Skip to content

Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors

chore: remove 9 dead/unreachable free providers (#3054)

Paijo76d697bb88fc
diff --git a/open-sse/config/petals.ts b/open-sse/config/petals.ts
deleted file mode 100644
index 569c65ba1d..0000000000
--- a/open-sse/config/petals.ts
+++ /dev/null
@@ -1,19 +0,0 @@
-export const PETALS_DEFAULT_BASE_URL = "https://chat.petals.dev/api/v1/generate";
-export const PETALS_DEFAULT_MODEL = "stabilityai/StableBeluga2";
-
-export function normalizePetalsBaseUrl(baseUrl: string | null | undefined): string {
- const normalized = String(baseUrl || PETALS_DEFAULT_BASE_URL)
- .trim()
- .replace(/\/+$/, "");
-
- if (normalized.endsWith("/api/v1/generate")) {
- return normalized;
- }
- if (normalized.endsWith("/api/v1")) {
- return `${normalized}/generate`;
- }
- if (normalized.endsWith("/api")) {
- return `${normalized}/v1/generate`;
- }
- return `${normalized}/api/v1/generate`;
-}
diff --git a/open-sse/config/providerRegistry.ts b/open-sse/config/providerRegistry.ts
index 8e9a50e666..6e8c696e23 100644
--- a/open-sse/config/providerRegistry.ts
+++ b/open-sse/config/providerRegistry.ts
@@ -2334,16 +2334,6 @@ const _REGISTRY_EAGER: Record<string, RegistryEntry> = {
models: [{ id: "auto", name: "Auto" }],
},
- lepton: {
- id: "lepton",
- alias: "lepton",
- format: "openai",
- executor: "default",
- baseUrl: "https://api.lepton.ai/v1/chat/completions",
- authType: "apikey",
- authHeader: "bearer",
- models: [{ id: "llama-3.1-8b", name: "Llama 3.1 8B" }],
- },
kluster: {
id: "kluster",
@@ -2378,16 +2368,6 @@ const _REGISTRY_EAGER: Record<string, RegistryEntry> = {
models: [{ id: "liquid-lfm-40b", name: "Liquid LFM 40B" }],
},
- nomic: {
- id: "nomic",
- alias: "nomic",
- format: "openai",
- executor: "default",
- baseUrl: "https://api.nomic.ai/v1/chat/completions",
- authType: "apikey",
- authHeader: "bearer",
- models: [{ id: "nomic-embed-text-v1.5", name: "Nomic Embed Text" }],
- },
monsterapi: {
id: "monsterapi",
@@ -2426,16 +2406,6 @@ const _REGISTRY_EAGER: Record<string, RegistryEntry> = {
],
},
- poolside: {
- id: "poolside",
- alias: "poolside",
- format: "openai",
- executor: "default",
- baseUrl: "https://api.poolside.ai/v1/chat/completions",
- authType: "apikey",
- authHeader: "bearer",
- models: [{ id: "poolside-model", name: "Poolside Model" }],
- },
chutes: {
id: "chutes",
@@ -2655,35 +2625,6 @@ const _REGISTRY_EAGER: Record<string, RegistryEntry> = {
{ id: "gemini-3-flash-preview", name: "Gemini 3 Flash" },
],
},
- enally: {
- id: "enally",
- alias: "enly",
- format: "openai",
- executor: "default",
- baseUrl: "https://ai.enally.in",
- authType: "apikey",
- authHeader: "X-API-Key",
- models: [
- { id: "default", name: "Default Model" },
- { id: "chat", name: "Chat Model" },
- { id: "reasoning", name: "Reasoning Model" },
- { id: "multimodal", name: "Multimodal Model" },
- ],
- },
- freetheai: {
- id: "freetheai",
- alias: "fta",
- format: "openai",
- executor: "default",
- baseUrl: "https://api.freetheai.xyz/v1/chat/completions",
- authType: "apikey",
- authHeader: "bearer",
- models: [
- { id: "free-fast", name: "Free Fast (Low Latency)" },
- { id: "free-smart", name: "Free Smart (Reasoning)" },
- { id: "free", name: "Free (Max Uptime)" },
- ],
- },
xai: {
id: "xai",
alias: "xai",
@@ -3631,42 +3572,6 @@ const _REGISTRY_EAGER: Record<string, RegistryEntry> = {
],
},
- replicate: {
- id: "replicate",
- alias: "rep",
- format: "openai",
- executor: "default",
- baseUrl: "https://openai-proxy.replicate.com/v1/chat/completions",
- modelsUrl: "https://openai-proxy.replicate.com/v1/models",
- authType: "apikey",
- authHeader: "Authorization",
- authPrefix: "Bearer",
- passthroughModels: true,
- defaultContextLength: 128000,
- models: [
- {
- id: "meta/meta-llama-3.1-405b-instruct",
- name: "Llama 3.1 405B Instruct (Free)",
- contextLength: 128000,
- },
- {
- id: "meta/meta-llama-3.1-70b-instruct",
- name: "Llama 3.1 70B Instruct (Free)",
- contextLength: 128000,
- },
- {
- id: "mistralai/mixtral-8x7b-instruct-v0.1",
- name: "Mixtral 8x7B Instruct (Free)",
- contextLength: 32768,
- },
- {
- id: "deepseek-ai/deepseek-r1",
- name: "DeepSeek R1 (Free)",
- contextLength: 65536,
- supportsReasoning: true,
- },
- ],
- },
hackclub: {
id: "hackclub",
diff --git a/src/lib/providers/imageValidation.ts b/src/lib/providers/imageValidation.ts
index 150a3a1804..de5057acda 100644
--- a/src/lib/providers/imageValidation.ts
+++ b/src/lib/providers/imageValidation.ts
@@ -12,10 +12,6 @@ const IMAGE_PROVIDER_VALIDATION_ENDPOINTS: Record<
string,
{ baseUrl?: string; path: string; method?: string }
> = {
- nanobanana: {
- baseUrl: "https://api.nanobananaapi.ai",
- path: "/api/v1/common/credit",
- },
"fal-ai": {
baseUrl: "https://api.fal.ai",
path: "/v1/models?limit=1",
diff --git a/src/lib/providers/staticModels.ts b/src/lib/providers/staticModels.ts
index 6e17464449..0cf74fe5fe 100644
--- a/src/lib/providers/staticModels.ts
+++ b/src/lib/providers/staticModels.ts
@@ -31,10 +31,6 @@ const STATIC_MODEL_PROVIDERS: Record<string, () => Array<{ id: string; name: str
{ id: "universal-3-pro", name: "Universal 3 Pro (Transcription)" },
{ id: "universal-2", name: "Universal 2 (Transcription)" },
],
- nanobanana: () => [
- { id: "nanobanana-flash", name: "NanoBanana Flash (Gemini 2.5 Flash)" },
- { id: "nanobanana-pro", name: "NanoBanana Pro (Gemini 3 Pro)" },
- ],
antigravity: () => ANTIGRAVITY_PUBLIC_MODELS.map((model) => ({ ...model })),
claude: () => [
{ id: "claude-opus-4-8", name: "Claude Opus 4.8" },
diff --git a/src/lib/providers/validation.ts b/src/lib/providers/validation.ts
index 19976bd5bd..6af959ddcd 100644
--- a/src/lib/providers/validation.ts
+++ b/src/lib/providers/validation.ts
@@ -69,7 +69,6 @@ import {
buildRunwayHeaders,
normalizeRunwayBaseUrl,
} from "@omniroute/open-sse/config/runway.ts";
-import { PETALS_DEFAULT_MODEL, normalizePetalsBaseUrl } from "@omniroute/open-sse/config/petals.ts";
import {
buildMaritalkChatUrl,
buildMaritalkModelsUrl,
@@ -961,10 +960,6 @@ async function validateAssemblyAIProvider({ apiKey, providerSpecificData = {} }:
}
}
-async function validateNanoBananaProvider({ apiKey, providerSpecificData = {} }: any) {
- return validateImageProviderApiKey({ provider: "nanobanana", apiKey, providerSpecificData });
-}
-
async function validateElevenLabsProvider({ apiKey, providerSpecificData = {} }: any) {
try {
// Lightweight auth check endpoint
@@ -2013,67 +2008,6 @@ async function validateRunwayProvider({ apiKey, providerSpecificData = {} }: any
return { valid: false, error: "Connection failed while testing Runway" };
}
-async function validatePetalsProvider({ apiKey, providerSpecificData = {} }: any) {
- const url = normalizePetalsBaseUrl(providerSpecificData.baseUrl);
- const modelId =
- typeof providerSpecificData.validationModelId === "string" &&
- providerSpecificData.validationModelId.trim()
- ? providerSpecificData.validationModelId.trim()
- : PETALS_DEFAULT_MODEL;
- const headers: Record<string, string> = {
- "Content-Type": "application/x-www-form-urlencoded",
- };
- if (apiKey) {
- headers.Authorization = `Bearer ${apiKey}`;
- }
-
- const body = new URLSearchParams({
- model: modelId,
- inputs: "test",
- max_new_tokens: "1",
- });
-
- try {
- const response = await validationWrite(url, {
- method: "POST",
- headers,
- body: body.toString(),
- });
-
- if (response.ok) {
- const payload = (await response.json().catch(() => ({}))) as Record<string, unknown>;
- if (payload.ok === false) {
- return {
- valid: false,
- error: "Petals API rejected validation request",
- };
- }
- return { valid: true, error: null, method: "petals_generate" };
- }
-
- if (response.status === 401 || response.status === 403) {
- return { valid: false, error: "Invalid API key" };
- }
-
- if (response.status === 429) {
- return {
- valid: true,
- error: null,
- method: "petals_generate",
- warning: "Rate limited, but endpoint is reachable",
- };
- }
-
- if (response.status >= 500) {
- return { valid: false, error: `Provider unavailable (${response.status})` };
- }
- } catch (error: any) {
- return toValidationErrorResult(error);
- }
-
- return { valid: false, error: "Connection failed while testing Petals" };
-}
-
async function validateNousResearchProvider({ apiKey, providerSpecificData = {} }: any) {
const baseUrl =
normalizeBaseUrl(providerSpecificData.baseUrl) || "https://inference-api.nousresearch.com/v1";
@@ -3785,7 +3719,6 @@ export async function validateProviderApiKey({ provider, apiKey, providerSpecifi
"command-code": validateCommandCodeProvider,
deepgram: validateDeepgramProvider,
assemblyai: validateAssemblyAIProvider,
- nanobanana: validateNanoBananaProvider,
"fal-ai": ({ apiKey, providerSpecificData }: any) =>
validateImageProviderApiKey({ provider: "fal-ai", apiKey, providerSpecificData }),
"stability-ai": ({ apiKey, providerSpecificData }: any) =>
@@ -3818,7 +3751,6 @@ export async function validateProviderApiKey({ provider, apiKey, providerSpecifi
isLocal,
}),
"nous-research": validateNousResearchProvider,
- petals: validatePetalsProvider,
poe: validatePoeProvider,
clarifai: validateClarifaiProvider,
reka: validateRekaProvider,
@@ -3970,37 +3902,6 @@ export async function validateProviderApiKey({ provider, apiKey, providerSpecifi
return toValidationErrorResult(error);
}
},
- // Poolside (#2723) — API has no /v1/models endpoint and returns 401 from
- // unknown routes, which the generic /models probe misreads as "invalid API key".
- // Validate via direct chat/completions probe with a minimal body.
- poolside: async ({ apiKey, providerSpecificData }: any) => {
- try {
- const baseUrl = normalizeBaseUrl(
- providerSpecificData?.baseUrl || "https://api.poolside.ai/v1"
- );
- const chatUrl = `${baseUrl.replace(/\/chat\/completions$/, "")}/chat/completions`;
- const res = await validationWrite(
- chatUrl,
- {
- method: "POST",
- headers: buildBearerHeaders(apiKey, providerSpecificData),
- body: JSON.stringify({
- model: "poolside-model",
- messages: [{ role: "user", content: "test" }],
- max_tokens: 1,
- }),
- },
- isLocal
- );
- if (res.status === 401 || res.status === 403) {
- return { valid: false, error: "Invalid API key" };
- }
- // Any non-auth response (200, 400, 422, 429) means auth passed
- return { valid: true, error: null };
- } catch (error: any) {
- return toValidationErrorResult(error);
- }
- },
// Xiaomi MiMo — Token Plan keys (tp-*) only work on regional endpoints
// (e.g. token-plan-sgp, token-plan-ams), not api.xiaomimimo.com.
// /v1/models works but validate via chat/completions for stronger auth check.
diff --git a/src/shared/constants/providers.ts b/src/shared/constants/providers.ts
index 7f6a7ef57c..d30a90c893 100644
--- a/src/shared/constants/providers.ts
+++ b/src/shared/constants/providers.ts
@@ -585,31 +585,6 @@ export const APIKEY_PROVIDERS = {
"55 free tier models including Grok-3, Claude 3.7, Qwen3, Kimi-K2, Gemini 2.5 Flash, DeepSeek-V3",
apiHint:
"Get your API key from https://panel.api.airforce — OpenAI-compatible endpoint at https://api.airforce/v1",
- capabilities: { embeddings: false },
- },
- astraflow: {
- id: "astraflow",
- alias: "astraflow",
- name: "Astraflow (UCloud Global)",
- icon: "cloud",
- color: "#0052D9",
- textIcon: "AF",
- passthroughModels: true,
- website: "https://astraflow.ucloud-global.com",
- apiHint:
- "Astraflow by UCloud — OpenAI-compatible platform supporting 200+ models (global endpoint). Get your API key at https://astraflow.ucloud-global.com",
- },
- "astraflow-cn": {
- id: "astraflow-cn",
- alias: "astraflow-cn",
- name: "Astraflow (UCloud China)",
- icon: "cloud",
- color: "#0052D9",
- textIcon: "AFC",
- passthroughModels: true,
- website: "https://astraflow.ucloud.cn",
- apiHint:
- "Astraflow by UCloud — OpenAI-compatible platform supporting 200+ models (China endpoint). Get your API key at https://astraflow.ucloud.cn",
},
qianfan: {
id: "qianfan",
@@ -934,32 +909,6 @@ export const APIKEY_PROVIDERS = {
freeNote: "Free unlimited access to Claude, GPT, Gemini — no credit card, no rate limits",
apiHint: "Sign up at https://completions.me for free API key. OpenAI-compatible endpoint.",
},
- enally: {
- id: "enally",
- alias: "enly",
- name: "Enally AI",
- icon: "school",
- color: "#8B5CF6",
- textIcon: "EN",
- website: "https://ai.enally.in",
- hasFree: true,
- freeNote: "Free for students and developers — no credit card, OTP verification",
- apiHint:
- "Get free API key at https://ai.enally.in/api — requires email and domain whitelisting.",
- },
- freetheai: {
- id: "freetheai",
- alias: "fta",
- name: "FreeTheAi",
- icon: "lock_open",
- color: "#10B981",
- textIcon: "FT",
- website: "https://freetheai.xyz",
- hasFree: true,
- freeNote: "Community-run — free forever, no paid tiers, no credit card",
- apiHint:
- "Get free API key via Discord: https://freetheai.xyz — 16,000+ models, OpenAI-compatible.",
- },
xai: {
id: "xai",
alias: "xai",
@@ -1078,15 +1027,6 @@ export const APIKEY_PROVIDERS = {
hasFree: true,
freeNote: "$1-5 trial credits on signup for serverless inference",
},
- nanobanana: {
- id: "nanobanana",
- alias: "nb",
- name: "NanoBanana",
- icon: "image",
- color: "#FFD700",
- textIcon: "NB",
- website: "https://nanobananaapi.ai",
- },
kie: {
id: "kie",
alias: "kie",
@@ -1255,20 +1195,6 @@ export const APIKEY_PROVIDERS = {
passthroughModels: true,
authHint: "No auth required. API accepts any non-empty string as key for identification.",
},
- replicate: {
- id: "replicate",
- alias: "rep",
- name: "Replicate",
- icon: "auto_awesome",
- color: "#3B82F6",
- textIcon: "RE",
- website: "https://replicate.com",
- hasFree: true,
- freeNote:
- "Free community models — Llama 3.1, Mixtral, DeepSeek R1. Passthrough for SDXL, Whisper, MusicGen.",
- passthroughModels: true,
- authHint: "Get API token at replicate.com/account/api-tokens",
- },
hackclub: {
id: "hackclub",
alias: "hc",
@@ -1512,17 +1438,6 @@ export const APIKEY_PROVIDERS = {
apiHint:
"Works without API key (use 'unused' as key). Get free token at token.llm7.io for higher limits.",
},
- lepton: {
- id: "lepton",
- alias: "lepton",
- name: "Lepton AI",
- icon: "bolt",
- color: "#10B981",
- textIcon: "LP",
- website: "https://lepton.ai",
- hasFree: true,
- freeNote: "Free tier available - fast inference on custom hardware",
- },
kluster: {
id: "kluster",
alias: "kluster",
@@ -1897,19 +1812,6 @@ export const APIKEY_PROVIDERS = {
hasFree: true,
freeNote: "Free tier: 50 RPM, 500,000 TPM — no credit card",
},
- petals: {
- id: "petals",
- alias: "petals",
- name: "Petals",
- icon: "hub",
- color: "#10B981",
- textIcon: "PT",
- website: "https://chat.petals.dev",
- authHint:
- "No API key is required for the public research endpoint. Leave the field blank, or provide a bearer token if your self-hosted Petals gateway uses auth.",
- apiHint:
- "Petals exposes a public HTTP API at https://chat.petals.dev/api/v1/generate and a WebSocket API at /api/v2/generate. OmniRoute targets the HTTP generate endpoint and supports self-hosted base URLs.",
- },
poe: {
id: "poe",
alias: "poe",
@@ -2198,19 +2100,6 @@ export const APIKEY_PROVIDERS = {
passthroughModels: true,
authHint: "Get API key from your Dify instance.",
},
- poolside: {
- id: "poolside",
- alias: "poolside",
- name: "Poolside",
- icon: "code",
- color: "#3B82F6",
- textIcon: "PS",
- website: "https://poolside.ai",
- hasFree: true,
- freeNote: "Free Laguna XS.2 and Laguna M.1 coding agent models. No credit card required.",
- passthroughModels: true,
- authHint: "Get API key at poolside.ai",
- },
"arcee-ai": {
id: "arcee-ai",
alias: "arcee",
@@ -2264,19 +2153,6 @@ export const APIKEY_PROVIDERS = {
passthroughModels: true,
authHint: "Get API key at atlas.nomic.ai",
},
- krutrim: {
- id: "krutrim",
- alias: "krutrim",
- name: "Krutrim",
- icon: "auto_awesome",
- color: "#F59E0B",
- textIcon: "KR",
- website: "https://krutrim.ai",
- hasFree: true,
- freeNote: "India's first AI (by Ola). Free tier available. No credit card required.",
- passthroughModels: true,
- authHint: "Get API key at krutrim.ai",
- },
monsterapi: {
id: "monsterapi",
alias: "monster",