Coding agents
Use Vultr Serverless Inference in Codex CLI, OpenCode, OpenClaw, pi and Hermes Agent, with the live model list, context windows and reasoning levels.
Each of these agents has a Vultr provider of ours: install it, set VULTR_, and pick a vultr/... model. Claude Code needs no plugin at all.
| Agent | Package | Speaks |
|---|---|---|
| Codex CLI | @vultr/model-provider-codex (npm) |
Responses |
| OpenCode | @vultr/model-provider-opencode (npm) |
Chat completions |
| OpenClaw | @vultr/model-provider-openclaw (ClawHub) |
Chat completions |
| pi | @vultr/model-provider-pi (npm) |
Chat completions |
| Hermes Agent | vultr/model-provider-hermes (GitHub) |
Chat completions |
| Claude Code | None: four environment variables | Messages |
What every provider does
- It reads the model list from
GET /v1/modelswhen the agent starts, so a new model shows up without an update. Listing needs no key. - It offers the models an agent can drive: text output, ready, tool calling and a known context window. Embedding, image and other models are left out. Models lists them.
- It gives the agent each model's context window, output limit and reasoning levels, and its prices where the agent shows them.
- It keeps the last good list on disk and uses it when the network is down.
VULTR_is the key.INFERENCE_ API_ KEY VULTR_replacesINFERENCE_ BASE_ URL https://api.vultrinference.com/v1.
Each agent's page has its install. The providers are open source, MIT licensed, at github.com/vultr/model-provider-<agent>. To build an integration of your own, start from the model catalog libraries they share.
Pick a model
Every provider names models as vultr/<id>, with the ids GET /v1/models lists. A reasoning level is the model's reasoning.effort: each agent offers the levels the model accepts, plus off where the model can answer without thinking. Reasoning has what each level does.
Endpoints