siyuan-note/siyuan · error

list models HTTP

Error message

list models HTTP %d: %s

What it means

ListAvailableModelsWithContext wraps a non-2xx response from the provider's model-list endpoint, including the first 64KB of the response body. This is the primary path for surfacing provider rejections (auth failures, bad endpoints, rate limits) when calling ListAvailableModels or the listModelsContract handler. The body text is the provider's own error payload, so it usually states the exact reason.

Solutions

1. Read the status and body text in the error: a 401 means fix the API key, 404 means fix the base URL, 429 means back off
2. Verify the model list endpoint path matches the provider (most OpenAI-compatible providers expect <baseURL>/v1/models)
3. Test the same request with curl using the configured base URL and key to isolate config vs network
4. If the body is an HTML error page, the URL is hitting the wrong service (proxy/landing page), not the API

Example fix

// before
baseURL := "https://api.example.com" // missing /v1
// after
baseURL := "https://api.example.com/v1" // so the request hits <baseURL>/models correctly

// before calling: verify key + base URL shape
if !strings.HasPrefix(apiKey, "sk-") { return errors.New("API key looks invalid") }
if !strings.HasSuffix(strings.TrimRight(baseURL, "/"), "/v1") { log.Println("base URL may need a /v1 suffix") }

if err != nil {
    msg := err.Error()
    switch {
    case strings.Contains(msg, "401"):
        return fixAPIKeyError(msg)
    case strings.Contains(msg, "429"):
        return backoffAndRetry()
    default:
        return fmt.Errorf("provider rejected model list: %w", err)
    }
}

When it happens

Trigger: Calling ListAvailableModels/ListAvailableModelsWithContext where the HTTP status is < 200 or >= 400, e.g. 401 invalid API key, 404 wrong base URL, 429 rate limited, 500 provider outage.

Common situations: Expired or wrong API key in the AI model config; base URL missing or wrongly adding /v1; using an OpenAI-specific endpoint against a provider with a different path; quota exhausted; proxy returning an error page.

Related errors

• invalid AI provider HTTP headers
• list models HTTP
• rerank HTTP
• asset path [ ] does not match data path [ ]
• authentication probe returned HTTP " + response.status

AI-assisted analysis of siyuan-note/siyuan@9f775e8a12 (2026-09-19). Data as JSON: /api/errors/a45512e5c8fa82a3. Report an issue: GitHub.

Appendix: source

Thrown at kernel/util/openai.go:392

	req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
	if err != nil {
		return nil, err
	}
	if apiKey != "" {
		req.Header.Set("Authorization", "Bearer "+apiKey)
	}
	resp, err := newAIProviderHTTPClient(apiBaseURL, headers...).Do(req)
	if err != nil {
		logging.LogErrorf("list models [%s] failed: %s", apiBaseURL, err)
		return
	}
	defer resp.Body.Close()
	if resp.StatusCode < http.StatusOK || http.StatusBadRequest <= resp.StatusCode {
		body, readErr := io.ReadAll(io.LimitReader(resp.Body, 64*1024))
		if readErr != nil {
			err = fmt.Errorf("list models HTTP %d", resp.StatusCode)
		} else {
			err = fmt.Errorf("list models HTTP %d: %s", resp.StatusCode, strings.TrimSpace(string(body)))
		}
		logging.LogErrorf("list models [%s] failed: %s", apiBaseURL, err)
		return
	}

	payload := &availableModelsPayload{}
	if err = json.NewDecoder(resp.Body).Decode(payload); err != nil {
		logging.LogErrorf("decode models [%s] failed: %s", apiBaseURL, err)
		return
	}
	for _, item := range payload.Data {
		id := strings.TrimSpace(item.ID)
		if id == "" {
			continue
		}
		models = append(models, AvailableModel{
			ID: id,
			ContextLength: firstValidModelContextLength(

View on GitHub (pinned to 9f775e8a12)