Your earlier direction was mostly right (OpenAI-compatible chat completions + Bearer key), but the correct canonical host/endpoint from paste.txt is https://gen.pollinations.ai/v1/chat/completions (and /openai is explicitly marked legacy/deprecated).[1] So Townie should implement Pollinations against gen.pollinations.ai by default, keep the base URL configurable, and add model discovery + fallback selection.[2][1]

1. Set defaults to:

• POLLINATIONS_BASE_URL = "https://gen.pollinations.ai"[1]
• POLLINATIONS_CHAT_PATH = "/v1/chat/completions"[1]
• Authorization: Bearer ${POLLINATIONS_TOKEN} header.[1]

2. Do not use /openai except as an emergency fallback, because the docs say it’s a legacy endpoint and recommends /v1/chat/completions instead.[1]

3. Use secret keys (sk_) only on the server side (Val Town env var), because publishable keys are beta and explicitly warned against for production client-side use.[2][1]

Pollinations explicitly supports model discovery endpoints, so Townie should implement runtime discovery and pick models based on capabilities and pricing metadata instead of hardcoding names.[1]

• On startup (and daily), call GET https://gen.pollinations.ai/v1/models to get available OpenAI-compatible text models.[1]
• Also call GET https://gen.pollinations.ai/text/models to get richer model metadata including pricing and capability flags like tools, reasoning, and context_window.[1]
• For images, call GET https://gen.pollinations.ai/image/models to enumerate image models and pricing.[1]

Use this ordered list, but only if each model exists in /v1/models (otherwise skip it):[1]

1. Primary: gemini (cheap/good default).[1]
2. Fallback 1: openai (broad compatibility baseline per examples).[1]
3. Fallback 2: gemini-large (use when you need higher quality / harder planning).[1]
4. Optional: gemini-search only if you intentionally add “web search” features, since it’s described as having google_search enabled.[1]

Townie should store the chosen primary/fallback model IDs in SQLite (or config) after discovery so requests don’t depend on discovery every time.[2][1]

• Inbox triage + tagging suggestions: use primary (gemini) to keep costs low.[1]
• AI “plan” generation for large batches (projects/apply rules): allow escalation to gemini-large when the task is complex or the first attempt fails validation.[1]
• If Pollinations returns model errors, automatically retry with the next fallback in order.[1]

Pollinations supports image generation at GET https://gen.pollinations.ai/image/<prompt>?model=flux with Bearer auth, so Townie can implement a /api/image/cover endpoint (or similar) for project cover images or “visual summaries.”[1] Also implement image model fallback using /image/models rather than hardcoding flux everywhere (but flux is a fine default).[1]

Readwise Reader API auth stays Authorization: Token XXX (separate from Pollinations), stored in Val Town env vars.[3][2] Keep Pollinations and Readwise tokens server-side only (Val Town environment variables), because Val Town endpoints are public-by-URL unless you add auth.[2]

If you want, I can give Townie an exact “decision function” (TypeScript) that consumes /text/models and picks the cheapest model that still has tools=true (if you need tool calling) vs tools=false (for pure summarization).[1]

Citations: [1] paste.txt
[2] llms-full-valtown.txt
[3] Reader API

• OpenAPI Version: 3.1.0
• API Version: 0.3.0

Documentation for gen.pollinations.ai - the pollinations.ai API gateway.

📝 Edit docs

Get your API key at https://enter.pollinations.ai

curl 'https://gen.pollinations.ai/image/a%20cat?model=flux' \
  -H 'Authorization: Bearer YOUR_API_KEY'

curl 'https://gen.pollinations.ai/v1/chat/completions' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "openai", "messages": [{"role": "user", "content": "Hello"}]}'

curl 'https://gen.pollinations.ai/v1/chat/completions' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "openai", "messages": [{"role": "user", "content": [{"type": "text", "text": "Describe this image"}, {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}]}]}'

Gemini Tools: gemini, gemini-large have code_execution enabled (can generate images/plots). gemini-search has google_search enabled. Responses may include content_blocks with image_url, text, or thinking types.

curl 'https://gen.pollinations.ai/text/hello?key=YOUR_API_KEY'

curl 'https://gen.pollinations.ai/v1/chat/completions' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "openai", "messages": [{"role": "user", "content": "Write a poem"}], "stream": true}' \
  --no-buffer

Always check available models before testing:

• Image models: /image/models
• Text models: /v1/models

Two key types (both consume Pollen from your balance):

• Publishable Keys (pk_): ⚠️ Beta - not yet ready for production use. For client-side apps, IP rate-limited (1 pollen per IP per hour). Warning: Exposing in public code will consume your Pollen if your app gets traffic.
• Secret Keys (sk_): Server-side only, no rate limits. Keep secret - never expose publicly.

Auth methods:

1. Header: Authorization: Bearer YOUR_API_KEY
2. Query param: ?key=YOUR_API_KEY

Check your balance and usage:

# Check pollen balance
curl 'https://gen.pollinations.ai/account/balance' \
  -H 'Authorization: Bearer YOUR_API_KEY'

# Get profile info
curl 'https://gen.pollinations.ai/account/profile' \
  -H 'Authorization: Bearer YOUR_API_KEY'

# View usage history
curl 'https://gen.pollinations.ai/account/usage' \
  -H 'Authorization: Bearer YOUR_API_KEY'

• URL: https://gen.pollinations.ai

• Method: GET
• Path: /account/profile
• Tags: gen.pollinations.ai

Get user profile info (name, email, GitHub username, tier, createdAt, nextResetAt). Requires account:profile permission for API keys.

• createdAt (required)

  string, format: date-time — Account creation timestamp (ISO 8601)

• email (required)

  object — User's email address

• githubUsername (required)

  object — GitHub username if linked

• name (required)

  object — User's display name

• nextResetAt (required)

  object — Next daily pollen reset timestamp (ISO 8601)

• tier (required)

  string, possible values: "anonymous", "spore", "seed", "flower", "nectar", "router" — User's current tier level

Example:

{
  "name": "",
  "email": "",
  "githubUsername": "",
  "tier": "anonymous",
  "createdAt": "",
  "nextResetAt": ""
}

• Method: GET
• Path: /account/balance
• Tags: gen.pollinations.ai

Get pollen balance. Returns the key's remaining budget if set, otherwise the user's total balance. Requires account:balance permission for API keys.

• balance (required)

  number — Remaining pollen balance (combines tier, pack, and crypto balances)

Example:

{
  "balance": 1
}

• Method: GET
• Path: /account/usage
• Tags: gen.pollinations.ai

Get request history and spending data. Supports JSON and CSV formats. Requires account:usage permission for API keys.

• count (required)

  number — Number of records returned

• usage (required)

  array — Array of usage records

  Items:

  • api_key (required)

    object — API key identifier used (masked)

  • api_key_type (required)

    object — Type of API key ('secret', 'publishable', 'temporary')

  • cost_usd (required)

    number — Cost in USD for this request

  • input_audio_tokens (required)

    number — Number of input audio tokens

  • input_cached_tokens (required)

    number — Number of cached input tokens

  • input_image_tokens (required)

    number — Number of input image tokens

  • input_text_tokens (required)

    number — Number of input text tokens

  • meter_source (required)

    object — Billing source ('tier', 'pack', 'crypto')

  • model (required)

    object — Model used for generation

  • output_audio_tokens (required)

    number — Number of output audio tokens

  • output_image_tokens (required)

    number — Number of output image tokens (1 per image)

  • output_reasoning_tokens (required)

    number — Number of reasoning tokens (for models with chain-of-thought)

  • output_text_tokens (required)

    number — Number of output text tokens

  • response_time_ms (required)

    object — Response time in milliseconds

  • timestamp (required)

    string — Request timestamp (YYYY-MM-DD HH:mm:ss format)

  • type (required)

    string — Request type (e.g., 'generate.image', 'generate.text')

Example:

{
  "usage": [
    {
      "timestamp": "",
      "type": "",
      "model": "",
      "api_key": "",
      "api_key_type": "",
      "meter_source": "",
      "input_text_tokens": 1,
      "input_cached_tokens": 1,
      "input_audio_tokens": 1,
      "input_image_tokens": 1,
      "output_text_tokens": 1,
      "output_reasoning_tokens": 1,
      "output_audio_tokens": 1,
      "output_image_tokens": 1,
      "cost_usd": 1,
      "response_time_ms": 1
    }
  ],
  "count": 1
}

• Method: GET
• Path: /v1/models
• Tags: gen.pollinations.ai

Get available text models (OpenAI-compatible). If an API key with model restrictions is provided, only allowed models are returned.

• data (required)

  array

  Items:

  • created (required)

    number

  • id (required)

    string

  • object (required)

    string

• object (required)

  string

Example:

{
  "object": "list",
  "data": [
    {
      "id": "",
      "object": "model",
      "created": 1
    }
  ]
}

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 500,
  "success": false,
  "error": {
    "code": "INTERNAL_ERROR",
    "message": "Oh snap, something went wrong on our end. We're on it!",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": ""
    },
    "requestId": "",
    "cause": null
  }
}

• Method: GET
• Path: /image/models
• Tags: gen.pollinations.ai

Get a list of available image generation models with pricing, capabilities, and metadata. If an API key with model restrictions is provided, only allowed models are returned.

Array of:

• aliases (required)

  array

  Items:

  string

• name (required)

  string

• pricing (required)

  object

• context_window

  number

• description

  string

• input_modalities

  array

  Items:

  string

• is_specialized

  boolean

• output_modalities

  array

  Items:

  string

• reasoning

  boolean

• tools

  boolean

• voices

  array

  Items:

  string

Example:

[
  {
    "name": "",
    "aliases": [
      ""
    ],
    "pricing": {
      "propertyName*": 1,
      "currency": "pollen"
    },
    "description": "",
    "input_modalities": [
      ""
    ],
    "output_modalities": [
      ""
    ],
    "tools": true,
    "reasoning": true,
    "context_window": 1,
    "voices": [
      ""
    ],
    "is_specialized": true
  }
]

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 500,
  "success": false,
  "error": {
    "code": "INTERNAL_ERROR",
    "message": "Oh snap, something went wrong on our end. We're on it!",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": ""
    },
    "requestId": "",
    "cause": null
  }
}

• Method: GET
• Path: /text/models
• Tags: gen.pollinations.ai

Get a list of available text generation models with pricing, capabilities, and metadata. If an API key with model restrictions is provided, only allowed models are returned.

Array of:

• aliases (required)

  array

  Items:

  string

• name (required)

  string

• pricing (required)

  object

• context_window

  number

• description

  string

• input_modalities

  array

  Items:

  string

• is_specialized

  boolean

• output_modalities

  array

  Items:

  string

• reasoning

  boolean

• tools

  boolean

• voices

  array

  Items:

  string

Example:

[
  {
    "name": "",
    "aliases": [
      ""
    ],
    "pricing": {
      "propertyName*": 1,
      "currency": "pollen"
    },
    "description": "",
    "input_modalities": [
      ""
    ],
    "output_modalities": [
      ""
    ],
    "tools": true,
    "reasoning": true,
    "context_window": 1,
    "voices": [
      ""
    ],
    "is_specialized": true
  }
]

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 500,
  "success": false,
  "error": {
    "code": "INTERNAL_ERROR",
    "message": "Oh snap, something went wrong on our end. We're on it!",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": ""
    },
    "requestId": "",
    "cause": null
  }
}

• Method: POST
• Path: /v1/chat/completions
• Tags: gen.pollinations.ai

OpenAI-compatible chat completions endpoint.

Legacy endpoint: /openai (deprecated, use /v1/chat/completions instead)

Authentication (Secret Keys Only):

Include your API key in the Authorization header as a Bearer token:

Authorization: Bearer YOUR_API_KEY

API keys can be created from your dashboard at enter.pollinations.ai. Both key types consume Pollen. Secret keys have no rate limits.

• messages (required)

  array

  Items:

  Any of:

  • content (required)

    object

  • role (required)

    string

  • cache_control

    object

    • type (required)

      string, possible values: "ephemeral"

  • name

    string

  • content (required)

    object

  • role (required)

    string

  • cache_control

    object

    • type (required)

      string, possible values: "ephemeral"

  • name

    string

  • content (required)

    object

  • role (required)

    string

  • name

    string

  • role (required)

    string

  • cache_control

    object

    • type (required)

      string, possible values: "ephemeral"

  • content

    object

  • function_call

    object

  • name

    string

  • tool_calls

    array

    Items:

    • function (required)

      object

      • arguments (required)

        string

      • name (required)

        string

    • id (required)

      string

    • type (required)

      string

  • content (required)

    object

  • role (required)

    string

  • tool_call_id (required)

    string

  • cache_control

    object

    • type (required)

      string, possible values: "ephemeral"

  • content (required)

    object

  • name (required)

    string

  • role (required)

    string

• audio

  object

  • format (required)

    string, possible values: "wav", "mp3", "flac", "opus", "pcm16"

  • voice (required)

    string, possible values: "alloy", "echo", "fable", "onyx", "shimmer", "coral", "verse", "ballad", "ash", "sage", "amuch", "dan"

• frequency_penalty

  object, default: 0

• function_call

  object

• functions

  array

  Items:

  • name (required)

    string

  • description

    string

  • parameters

    object

• logit_bias

  object, default: null

• logprobs

  object, default: false

• max_tokens

  object

• modalities

  array

  Items:

  string, possible values: "text", "audio"

• model

  string, possible values: "openai", "openai-fast", "openai-large", "qwen-coder", "mistral", "openai-audio", "gemini", "gemini-fast", "deepseek", "grok", "gemini-search", "chickytutor", "midijourney", "claude-fast", "claude", "claude-large", "perplexity-fast", "perplexity-reasoning", "kimi", "gemini-large", "nova-fast", "glm", "minimax", "nomnom", default: "openai" — AI model for text generation. See /v1/models for full list.

• parallel_tool_calls

  boolean, default: true

• presence_penalty

  object, default: 0

• reasoning_effort

  string, possible values: "none", "minimal", "low", "medium", "high", "xhigh"

• repetition_penalty

  object

• response_format

  object

• seed

  object

• stop

  object

• stream

  object, default: false

• stream_options

  object

• temperature

  object, default: 1

• thinking

  object

• thinking_budget

  integer

• tool_choice

  object

• tools

  array

  Items:

  Any of:

  • function (required)

    object

    • name (required)

      string

    • description

      string

    • parameters

      object

    • strict

      object, default: false

  • type (required)

    string

  • type (required)

    string, possible values: "code_execution", "google_search", "google_maps", "url_context", "computer_use", "file_search"

• top_logprobs

  object

• top_p

  object, default: 1

• user

  string

Example:

{
  "messages": [
    {
      "content": "",
      "role": "system",
      "name": "",
      "cache_control": {
        "type": "ephemeral"
      }
    }
  ],
  "model": "openai",
  "modalities": [
    "text"
  ],
  "audio": {
    "voice": "alloy",
    "format": "wav"
  },
  "frequency_penalty": 0,
  "repetition_penalty": 0,
  "logit_bias": null,
  "logprobs": false,
  "top_logprobs": 0,
  "max_tokens": 0,
  "presence_penalty": 0,
  "response_format": {
    "type": "text"
  },
  "seed": -1,
  "stop": "",
  "stream": false,
  "stream_options": {
    "include_usage": true
  },
  "thinking": {
    "type": "disabled",
    "budget_tokens": 1
  },
  "reasoning_effort": "none",
  "thinking_budget": 0,
  "temperature": 1,
  "top_p": 1,
  "tools": [
    {
      "type": "function",
      "function": {
        "description": "",
        "name": "",
        "parameters": {
          "propertyName*": "anything"
        },
        "strict": false
      }
    }
  ],
  "tool_choice": "none",
  "parallel_tool_calls": true,
  "user": "",
  "function_call": "none",
  "functions": [
    {
      "description": "",
      "name": "",
      "parameters": {
        "propertyName*": "anything"
      }
    }
  ]
}

• choices (required)

  array

  Items:

  • content_filter_results

    object

  • finish_reason

    object

  • index

    integer

  • logprobs

    object

  • message

    object

    • role (required)

      string

    • audio

      object

    • content

      object

    • content_blocks

      object

    • function_call

      object

    • reasoning_content

      object

    • tool_calls

      object

• created (required)

  integer

• id (required)

  string

• model (required)

  string

• object (required)

  string

• usage (required)

  object

  • completion_tokens (required)

    integer

  • prompt_tokens (required)

    integer

  • total_tokens (required)

    integer

  • completion_tokens_details

    object

  • prompt_tokens_details

    object

• citations

  array

  Items:

  string

• prompt_filter_results

  object

• system_fingerprint

  object

• user_tier

  string, possible values: "anonymous", "seed", "flower", "nectar"

Example:

{
  "id": "",
  "choices": [
    {
      "finish_reason": "",
      "index": 0,
      "message": {
        "content": "",
        "tool_calls": [
          {
            "id": "",
            "type": "function",
            "function": {
              "name": "",
              "arguments": ""
            }
          }
        ],
        "role": "assistant",
        "function_call": {
          "arguments": "",
          "name": ""
        },
        "content_blocks": [
          {
            "type": "text",
            "text": "",
            "cache_control": {
              "type": "ephemeral"
            }
          }
        ],
        "audio": {
          "transcript": "",
          "data": "",
          "id": "",
          "expires_at": -9007199254740991
        },
        "reasoning_content": ""
      },
      "logprobs": {
        "content": [
          {
            "token": "",
            "logprob": 1,
            "bytes": [
              "[Max Depth Exceeded]"
            ],
            "top_logprobs": [
              {
                "token": "[Max Depth Exceeded]",
                "logprob": "[Max Depth Exceeded]",
                "bytes": "[Max Depth Exceeded]"
              }
            ]
          }
        ]
      },
      "content_filter_results": {
        "hate": {
          "filtered": true,
          "severity": "safe"
        },
        "self_harm": {
          "filtered": true,
          "severity": "safe"
        },
        "sexual": {
          "filtered": true,
          "severity": "safe"
        },
        "violence": {
          "filtered": true,
          "severity": "safe"
        },
        "jailbreak": {
          "filtered": true,
          "detected": true
        },
        "protected_material_text": {
          "filtered": true,
          "detected": true
        },
        "protected_material_code": {
          "filtered": true,
          "detected": true
        }
      }
    }
  ],
  "prompt_filter_results": [
    {
      "prompt_index": 0,
      "content_filter_results": {
        "hate": {
          "filtered": true,
          "severity": "safe"
        },
        "self_harm": {
          "filtered": true,
          "severity": "safe"
        },
        "sexual": {
          "filtered": true,
          "severity": "safe"
        },
        "violence": {
          "filtered": true,
          "severity": "safe"
        },
        "jailbreak": {
          "filtered": true,
          "detected": true
        },
        "protected_material_text": {
          "filtered": true,
          "detected": true
        },
        "protected_material_code": {
          "filtered": true,
          "detected": true
        }
      }
    }
  ],
  "created": -9007199254740991,
  "model": "",
  "system_fingerprint": "",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 0,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "prompt_tokens": 0,
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0
    },
    "total_tokens": 0
  },
  "user_tier": "anonymous",
  "citations": [
    ""
  ]
}

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • fieldErrors (required)

      object

    • formErrors (required)

      array

      Items:

      string

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 400,
  "success": false,
  "error": {
    "code": "BAD_REQUEST",
    "message": "Something was wrong with the input data, check the details for more info.",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": "",
      "formErrors": [
        ""
      ],
      "fieldErrors": {
        "propertyName*": [
          ""
        ]
      }
    },
    "requestId": "",
    "cause": null
  }
}

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 401,
  "success": false,
  "error": {
    "code": "UNAUTHORIZED",
    "message": "You need to authenticate by providing a session cookie or Authorization header (Bearer token).",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": ""
    },
    "requestId": "",
    "cause": null
  }
}

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 500,
  "success": false,
  "error": {
    "code": "INTERNAL_ERROR",
    "message": "Oh snap, something went wrong on our end. We're on it!",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": ""
    },
    "requestId": "",
    "cause": null
  }
}

• Method: GET
• Path: /text/{prompt}
• Tags: gen.pollinations.ai

Generates text from text prompts.

Authentication:

Include your API key either:

• In the Authorization header as a Bearer token: Authorization: Bearer YOUR_API_KEY
• As a query parameter: ?key=YOUR_API_KEY

API keys can be created from your dashboard at enter.pollinations.ai.

string

Example:

true

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • fieldErrors (required)

      object

    • formErrors (required)

      array

      Items:

      string

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 400,
  "success": false,
  "error": {
    "code": "BAD_REQUEST",
    "message": "Something was wrong with the input data, check the details for more info.",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": "",
      "formErrors": [
        ""
      ],
      "fieldErrors": {
        "propertyName*": [
          ""
        ]
      }
    },
    "requestId": "",
    "cause": null
  }
}

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 401,
  "success": false,
  "error": {
    "code": "UNAUTHORIZED",
    "message": "You need to authenticate by providing a session cookie or Authorization header (Bearer token).",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": ""
    },
    "requestId": "",
    "cause": null
  }
}

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 500,
  "success": false,
  "error": {
    "code": "INTERNAL_ERROR",
    "message": "Oh snap, something went wrong on our end. We're on it!",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": ""
    },
    "requestId": "",
    "cause": null
  }
}

• Method: GET
• Path: /image/{prompt}
• Tags: gen.pollinations.ai

Generate an image or video from a text prompt.

Image Models: flux (default), turbo, gptimage, kontext, seedream, nanobanana, nanobanana-pro

Video Models: veo, seedance

• veo: Text-to-video only (4-8 seconds)
• seedance: Text-to-video and image-to-video (2-10 seconds)

Authentication:

Include your API key either:

• In the Authorization header as a Bearer token: Authorization: Bearer YOUR_API_KEY
• As a query parameter: ?key=YOUR_API_KEY

API keys can be created from your dashboard at enter.pollinations.ai.

string, format: binary

Example:

{}

string, format: binary

Example:

{}

string, format: binary

Example:

{}

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • fieldErrors (required)

      object

    • formErrors (required)

      array

      Items:

      string

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 400,
  "success": false,
  "error": {
    "code": "BAD_REQUEST",
    "message": "Something was wrong with the input data, check the details for more info.",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": "",
      "formErrors": [
        ""
      ],
      "fieldErrors": {
        "propertyName*": [
          ""
        ]
      }
    },
    "requestId": "",
    "cause": null
  }
}

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 401,
  "success": false,
  "error": {
    "code": "UNAUTHORIZED",
    "message": "You need to authenticate by providing a session cookie or Authorization header (Bearer token).",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": ""
    },
    "requestId": "",
    "cause": null
  }
}

• error (required)

  object

  • code (required)

    string

  • details (required)

    object

    • name (required)

      string

    • stack

      string

  • message (required)

    object

  • timestamp (required)

    string

  • cause

    object

  • requestId

    string

• status (required)

  number

• success (required)

  boolean

Example:

{
  "status": 500,
  "success": false,
  "error": {
    "code": "INTERNAL_ERROR",
    "message": "Oh snap, something went wrong on our end. We're on it!",
    "timestamp": "",
    "details": {
      "name": "",
      "stack": ""
    },
    "requestId": "",
    "cause": null
  }
}

• Type: object

• name (required)

  string

• stack

  string

Example:

{
  "name": "",
  "stack": ""
}

• Type: object

• type (required)

  string, possible values: "ephemeral"

Example:

{
  "type": "ephemeral"
}

• Type: string

Example:

• Type: object

• hate

  object

  • filtered (required)

    boolean

  • severity (required)

    string, possible values: "safe", "low", "medium", "high"

• jailbreak

  object

  • detected (required)

    boolean

  • filtered (required)

    boolean

• protected_material_code

  object

  • detected (required)

    boolean

  • filtered (required)

    boolean

• protected_material_text

  object

  • detected (required)

    boolean

  • filtered (required)

    boolean

• self_harm

  object

  • filtered (required)

    boolean

  • severity (required)

    string, possible values: "safe", "low", "medium", "high"

• sexual

  object

  • filtered (required)

    boolean

  • severity (required)

    string, possible values: "safe", "low", "medium", "high"

• violence

  object

  • filtered (required)

    boolean

  • severity (required)

    string, possible values: "safe", "low", "medium", "high"

Example:

{
  "hate": {
    "filtered": true,
    "severity": "safe"
  },
  "self_harm": {
    "filtered": true,
    "severity": "safe"
  },
  "sexual": {
    "filtered": true,
    "severity": "safe"
  },
  "violence": {
    "filtered": true,
    "severity": "safe"
  },
  "jailbreak": {
    "filtered": true,
    "detected": true
  },
  "protected_material_text": {
    "filtered": true,
    "detected": true
  },
  "protected_material_code": {
    "filtered": true,
    "detected": true
  }
}

• Type: object

• completion_tokens (required)

  integer

• prompt_tokens (required)

  integer

• total_tokens (required)

  integer

• completion_tokens_details

  object

• prompt_tokens_details

  object

Example:

{
  "completion_tokens": 0,
  "completion_tokens_details": {
    "accepted_prediction_tokens": 0,
    "audio_tokens": 0,
    "reasoning_tokens": 0,
    "rejected_prediction_tokens": 0
  },
  "prompt_tokens": 0,
  "prompt_tokens_details": {
    "audio_tokens": 0,
    "cached_tokens": 0
  },
  "total_tokens": 0
}

• Type: object

• fieldErrors (required)

  object

• formErrors (required)

  array

  Items:

  string

• name (required)

  string

• stack

  string

Example:

{
  "name": "",
  "stack": "",
  "formErrors": [
    ""
  ],
  "fieldErrors": {
    "propertyName*": [
      ""
    ]
  }
}

• Type:

Example:

Union type for message content parts. Can be one of:

• Text content: { type: "text", text: string, cache_control?: CacheControl }
• Image content: { type: "image_url", image_url: { url: string, detail?: "auto" | "low" | "high", mime_type?: string } }
• Video content: { type: "video_url", video_url: { url: string, mime_type?: string } }
• Audio content: { type: "input_audio", input_audio: { data: string, format: "wav" | "mp3" | "flac" | "opus" | "pcm16" }, cache_control?: CacheControl }
• File content: { type: "file", file: { file_data?: string, file_id?: string, file_name?: string, file_url?: string, mime_type?: string }, cache_control?: CacheControl }
• Custom types: Any object with a type field for provider-specific extensions

Example (text):

{
  "type": "text",
  "text": "Hello, world!"
}

Example (image):

{
  "type": "image_url",
  "image_url": {
    "url": "https://example.com/image.jpg",
    "detail": "high"
  }
}

Example (video):

{
  "type": "video_url",
  "video_url": {
    "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
  }
}