Using with coding tools
Many coding assistants let you point them at an OpenAI-compatible endpoint. The two settings are always the same:
Looking for an autonomous agent — one that edits files, runs commands and iterates on its own? See AI Agents for tools we have verified end to end against this API, with full setup for each. This page covers pointing a general-purpose assistant at the endpoint.
| Setting | Value |
|---|---|
| Base URL | https://api.devotel.com/v1 |
| API key | your dvt-... key |
| Model | kimi-k3 |
Environment variables
Most tools read the standard OpenAI variables, which is the quickest thing to try first:
export OPENAI_API_KEY="dvt-..."
export OPENAI_BASE_URL="https://api.devotel.com/v1"Some older tools read OPENAI_API_BASE instead — set both if you are unsure:
export OPENAI_API_BASE="https://api.devotel.com/v1"Continue (VS Code / JetBrains)
~/.continue/config.json:
{
"models": [
{
"title": "Kimi K3 (Devotel)",
"provider": "openai",
"model": "kimi-k3",
"apiBase": "https://api.devotel.com/v1",
"apiKey": "dvt-..."
}
]
}Aider
export OPENAI_API_KEY="dvt-..."
export OPENAI_API_BASE="https://api.devotel.com/v1"
aider --model openai/kimi-k3Zed
In settings.json, under the assistant’s OpenAI-compatible provider:
{
"language_models": {
"openai": {
"api_url": "https://api.devotel.com/v1",
"available_models": [{ "name": "kimi-k3", "display_name": "Kimi K3 (Devotel)" }]
}
}
}Put the key in the editor’s credential store rather than the settings file.
Anything else
If a tool asks for “OpenAI-compatible endpoint”, “custom base URL” or “self-hosted OpenAI”, give it the base URL and key above. Confirm the plumbing with a plain curl first — if this returns a completion, the endpoint is fine and any remaining problem is in the tool’s configuration:
curl https://api.devotel.com/v1/chat/completions \
-H "Authorization: Bearer $DEVOTEL_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"kimi-k3","messages":[{"role":"user","content":"reply with OK"}]}'Things that trip tools up
Reasoning output. Kimi K3 returns reasoning_content alongside content. Tools that only read
content behave correctly. Tools that concatenate every string field may show you the model’s
thinking as if it were code — check the tool’s raw-response handling if output looks odd.
Slow first token. Reasoning happens before any visible output, so a tool with an aggressive timeout may give up before the answer starts. Raise the request timeout if you see empty responses.
max_tokens defaults. Some tools set a low max_tokens by default. Because the cap includes
reasoning tokens, a low value can consume the whole budget thinking and return nothing. If a tool
returns empty completions, raise or remove its output cap — see
Chat Completions.
Unsupported endpoints. A tool that wants embeddings (for local codebase indexing, say) will fail on that feature — embeddings are not implemented yet. Chat features still work.
Tune reasoning_effort before anything else. A coding assistant fires many small requests —
completions, edits, file lookups — and reasoning tokens bill as output at 5× the input rate. Set
the key’s default to low or none and reserve high/max for the requests that need real
thinking; it is the difference between a cheap assistant and an expensive one, and it cuts latency
in the same direction. See Chat Completions.
Rate limits are per key, and a new key starts with no effective cap — but an administrator can assign specific limits to any key, and a coding assistant making rapid parallel edits is the kind of traffic that then hits them. See Rate Limits & Errors.