- 1M
- Speed
- 56 tok/s
-
GLM 5.3 Flash
ZAI
- Context
- 1M
- Speed
- 108 tok/s
DeepSeek V4.1 Flash
Deepseek
- Context
- 1M
- Speed
- 187 tok/s
-
DeepSeek V4 Flash 0731
Deepseek
- Context
- 1M
- Speed
- 273 tok/s
Find your fit.
Two ways to pay: token-based if your usage varies, concurrency-based if you have rather consistent workloads and don't want to think about usage.
Basic
For lightweight Coding workflows
>2× more tokens than Claude's 99 € plan
- Drop-in for Cursor, Codex, Claude Code and more
- Agents allowed
- EU-hosted
- No lock-in — cancel monthly
Current models
- GLM 5.3
- up to 700M tokens/month (Claude: ≈250M)
- GLM 5.3 Flash
- up to 6.5B tokens/month
- DeepSeek V4.1 Flash
- up to 6.5B tokens/month
Pro
For your daily coding workloads
>2× more tokens than Claude's 199 € plan
- Drop-in for Cursor, Codex, Claude Code and more
- Agents allowed
- EU-hosted
- No lock-in — cancel monthly
Current models
- GLM 5.3
- up to 2.5B tokens/month (Claude: ≈1B)
- GLM 5.3 Flash
- up to 25B tokens/month
- DeepSeek V4.1 Flash
- up to 25B tokens/month
Unlimited 3x
For power users
- Drop-in for Cursor, Codex, Claude Code and more
- Agents allowed
- EU-hosted
- No lock-in — cancel monthly
- 3 concurrent generations, no token limit
Current models
- GLM 5.3
- up to 1 concurrent generations
- GLM 5.3 Flash
- up to 2 concurrent generations
- DeepSeek V4.1 Flash
- up to 2 concurrent generations
Unlimited 6x
For power users
- Drop-in for Cursor, Codex, Claude Code and more
- Agents allowed
- EU-hosted
- No lock-in — cancel monthly
- 6 concurrent generations, no token limit
Current models
- GLM 5.3
- up to 2 concurrent generations
- GLM 5.3 Flash
- up to 4 concurrent generations
- DeepSeek V4.1 Flash
- up to 4 concurrent generations
This offer is intended exclusively for businesses as defined by § 14 BGB (German Civil Code) · all prices plus statutory VAT.
Testimonials
“We put Melious through a thorough hands-on test. With GLM 5.2 we measured more than 350 tokens per second, and a development task that used to take 45 minutes was done in about 7. It stayed stable throughout, entirely on European infrastructure, and our data is not used for training. That convinced us to integrate Melious as a provider in ALBERT | AI, the AI in agorum core pro.”
FAQ
- Every coding plan includes selected frontier open-weight models built and tested for agentic coding. When a better open-weight coding model ships, it's added to your plan automatically, at no extra cost.
- No. Set your base URL to api.melious.ai/v1 and use your Melious API key — anything OpenAI- or Anthropic-compatible works unchanged, which covers 20+ tools including Claude Code, Cursor, Codex and Cline. Prefer a guided setup? The Melious CLI configures your tools for you.
- Token-based plans (Basic, Pro) bill by how much usage your requests draw each month — good if your usage varies day to day. Concurrency-based plans (Unlimited 3x/6x) instead cap how many requests can run in parallel and remove the token ceiling — good if you have rather consistent workloads and don't want to think about usage.
- No, never. Your prompts, code and completions stay on European infrastructure and are never logged or used for training — ours or anyone else's.
- Yes — nothing is different here. Coding plans run on the exact same European infrastructure and jurisdiction guarantee as the rest of Melious: EU/EEA only, no US legal exposure, no exceptions for agentic traffic.