To connect Bluehost AI Credits to a self-installed OpenClaw, add a Custom Provider that points to https://gateway.ai.bluehost.com, select OpenAI-compatible (chat-completions) mode, enter your AI Credits API key, and use the exact model ID from Bluehost’s current model list. Then send a test message. If OpenClaw runs as Bluehost’s packaged Unmanaged VPS application, follow Bluehost’s separate, version-specific procedure instead, because its file paths, service user and restart steps differ.
Check which OpenClaw setup you run
Bluehost documents two deployment paths, and the steps below are not interchangeable.
- Self-installed OpenClaw: you installed OpenClaw yourself and configure it through the first-run onboarding flow or by editing
~/.openclaw/openclaw.json. Bluehost’s self-install guide was updated September 16, 2026. - Bluehost Unmanaged VPS application: OpenClaw was deployed from Bluehost’s packaged application. Bluehost’s guide targets OpenClaw 2026.8.2 (0965053), assumes root SSH access and a service user named
openclaw, and reads its environment from/etc/default/openclaw. That guide was updated September 23, 2026.
Do not mix the two. The packaged guide’s paths, service user and restart commands apply only to that deployment, and Bluehost directs self-install users to the other guide.
Connect a self-installed OpenClaw
- Connect to the server over SSH and run
openclawfor first-time setup. Follow the onboarding prompts until the workspace and gateway are initialized and you reach model-provider setup. - Choose More…, then Custom Provider.
- Enter
https://gateway.ai.bluehost.comas the API base URL, then enter your Bluehost AI Credits API key. OpenClaw offers both a paste option and an external secret-provider option. Use whichever keeps the key out of readable plain-text files on your installation. - Choose OpenAI-compatible (Uses /chat/completions). Bluehost says not to select the Responses-compatible or Anthropic-compatible options for this gateway.
- Enter the exact model ID from Bluehost’s AI Models and Credit Pricing listing. Model IDs quoted in tutorials, including this one, can go out of date, so copy the live ID from Bluehost.
- Complete setup after the verification prompt, then hand off to the agent and send a test message.
Edit openclaw.json on an existing self-install
If OpenClaw is already running, Bluehost’s self-install guide shows the same connection as a direct configuration change in ~/.openclaw/openclaw.json:
The Tool Desk
Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →#1 Best Overall
- Dell Precision 7920 Tower Workstation
- 2x Intel Xeon Gold 6130 16-Core 2.1GHz (3.7GHz Turbo)
- 192GB DDR4 Memory - upgradable to 1.5TB
- 2x 1TB SSD + 2x 4TB HDD (Removable Hot Swap Drive bays)
- Nvidia Quadro P1000 4GB - Windows 11 Professional 64-bit
- Add a provider entry named
bluehost-ai-creditsundermodels.providers. - Set its
apivalue toopenai-completions. - List your exact model ID under that provider.
- Set
agents.defaults.model.primarytobluehost-ai-credits/followed by that same model ID.
Bluehost presents this as a sample configuration. Check the field names against your installed OpenClaw version before saving the file, and restart OpenClaw afterward so the change is loaded.
Connect the Bluehost Unmanaged VPS application
This path is tied to OpenClaw 2026.8.2 (0965053). If your installed version differs, compare the guide’s steps with your version’s documentation before running anything.
Store the key in the service environment
Bluehost’s guide places the API key in /etc/default/openclaw, exports it for the setup shell and restarts the service. The service unit reads that file through an EnvironmentFile=-/etc/default/openclaw entry. The leading hyphen tells systemd to ignore the file if it is missing, so a missing or misnamed file does not stop the service from starting. The key simply will not be loaded, which typically shows up later as an authentication failure.
Rank #2
- [Local AI Inference & 70B Model Ready] Equipped with the AMD Ryzen 7 PRO 8845HS processor, NEXUS is engineered for heavy local AI workloads. With a full-size GPU bay, it runs 70B LLMs natively without an internet connection. Ideal for AI developers and tech enthusiasts who need private environment for coding and model testing.
- [132TB Mass Storage with ZFS Integrity] Features a hybrid storage architecture (3×NVMe + 4×3.5" HDD) supporting up to 132TB. Utilizing the enterprise-grade ZFS file system and ECC memory, it prevents data corruption and bit rot—a must-have for professional photographers and video editors safeguarding 4K/8K RAW footage.
- [OpenClaw-Driven Automation Workflow] The built-in OpenClaw execution layer allows complex automated tasks to be processed locally. Even when offline, your backup schedules and AI file organization continue seamlessly. Say goodbye to monthly cloud subscriptions and high latency.
- [Dual 10GbE & USB4 Ultra-Connectivity] Experience server-class speeds with dual 10GbE ports and a 40Gbps USB4 interface. It enables multi-user real-time collaboration on large project files directly from the NAS, ensuring zero-lag editing for creative studios and production teams.
- [Open-Source ZimaOS for Total Privacy] Running on the fully open-source ZimaOS, NEXUS ensures your data stays physically on-premise with no backdoors. It acts as a "Digital Fortress" for privacy-conscious families and small businesses who demand absolute data sovereignty.
Discover and merge the model list
The guide retrieves models from https://gateway.ai.bluehost.com/v1/models, filters the result to chat-capable models and merges them into the bluehost-ai-credits provider. Bluehost recommends repeating this step when new models are added, because the catalog changes.
Quick wins for a faster PC:
Repair Windows errors before they cause bigger problemsFix Now →Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Attach the key with SecretRef and restart
The guide attaches the API key through OpenClaw’s SecretRef flags, sets a default model and restarts the service. It also offers a config query that displays the loaded model list, which you can use to confirm the merge worked.
Two credential mistakes to avoid:
- Do not write a literal value such as
env:BLUEHOST_AI_CREDITS_KEYinto the provider JSON. That string does not resolve the environment variable. OpenClaw sends the text itself as the key, and the gateway can reject it with HTTP 401. - Do not paste the key directly into shell commands. It can remain in your command history.
Verify the connection
- Self-install: send an agent message and confirm that a response arrives and that the status line shows the custom provider and model you selected.
- Unmanaged VPS application: inspect the configured provider model list, then confirm the service restarted with the environment file and SecretRef in place.
Troubleshoot common failures
| Symptom | Likely cause | What to check |
|---|---|---|
| Onboarding verification fails | Wrong gateway URL, wrong API mode or model ID mismatch | The URL is https://gateway.ai.bluehost.com, the mode is OpenAI-compatible (/chat/completions), and the model ID matches Bluehost’s current catalog character for character. |
| HTTP 401 from the gateway on the VPS application | A literal environment-variable string was used as the key, or the variable never loaded | Re-attach the key with the SecretRef flags, confirm /etc/default/openclaw exists and contains the key, and restart the service. |
| A listed model fails when used | Some models in the gateway list may not yet be usable | Refresh the model list and try another chat model from Bluehost’s current catalog. |
| The agent responds, but not with the intended model | The default model still points elsewhere | Self-install: check agents.defaults.model.primary. VPS application: check the default model set in the packaged guide’s steps. |
Credits, eligibility and pricing
Bluehost describes AI Credits as a prepaid balance used through an AI Gateway and a single API key. Requests consume credits at model-specific rates, so the same number of requests can cost different amounts on different models. AI Credits are available on Self-Managed VPS and VDS plans, according to Bluehost’s AI Credits overview (updated September 16, 2026).
Rank #3
- Professional AI & Creator Workstation: AMD Radeon AI PRO R9700 GPU with 32GB GDDR6 is engineered for AI development, professional content creation, and compute-intensive workloads.
- Massive 32GB Memory Capacity: 32GB of GDDR6 memory on a 256-bit bus provides ample bandwidth for large AI models, 8K video editing, and complex 3D rendering.
- Advanced RDNA 4 with AI Accelerators: 64 Compute Units with 3rd Gen Ray Tracing and dedicated 2nd Gen AI Accelerators for groundbreaking AI performance and visual computing.
- Professional Blower Cooling: Efficient single blower design exhausts heat directly out of the chassis, ideal for multi-GPU workstation and server configurations.
- Enterprise-Grade Thermal Solution: Vapor chamber heatsink with industrial Honeywell PTM7950 thermal interface material ensures reliable cooling under sustained professional loads.
| Pack listed by Bluehost | Price | Effective price per credit |
|---|---|---|
| 500 credits | $5 | $0.010 |
| 1,000 credits | $10 | $0.010 |
| 5,000 credits | $50 | $0.010 |
| 10,000 credits | $100 | $0.010 |
These are the 2026 list prices in Bluehost’s overview, which warns that prices can change. Check the current figures under the AI Tooling tab in the Bluehost Portal. The $0.010 per-credit figure describes these packs only. It is not an estimate of what a particular OpenClaw workload will cost, since that depends on which models you call and how often.
Bluehost also states the following balance rules:
- Credits are prepaid, not a recurring subscription.
- A balance expires 12 months after the most recent purchase.
- A new purchase resets the 12-month window for the entire balance.
- Unused credits are non-refundable.
Confirm the current product terms in the portal before buying.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
