Added pollinations

docs/cli/index.md

@@ -307,6 +307,7 @@ Options:
 - `--openrouter-api-key <key>`
 - `--ai-gateway-api-key <key>`
 - `--moonshot-api-key <key>`
+- `--pollinations-api-key <key>`
 - `--kimi-code-api-key <key>`
 - `--gemini-api-key <key>`
 - `--zai-api-key <key>`

docs/docs.json

@@ -93,6 +93,14 @@
       "source": "/moonshot/",
       "destination": "/providers/moonshot"
     },
+    {
+      "source": "/pollinations",
+      "destination": "/providers/pollinations"
+    },
+    {
+      "source": "/pollinations/",
+      "destination": "/providers/pollinations"
+    },
     {
       "source": "/openrouter",
       "destination": "/providers/openrouter"
@@ -1010,6 +1018,7 @@
           "providers/anthropic",
           "bedrock",
           "providers/moonshot",
+          "providers/pollinations",
           "providers/minimax",
           "providers/vercel-ai-gateway",
           "providers/openrouter",

docs/providers/index.md

@@ -39,6 +39,7 @@ See [Venice AI](/providers/venice).
 - [OpenRouter](/providers/openrouter)
 - [Vercel AI Gateway](/providers/vercel-ai-gateway)
 - [Moonshot AI (Kimi + Kimi Code)](/providers/moonshot)
+- [Pollinations.ai](/providers/pollinations)
 - [OpenCode Zen](/providers/opencode)
 - [Amazon Bedrock](/bedrock)
 - [Z.AI](/providers/zai)

docs/providers/pollinations.md

@@ -0,0 +1,90 @@
+---
+summary: "Configure Pollinations.ai (Free/Open Source API)"
+---
+
+# Pollinations.ai
+
+Pollinations.ai provides AI API access with OpenAI-compatible endpoints. It supports various models including OpenAI's GPT series, Qwen, and Mistral.
+
+## Usage
+
+You can configure Pollinations interactively during onboarding:
+
+```bash
+moltbot onboard --auth-choice pollinations
+```
+
+Or configure it manually in your `moltbot.json` config file.
+
+## Configuration
+
+Pollinations uses a standard OpenAI-compatible endpoint. While it may offer a limited free tier, obtaining an API key is recommended for reliable access.
+
+### Config snippet
+
+```javascript
+// moltbot.json (partial)
+{
+  env: {
+    // Set your Pollinations API key here (sk-...)
+    POLLINATIONS_API_KEY: "sk-..." 
+  },
+  agents: {
+    defaults: {
+      model: { primary: "pollinations/openai" },
+      // Optional: alias for easier switching
+      models: {
+        "pollinations/openai": { alias: "Pollinations GPT-5 Mini" }
+      }
+    }
+  },
+  models: {
+    providers: {
+      pollinations: {
+        baseUrl: "https://gen.pollinations.ai/v1",
+        api: "openai-completions",
+        apiKey: "${POLLINATIONS_API_KEY}",
+        models: [
+          {
+            id: "openai",
+            name: "OpenAI GPT-5 Mini",
+            contextWindow: 128000,
+            maxTokens: 8192
+          },
+          // ... other models
+        ]
+      }
+    }
+  }
+}
+```
+
+## Available Models
+
+Pollinations offers a wide range of models. Common ones include:
+
+- `pollinations/openai`: **GPT-5 Mini** (0.15/0.60 Pollen/M)
+- `pollinations/openai-large`: **GPT-5.2** (1.75/14.0 Pollen/M)
+- `pollinations/openai-fast`: **GPT-5 Nano** (0.06/0.44 Pollen/M)
+- `pollinations/claude`: **Claude Sonnet 4.5** (3.0/15.0 Pollen/M)
+- `pollinations/claude-large`: **Claude Opus 4.5** (5.0/25.0 Pollen/M)
+- `pollinations/claude-fast`: **Claude Haiku 4.5** (1.0/5.0 Pollen/M)
+- `pollinations/gemini`: **Gemini 3 Flash** (0.5/3.0 Pollen/M)
+- `pollinations/gemini-large`: **Gemini 3 Pro** (2.0/12.0 Pollen/M)
+- `pollinations/gemini-fast`: **Gemini 2.5 Flash Lite** (0.1/0.4 Pollen/M)
+- `pollinations/qwen-coder`: **Qwen3 Coder 30B** (0.06/0.22 Pollen/M)
+- `pollinations/mistral`: **Mistral Small 3.2 24B** (0.15/0.35 Pollen/M)
+- `pollinations/deepseek`: **DeepSeek V3.2** (0.57/1.68 Pollen/M)
+- `pollinations/grok`: **xAI Grok 4 Fast** (0.2/0.5 Pollen/M)
+- `pollinations/perplexity-fast`: **Perplexity Sonar** (1.0/1.0 Pollen/M)
+- `pollinations/nova-fast`: **Amazon Nova Micro** (0.04/0.15 Pollen/M)
+
+*Costs are per million tokens (Input/Output). Prices subject to change.*
+
+## Notes
+
+- **API Key**: An API key is required. Get one at [enter.pollinations.ai](https://enter.pollinations.ai/).
+- **Cost**: Usage consumes "Pollen" credits, each pollen is equal to 1$ (Temporarily for beta 1 pollen is 0.5$).
+- **Privacy**: See [pollinations.ai](https://pollinations.ai) for privacy details.
+
+

src/agents/model-auth.ts

@@ -285,6 +285,7 @@ export function resolveEnvApiKey(provider: string): EnvApiKeyResult | null {
     venice: "VENICE_API_KEY",
     mistral: "MISTRAL_API_KEY",
     opencode: "OPENCODE_API_KEY",
+    pollinations: "POLLINATIONS_API_KEY",
   };
   const envVar = envMap[normalized];
   if (!envVar) return null;

src/agents/models-config.providers.ts

@@ -53,6 +53,16 @@ const KIMI_CODE_DEFAULT_COST = {
   cacheWrite: 0,
 };
 
+const POLLINATIONS_BASE_URL = "https://gen.pollinations.ai/v1";
+const POLLINATIONS_DEFAULT_CONTEXT_WINDOW = 128000;
+const POLLINATIONS_DEFAULT_MAX_TOKENS = 8192;
+const POLLINATIONS_DEFAULT_COST = {
+  input: 0,
+  output: 0,
+  cacheRead: 0,
+  cacheWrite: 0,
+};
+
 const QWEN_PORTAL_BASE_URL = "https://portal.qwen.ai/v1";
 const QWEN_PORTAL_OAUTH_PLACEHOLDER = "qwen-oauth";
 const QWEN_PORTAL_DEFAULT_CONTEXT_WINDOW = 128000;
@@ -333,6 +343,186 @@ function buildQwenPortalProvider(): ProviderConfig {
   };
 }
 
+function buildPollinationsProvider(): ProviderConfig {
+  return {
+    baseUrl: POLLINATIONS_BASE_URL,
+    api: "openai-completions",
+    models: [
+      {
+        id: "openai",
+        name: "OpenAI GPT-5 Mini",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 0.15, output: 0.6, cacheRead: 0.04, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "openai-large",
+        name: "OpenAI GPT-5.2",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 1.75, output: 14.0, cacheRead: 0.18, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "openai-fast",
+        name: "OpenAI GPT-5 Nano",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 0.06, output: 0.44, cacheRead: 0.01, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "claude",
+        name: "Anthropic Claude Sonnet 4.5",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 3.0, output: 15.0, cacheRead: 0, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "claude-large",
+        name: "Anthropic Claude Opus 4.5",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 5.0, output: 25.0, cacheRead: 0, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "claude-fast",
+        name: "Anthropic Claude Haiku 4.5",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 1.0, output: 5.0, cacheRead: 0, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "gemini",
+        name: "Google Gemini 3 Flash",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 0.5, output: 3.0, cacheRead: 0.05, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "gemini-large",
+        name: "Google Gemini 3 Pro",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 2.0, output: 12.0, cacheRead: 0.2, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "gemini-fast",
+        name: "Google Gemini 2.5 Flash Lite",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 0.1, output: 0.4, cacheRead: 0.01, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "qwen-coder",
+        name: "Qwen3 Coder 30B",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 0.06, output: 0.22, cacheRead: 0, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "mistral",
+        name: "Mistral Small 3.2 24B",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 0.15, output: 0.35, cacheRead: 0, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "deepseek",
+        name: "DeepSeek V3.2",
+        reasoning: true,
+        input: ["text"],
+        cost: { input: 0.57, output: 1.68, cacheRead: 0.29, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "grok",
+        name: "xAI Grok 4 Fast",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 0.2, output: 0.5, cacheRead: 0.2, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "perplexity-fast",
+        name: "Perplexity Sonar",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 1.0, output: 1.0, cacheRead: 0, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "perplexity-reasoning",
+        name: "Perplexity Sonar Reasoning",
+        reasoning: true,
+        input: ["text"],
+        cost: { input: 2.0, output: 8.0, cacheRead: 0, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "kimi",
+        name: "Moonshot Kimi K2.5",
+        reasoning: true,
+        input: ["text"],
+        cost: { input: 0.6, output: 3.0, cacheRead: 0.1, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "glm",
+        name: "Z.ai GLM-4.7",
+        reasoning: true,
+        input: ["text"],
+        cost: { input: 0.6, output: 2.21, cacheRead: 0.3, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "minimax",
+        name: "MiniMax M2.1",
+        reasoning: true,
+        input: ["text"],
+        cost: { input: 0.3, output: 1.2, cacheRead: 0.15, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+      {
+        id: "nova-fast",
+        name: "Amazon Nova Micro",
+        reasoning: false,
+        input: ["text"],
+        cost: { input: 0.04, output: 0.15, cacheRead: 0, cacheWrite: 0 },
+        contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+        maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+      },
+    ],
+  };
+}
+
 function buildSyntheticProvider(): ProviderConfig {
   return {
     baseUrl: SYNTHETIC_BASE_URL,
@@ -410,6 +600,20 @@ export async function resolveImplicitProviders(params: {
     };
   }
 
+  const pollinationsKey =
+    resolveEnvApiKeyVarName("pollinations") ??
+    resolveApiKeyFromProfiles({ provider: "pollinations", store: authStore });
+  // Always add Pollinations if explicitly asked, or if we have a profile.
+  // Since it's free, maybe we should add it by default?
+  // For now, let's follow the pattern: add if key/profile exists OR maybe if it's just enabled via config (not implemented here yet).
+  // But since it doesn't strictly need a key, users might just select it.
+  // The 'resolveImplicitProviders' logic seems to depend on keys or profiles being present.
+  // We can treat it like Ollama: only if configured/detected.
+  // If the user selects it in onboarding, they will get a profile (maybe with dummy key).
+  if (pollinationsKey) {
+    providers.pollinations = { ...buildPollinationsProvider(), apiKey: pollinationsKey };
+  }
+
   // Ollama provider - only add if explicitly configured
   const ollamaKey =
     resolveEnvApiKeyVarName("ollama") ??

src/cli/program/register.onboard.ts

@@ -52,7 +52,7 @@ export function registerOnboardCommand(program: Command) {
     .option("--mode <mode>", "Wizard mode: local|remote")
     .option(
       "--auth-choice <choice>",
-      "Auth: setup-token|token|chutes|openai-codex|openai-api-key|openrouter-api-key|ai-gateway-api-key|moonshot-api-key|kimi-code-api-key|synthetic-api-key|venice-api-key|gemini-api-key|zai-api-key|apiKey|minimax-api|minimax-api-lightning|opencode-zen|skip",
+      "Auth: setup-token|token|chutes|openai-codex|openai-api-key|openrouter-api-key|ai-gateway-api-key|moonshot-api-key|kimi-code-api-key|synthetic-api-key|venice-api-key|gemini-api-key|zai-api-key|apiKey|minimax-api|minimax-api-lightning|opencode-zen|pollinations|skip",
     )
     .option(
       "--token-provider <id>",
@@ -75,6 +75,7 @@ export function registerOnboardCommand(program: Command) {
     .option("--minimax-api-key <key>", "MiniMax API key")
     .option("--synthetic-api-key <key>", "Synthetic API key")
     .option("--venice-api-key <key>", "Venice API key")
+    .option("--pollinations-api-key <key>", "Pollinations API key")
     .option("--opencode-zen-api-key <key>", "OpenCode Zen API key")
     .option("--gateway-port <port>", "Gateway port")
     .option("--gateway-bind <mode>", "Gateway bind: loopback|tailnet|lan|auto|custom")
@@ -125,6 +126,7 @@ export function registerOnboardCommand(program: Command) {
             minimaxApiKey: opts.minimaxApiKey as string | undefined,
             syntheticApiKey: opts.syntheticApiKey as string | undefined,
             veniceApiKey: opts.veniceApiKey as string | undefined,
+            pollinationsApiKey: opts.pollinationsApiKey as string | undefined,
             opencodeZenApiKey: opts.opencodeZenApiKey as string | undefined,
             gatewayPort:
               typeof gatewayPort === "number" && Number.isFinite(gatewayPort)

src/commands/auth-choice-options.ts

@@ -20,7 +20,8 @@ export type AuthChoiceGroupId =
   | "minimax"
   | "synthetic"
   | "venice"
-  | "qwen";
+  | "qwen"
+  | "pollinations";
 
 export type AuthChoiceGroup = {
   value: AuthChoiceGroupId;
@@ -59,6 +60,12 @@ const AUTH_CHOICE_GROUP_DEFS: {
     hint: "OAuth",
     choices: ["qwen-portal"],
   },
+  {
+    value: "pollinations",
+    label: "Pollinations.ai",
+    hint: "API Key",
+    choices: ["pollinations"],
+  },
   {
     value: "synthetic",
     label: "Synthetic",
@@ -165,6 +172,11 @@ export function buildAuthChoiceOptions(params: {
   });
   options.push({ value: "zai-api-key", label: "Z.AI (GLM 4.7) API key" });
   options.push({ value: "qwen-portal", label: "Qwen OAuth" });
+  options.push({
+    value: "pollinations",
+    label: "Pollinations.ai",
+    hint: "Daily free tokens",
+  });
   options.push({
     value: "copilot-proxy",
     label: "Copilot Proxy (local)",

src/commands/auth-choice.apply.api-providers.ts

@@ -21,6 +21,8 @@ import {
   applyOpencodeZenProviderConfig,
   applyOpenrouterConfig,
   applyOpenrouterProviderConfig,
+  applyPollinationsConfig,
+  applyPollinationsProviderConfig,
   applySyntheticConfig,
   applySyntheticProviderConfig,
   applyVeniceConfig,
@@ -31,6 +33,7 @@ import {
   KIMI_CODE_MODEL_REF,
   MOONSHOT_DEFAULT_MODEL_REF,
   OPENROUTER_DEFAULT_MODEL_REF,
+  POLLINATIONS_DEFAULT_MODEL_REF,
   SYNTHETIC_DEFAULT_MODEL_REF,
   VENICE_DEFAULT_MODEL_REF,
   VERCEL_AI_GATEWAY_DEFAULT_MODEL_REF,
@@ -39,6 +42,7 @@ import {
   setMoonshotApiKey,
   setOpencodeZenApiKey,
   setOpenrouterApiKey,
+  setPollinationsApiKey,
   setSyntheticApiKey,
   setVeniceApiKey,
   setVercelAiGatewayApiKey,
@@ -85,6 +89,8 @@ export async function applyAuthChoiceApiProviders(
       authChoice = "venice-api-key";
     } else if (params.opts.tokenProvider === "opencode") {
       authChoice = "opencode-zen";
+    } else if (params.opts.tokenProvider === "pollinations") {
+      authChoice = "pollinations";
     }
   }
 
@@ -579,5 +585,63 @@ export async function applyAuthChoiceApiProviders(
     return { config: nextConfig, agentModelOverride };
   }
 
+  if (authChoice === "pollinations") {
+    let hasCredential = false;
+
+    if (!hasCredential && params.opts?.token && params.opts?.tokenProvider === "pollinations") {
+      await setPollinationsApiKey(normalizeApiKeyInput(params.opts.token), params.agentDir);
+      hasCredential = true;
+    }
+
+    if (!hasCredential) {
+      await params.prompter.note(
+        [
+          "Pollinations.ai provides AI API access.",
+          "Get your API key at: https://pollinations.ai/",
+        ].join("\n"),
+        "Pollinations.ai",
+      );
+    }
+
+    const envKey = resolveEnvApiKey("pollinations");
+    if (envKey) {
+      const useExisting = await params.prompter.confirm({
+        message: `Use existing POLLINATIONS_API_KEY (${envKey.source}, ${formatApiKeyPreview(envKey.apiKey)})?`,
+        initialValue: true,
+      });
+      if (useExisting) {
+        await setPollinationsApiKey(envKey.apiKey, params.agentDir);
+        hasCredential = true;
+      }
+    }
+    if (!hasCredential) {
+      const key = await params.prompter.text({
+        message: "Enter Pollinations API key",
+        validate: validateApiKeyInput,
+      });
+      await setPollinationsApiKey(normalizeApiKeyInput(String(key)), params.agentDir);
+    }
+    nextConfig = applyAuthProfileConfig(nextConfig, {
+      profileId: "pollinations:default",
+      provider: "pollinations",
+      mode: "api_key",
+    });
+    {
+      const applied = await applyDefaultModelChoice({
+        config: nextConfig,
+        setDefaultModel: params.setDefaultModel,
+        defaultModel: POLLINATIONS_DEFAULT_MODEL_REF,
+        applyDefaultConfig: applyPollinationsConfig,
+        applyProviderConfig: applyPollinationsProviderConfig,
+        noteDefault: POLLINATIONS_DEFAULT_MODEL_REF,
+        noteAgentModel,
+        prompter: params.prompter,
+      });
+      nextConfig = applied.config;
+      agentModelOverride = applied.agentModelOverride ?? agentModelOverride;
+    }
+    return { config: nextConfig, agentModelOverride };
+  }
+
   return null;
 }

src/commands/onboard-auth.config-core.ts

@@ -25,6 +25,10 @@ import {
   MOONSHOT_BASE_URL,
   MOONSHOT_DEFAULT_MODEL_ID,
   MOONSHOT_DEFAULT_MODEL_REF,
+  POLLINATIONS_BASE_URL,
+  POLLINATIONS_DEFAULT_MODEL_REF,
+  POLLINATIONS_MODEL_CATALOG,
+  buildPollinationsModelDefinition,
 } from "./onboard-auth.models.js";
 
 export function applyZaiConfig(cfg: MoltbotConfig): MoltbotConfig {
@@ -411,6 +415,81 @@ export function applyVeniceConfig(cfg: MoltbotConfig): MoltbotConfig {
   };
 }
 
+export function applyPollinationsProviderConfig(cfg: MoltbotConfig): MoltbotConfig {
+  const models = { ...cfg.agents?.defaults?.models };
+
+  // Add the default model
+  models[POLLINATIONS_DEFAULT_MODEL_REF] = {
+    ...models[POLLINATIONS_DEFAULT_MODEL_REF],
+    alias: models[POLLINATIONS_DEFAULT_MODEL_REF]?.alias ?? "Pollinations GPT-5 Mini",
+  };
+
+  const providers = { ...cfg.models?.providers };
+  const existingProvider = providers.pollinations;
+  const existingModels = Array.isArray(existingProvider?.models) ? existingProvider.models : [];
+  const pollinationsModels = Object.keys(POLLINATIONS_MODEL_CATALOG).map((id) =>
+    buildPollinationsModelDefinition({ id }),
+  );
+  const mergedModels = [
+    ...existingModels,
+    ...pollinationsModels.filter(
+      (model) => !existingModels.some((existing) => existing.id === model.id),
+    ),
+  ];
+  const { apiKey: existingApiKey, ...existingProviderRest } = (existingProvider ?? {}) as Record<
+    string,
+    unknown
+  > as { apiKey?: string };
+  // Pollinations doesn't technically require a key but we might support it if users want to pass one.
+  const resolvedApiKey = typeof existingApiKey === "string" ? existingApiKey : undefined;
+  const normalizedApiKey = resolvedApiKey?.trim();
+
+  providers.pollinations = {
+    ...existingProviderRest,
+    baseUrl: POLLINATIONS_BASE_URL,
+    api: "openai-completions",
+    ...(normalizedApiKey ? { apiKey: normalizedApiKey } : {}),
+    models: mergedModels.length > 0 ? mergedModels : pollinationsModels,
+  };
+
+  return {
+    ...cfg,
+    agents: {
+      ...cfg.agents,
+      defaults: {
+        ...cfg.agents?.defaults,
+        models,
+      },
+    },
+    models: {
+      mode: cfg.models?.mode ?? "merge",
+      providers,
+    },
+  };
+}
+
+export function applyPollinationsConfig(cfg: MoltbotConfig): MoltbotConfig {
+  const next = applyPollinationsProviderConfig(cfg);
+  const existingModel = next.agents?.defaults?.model;
+  return {
+    ...next,
+    agents: {
+      ...next.agents,
+      defaults: {
+        ...next.agents?.defaults,
+        model: {
+          ...(existingModel && "fallbacks" in (existingModel as Record<string, unknown>)
+            ? {
+                fallbacks: (existingModel as { fallbacks?: string[] }).fallbacks,
+              }
+            : undefined),
+          primary: POLLINATIONS_DEFAULT_MODEL_REF,
+        },
+      },
+    },
+  };
+}
+
 export function applyAuthProfileConfig(
   cfg: MoltbotConfig,
   params: {

src/commands/onboard-auth.credentials.ts

@@ -112,6 +112,19 @@ export async function setVeniceApiKey(key: string, agentDir?: string) {
   });
 }
 
+export async function setPollinationsApiKey(key: string, agentDir?: string) {
+  // Write to resolved agent dir so gateway finds credentials on startup.
+  upsertAuthProfile({
+    profileId: "pollinations:default",
+    credential: {
+      type: "api_key",
+      provider: "pollinations",
+      key,
+    },
+    agentDir: resolveAuthAgentDir(agentDir),
+  });
+}
+
 export const ZAI_DEFAULT_MODEL_REF = "zai/glm-4.7";
 export const OPENROUTER_DEFAULT_MODEL_REF = "openrouter/auto";
 export const VERCEL_AI_GATEWAY_DEFAULT_MODEL_REF = "vercel-ai-gateway/anthropic/claude-opus-4.5";

src/commands/onboard-auth.models.ts

@@ -20,6 +20,12 @@ export const KIMI_CODE_MAX_TOKENS = 32768;
 export const KIMI_CODE_HEADERS = { "User-Agent": "KimiCLI/0.77" } as const;
 export const KIMI_CODE_COMPAT = { supportsDeveloperRole: false } as const;
 
+export const POLLINATIONS_BASE_URL = "https://gen.pollinations.ai/v1";
+export const POLLINATIONS_DEFAULT_MODEL_ID = "openai";
+export const POLLINATIONS_DEFAULT_MODEL_REF = `pollinations/${POLLINATIONS_DEFAULT_MODEL_ID}`;
+export const POLLINATIONS_DEFAULT_CONTEXT_WINDOW = 128000;
+export const POLLINATIONS_DEFAULT_MAX_TOKENS = 8192;
+
 // Pricing: MiniMax doesn't publish public rates. Override in models.json for accurate costs.
 export const MINIMAX_API_COST = {
   input: 15,
@@ -51,6 +57,12 @@ export const KIMI_CODE_DEFAULT_COST = {
   cacheRead: 0,
   cacheWrite: 0,
 };
+export const POLLINATIONS_DEFAULT_COST = {
+  input: 0,
+  output: 0,
+  cacheRead: 0,
+  cacheWrite: 0,
+};
 
 const MINIMAX_MODEL_CATALOG = {
   "MiniMax-M2.1": { name: "MiniMax M2.1", reasoning: false },
@@ -116,3 +128,26 @@ export function buildKimiCodeModelDefinition(): ModelDefinitionConfig {
     compat: KIMI_CODE_COMPAT,
   };
 }
+
+export const POLLINATIONS_MODEL_CATALOG = {
+  openai: { name: "Pollinations (OpenAI Default)", reasoning: false },
+  "openai-large": { name: "Pollinations Large (GPT-4o)", reasoning: false },
+  "openai-fast": { name: "Pollinations Fast (GPT-4o-mini)", reasoning: false },
+  "qwen-coder": { name: "Pollinations Qwen Coder", reasoning: false },
+  mistral: { name: "Pollinations Mistral", reasoning: false },
+} as const;
+
+type PollinationsCatalogId = keyof typeof POLLINATIONS_MODEL_CATALOG;
+
+export function buildPollinationsModelDefinition(params: { id: string }): ModelDefinitionConfig {
+  const catalog = POLLINATIONS_MODEL_CATALOG[params.id as PollinationsCatalogId];
+  return {
+    id: params.id,
+    name: catalog?.name ?? `Pollinations ${params.id}`,
+    reasoning: catalog?.reasoning ?? false,
+    input: ["text"],
+    cost: POLLINATIONS_DEFAULT_COST,
+    contextWindow: POLLINATIONS_DEFAULT_CONTEXT_WINDOW,
+    maxTokens: POLLINATIONS_DEFAULT_MAX_TOKENS,
+  };
+}

src/commands/onboard-auth.ts

@@ -11,6 +11,8 @@ export {
   applyMoonshotProviderConfig,
   applyOpenrouterConfig,
   applyOpenrouterProviderConfig,
+  applyPollinationsConfig,
+  applyPollinationsProviderConfig,
   applySyntheticConfig,
   applySyntheticProviderConfig,
   applyVeniceConfig,
@@ -41,6 +43,7 @@ export {
   setMoonshotApiKey,
   setOpencodeZenApiKey,
   setOpenrouterApiKey,
+  setPollinationsApiKey,
   setSyntheticApiKey,
   setVeniceApiKey,
   setVercelAiGatewayApiKey,
@@ -54,6 +57,7 @@ export {
   buildMinimaxApiModelDefinition,
   buildMinimaxModelDefinition,
   buildMoonshotModelDefinition,
+  buildPollinationsModelDefinition,
   DEFAULT_MINIMAX_BASE_URL,
   KIMI_CODE_BASE_URL,
   KIMI_CODE_MODEL_ID,
@@ -64,4 +68,7 @@ export {
   MOONSHOT_BASE_URL,
   MOONSHOT_DEFAULT_MODEL_ID,
   MOONSHOT_DEFAULT_MODEL_REF,
+  POLLINATIONS_BASE_URL,
+  POLLINATIONS_DEFAULT_MODEL_ID,
+  POLLINATIONS_DEFAULT_MODEL_REF,
 } from "./onboard-auth.models.js";

src/commands/onboard-non-interactive/local/auth-choice.ts

@@ -14,6 +14,7 @@ import {
   applyMoonshotConfig,
   applyOpencodeZenConfig,
   applyOpenrouterConfig,
+  applyPollinationsConfig,
   applySyntheticConfig,
   applyVeniceConfig,
   applyVercelAiGatewayConfig,
@@ -25,6 +26,7 @@ import {
   setMoonshotApiKey,
   setOpencodeZenApiKey,
   setOpenrouterApiKey,
+  setPollinationsApiKey,
   setSyntheticApiKey,
   setVeniceApiKey,
   setVercelAiGatewayApiKey,
@@ -309,6 +311,25 @@ export async function applyNonInteractiveAuthChoice(params: {
     return applyVeniceConfig(nextConfig);
   }
 
+  if (authChoice === "pollinations") {
+    const resolved = await resolveNonInteractiveApiKey({
+      provider: "pollinations",
+      cfg: baseConfig,
+      flagValue: opts.pollinationsApiKey,
+      flagName: "--pollinations-api-key",
+      envVar: "POLLINATIONS_API_KEY",
+      runtime,
+    });
+    if (!resolved) return null;
+    if (resolved.source !== "profile") await setPollinationsApiKey(resolved.key);
+    nextConfig = applyAuthProfileConfig(nextConfig, {
+      profileId: "pollinations:default",
+      provider: "pollinations",
+      mode: "api_key",
+    });
+    return applyPollinationsConfig(nextConfig);
+  }
+
   if (
     authChoice === "minimax-cloud" ||
     authChoice === "minimax-api" ||

src/commands/onboard-types.ts

@@ -31,6 +31,7 @@ export type AuthChoice =
   | "github-copilot"
   | "copilot-proxy"
   | "qwen-portal"
+  | "pollinations"
   | "skip";
 export type GatewayAuthChoice = "token" | "password";
 export type ResetScope = "config" | "config+creds+sessions" | "full";
@@ -70,6 +71,7 @@ export type OnboardOptions = {
   minimaxApiKey?: string;
   syntheticApiKey?: string;
   veniceApiKey?: string;
+  pollinationsApiKey?: string;
   opencodeZenApiKey?: string;
   gatewayPort?: number;
   gatewayBind?: GatewayBind;