openrouter-multimodal

Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP.

stdiocommunityservice

Package Details

@stabgan/openrouter-mcp-multimodal

4.5.1•https://www.npmjs.com/package/@stabgan/openrouter-mcp-multimodal

Transportstdio

Environment Variables

OPENROUTER_API_KEY(str)

RequiredSecret

OpenRouter API key. Get one free at https://openrouter.ai/keys

OPENROUTER_DEFAULT_MODEL(str)

Default model for chat + analyze tools. Defaults to nvidia/nemotron-nano-12b-v2-vl:free.

OPENROUTER_OUTPUT_DIR(str)

Sandbox root for save_path on generate_* tools. Defaults to the current working directory.

OPENROUTER_MAX_TOKENS(str)

Default max_tokens for chat_completion when unset in the request.

OPENROUTER_PROVIDER_SORT(str)

price / throughput / latency

OPENROUTER_PROVIDER_IGNORE(str)

CSV of provider slugs to exclude.

OPENROUTER_PROVIDER_ORDER(str)

JSON array or CSV of preferred provider IDs.

OPENROUTER_PROVIDER_QUANTIZATIONS(str)

CSV of quantization levels (fp16,int8).

OPENROUTER_PROVIDER_REQUIRE_PARAMETERS(str)

true/false. Require providers to support all request params.

OPENROUTER_PROVIDER_DATA_COLLECTION(str)

allow/deny

OPENROUTER_PROVIDER_ALLOW_FALLBACKS(str)

true/false

OPENROUTER_CACHE_RESPONSES(str)

Enable response caching server-wide. Sends X-OpenRouter-Cache: true on every chat/analyze call unless overridden per-request. Zero tokens billed on cache hits.

OPENROUTER_INCLUDE_REASONING(str)

Enable reasoning tokens passthrough server-wide. Adds _meta.reasoning to chat_completion responses for DeepSeek R1 / Gemini Thinking / Opus 4.7.

docker.io/stabgan/openrouter-mcp-multimodal:4.5.1

https://hub.docker.com/r/stabgan/openrouter-mcp-multimodal

Transportstdio

Environment Variables

OPENROUTER_API_KEY(str)

RequiredSecret

OpenRouter API key. Get one free at https://openrouter.ai/keys