GDPR-compliant models for your agent

AI Agent Token Plan for OpenClaw & Hermes Agent

Connect OpenClaw and Hermes to DeepSeek, Qwen, Kimi, and more with one European AI API.

Integration

Up and running in five minutes.

Your agent stays exactly as-is. Point it at LLMBase for a wider model choice through a European-operated API boundary.

# OpenClaw → Settings → Providers → Add custom provider

Provider type:  OpenAI-compatible
Name:           LLMBase
Base URL:       https://llmbase.ai/api/v1/agents
API Key:        llmbase_chat_...

# Then pick a model from the LLMBase model catalog, e.g. moonshotai/kimi-k3

# Hermes → Settings → AI Provider → Custom

# Hermes' default reasoning_effort: medium is accepted for compatible models.

model:
  provider: llmbase
  model: moonshotai/kimi-k3
  base_url: https://llmbase.ai/api/v1/agents
  api_key: llmbase_chat_...
  api_mode: chat_completions

custom_providers:
  - name: llmbase
    base_url: https://llmbase.ai/api/v1/agents
    api_key: llmbase_chat_...
    api_mode: chat_completions
    model: moonshotai/kimi-k3

Plans

The right capacity for your agent.

Chat and Agent API share the same included subscription budget.

Pro

Full AI power. Premium models. Advanced research tools.

$19/month

Professional included usage
Access to all AI Models
Web Search, Research, PDF exports
Up to 20 Workspaces
Generate more images
Advanced Reasoning
Max. privacy, no logs, EU-Servers
Use with Agents (OpenClaw & Hermes)

Subscribe for $19/month

Expert

For people replacing multiple AI subscriptions

$99/month

Everything in Pro
5x Pro included usage
Same models and per-request capabilities as Max
50 Workspaces
1 GB per Workspace
More included image generation
Research within included usage
Agent workflows within included usage

Subscribe for $99/month

Max

Highest usage

Twice Expert's included usage, with more workspace storage

$199/month

Everything in Expert
2x Expert included usage
Same models and per-request capabilities as Expert
100 Workspaces
5 GB per Workspace
More included image generation
Research within included usage
Agent workflows within included usage

Subscribe for $199/month

Available models

DeepSeek, Qwen, Kimi.
The right model for every task.

Every model accessible from your agent. Switch models mid-workflow — no reconfiguration needed.

Model	Context	Included
Kimi K3 moonshotai/kimi-k3	1M	Included
GLM 5.2 z-ai/glm-5.2	1M	Included
Kimi K2.7 Code moonshotai/kimi-k2.7-code	256K	Included
MiniMax M3 minimax/minimax-m3	512K	Included
DeepSeek V4 Pro deepseek/deepseek-v4-pro	1M	Included
DeepSeek V4 Flash deepseek/deepseek-v4-flash	1M	Included
Qwen3.6-35B-A3B qwen/qwen3.6-35b-a3b	256K	Included
Kimi K2.6 moonshotai/kimi-k2.6	256K	Included
Qwen3.5 397B A17B qwen/qwen3.5-397b-a17b	256K	Included
FLUX 2 Klein black-forest-labs/flux.2-klein-4b	—	Included
Qwen3 Embedding 8B qwen/qwen3-embedding-8b	31K	Included
Qwen3-VL-30B-A3B-Instruct qwen/qwen3-vl-30b-a3b-instruct	256K	Included
gpt-oss-120b openai/gpt-oss-120b	128K	Included
gpt-oss-20b openai/gpt-oss-20b	128K	Included

Processing location depends on the selected model and available infrastructure.

Agent docs

Frequently Asked Questions

Does my agent keep working the same way?

Yes. You only change the base URL and API key in your OpenClaw or Hermes config. Your workflow, prompts, and tools stay exactly as they are.

When does Pro make sense vs. pay-per-use?

Pro makes sense if you already use LLMBase Chat daily — you get agents on top for a flat fee and always know your monthly cost. Pay-per-use wins for pure API usage, high volume, or when you need exact per-token accounting.

Which key do I give to OpenClaw or Hermes?

Create a chat agent key (llmbase_chat_...) in the dashboard and paste it into OpenClaw or Hermes. Your account login and inference API keys stay private and separate.

What happens when the included budget is used?

Your agent receives a budget error and pauses. For separate pay-per-use API billing, use a normal Inference API key.

LLMBase Agents