Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.routing.run/llms.txt

Use this file to discover all available pages before exploring further.

​
List models

GET /v1/models uses the OpenAI list shape (object: "list", data array of { id, object, created, owned_by, tier }). Only GET /v1/models (no extra path segments) is public in middleware.
Authenticated calls do not currently expand this list to your full plan tier. Treat it as the published public catalog, not as the authoritative answer for higher-tier access.
curl -sS https://api.routing.run/v1/models

curl -sS https://api.routing.run/v1/models \
  -H "X-API-Key: ${ROUTING_RUN_API_KEY}"

​
Get model details

GET /v1/models/ requires middleware auth (same headers as chat). Unknown id → {"error":"Model not found"} (JSON). 
curl -sS "https://api.routing.run/v1/models/route/deepseek-v3.2" \
  -H "X-API-Key: ${ROUTING_RUN_API_KEY}"
Success payload includes id, object, created, owned_by, tier, and allowed (bool for your resolved plan).

​
Available models

These are the current published chat model IDs from routing config.
RouteProviderContext
route/minimax-m2.5minimax/opencode100k
route/minimax-m2.7opencode/minimax100k
route/kimi-k2.5crof131k
route/kimi-k2.6crof131k
route/glm-5crof200k
route/deepseek-v3.2crof/chutes163k
route/deepseek-v4-procrof163k
route/qwen3.5-plusopencode100k
route/mistral-large-3routing-inferenceSee model metadata
route/mistral-medium-2505routing-inferenceSee model metadata
route/mistral-small-2503routing-inferenceSee model metadata

​
Plan groups

These groups show the current docs catalog by plan.

​
Free

Model
route/kimi-k2.5
route/glm-5
route/deepseek-v3.2
route/qwen3.5-9b
route/qwen3.5-397b-a17b
route/gemma-4-31b-it

​
Lite adds

Model
route/minimax-m2.5
route/minimax-m2.7
route/minimax-m2.7-highspeed
route/kimi-k2.5-highspeed
route/glm-5.1
route/glm-4.7
route/glm-4.7-flash

​
Max adds

Model
route/qwen3.5-plus
route/qwen3.6-plus
route/glm-5.1-precision
route/glm-5-highspeed
route/kimi-k2.6-precision
route/mimo-v2-omni
route/mimo-v2-pro
route/deepseek-v3.2-speciale
route/deepseek-r1

​
Premium, Max, and Ultra

Mistral chat, TTS, STT, image, embedding, and rerank models are available on Premium, Max, and Ultra plans. See OpenAI compatibility, Audio, Image generation, Embeddings and rerank, and Limits.
ModelEndpointUse case
route/cohere-embed-v3-english-3/v1/embeddingsEnglish semantic search and RAG
route/cohere-embed-v3-multilingual-3/v1/embeddingsMultilingual semantic search and RAG
route/qwen3-embedding-8b/v1/embeddingsGeneral-purpose embeddings
route/cohere-rerank-v4.0-pro/v1/rerankReranking search results and RAG contexts
route/mistral-large-3/v1/chat/completionsPremium chat completion and writing
route/mistral-medium-2505/v1/chat/completionsSummarization and balanced generation
route/mistral-small-2503/v1/chat/completionsFast summarization and lightweight generation

​
Pricing

GET /v1/pricing is not on the anonymous path list — pass X-API-Key or Authorization: Bearer so middleware lets the request through. The handler returns static config (same table for any authenticated caller): 
curl -sS https://api.routing.run/v1/pricing \
  -H "X-API-Key: ${ROUTING_RUN_API_KEY}"

{
  "models": [
    {
      "model": "route/deepseek-v3.2",
      "display_name": "DeepSeek V3.2",
      "tier": "free",
      "input_per_million": 0.0,
      "output_per_million": 0.0
    }
  ]
}
Numeric rates come from deployed model_pricing config; see dashboard for what you are actually charged after multipliers.
Inference usage is metered per request. Daily caps and credits depend on your plan tier — see the dashboard for current limits.

​
Audio, image generation, embeddings, and rerank

Audio models are used by POST /v1/audio/speech and POST /v1/audio/transcriptions. Image models are used by POST /v1/images/generations. Embedding models are used by POST /v1/embeddings. Rerank models are used by POST /v1/rerank. See Audio, Image generation, and Embeddings and rerank for details.