API reference

Models catalog

Every serverless model, pricing, and context window. Pull it live from the API.

Live catalog endpoint

curl https://api.runaii.cloud/v1/models

{
  "object": "list",
  "data": [
    {
      "id": "glm-5.3-flash",
      "object": "model",
      "context_length": 1000000,
      "pricing": { "prompt": 0.15, "completion": 0.5, "input_cache_read": 0.03 },
      "upstream_id": "glm-5.3-flash"
    }
  ]
}

Pricing is USD per 1M tokens; input_cache_read appears on models with prompt caching. Integrate against this endpoint rather than hardcoding rates — the catalog is the source of truth and prices can change.

Highlights (at time of writing)

Model	Context	Prompt $/1M	Cached $/1M	Completion $/1M	Best for
`glm-5.3-flash`	1M	$0.15	$0.03	$0.50	Fast multimodal workhorse, RAG
`glm-5.3`	1M	$1.40	$0.26	$4.40	Frontier agentic + coding
`kimi-k3`	1M	$3.00	—	$15.00	Long-context reasoning
`deepseek-v4-pro`	1M	$1.32	$0.044	$3.96	SWE-bench leader, math
`deepseek-v4-flash`	1M	$0.22	$0.022	$0.66	High-volume pipelines
`qwen3.8-max`	262k	$2.00	—	$6.00	Multilingual flagship
`gpt-oss-120b`	131k	$0.15	$0.015	$0.60	Efficient reasoning
`minimax-m3`	512k	$0.30	$0.03	$1.20	Long-context generalist
`llama-3.3-70b`	131k	$0.23	$0.023	$0.85	Ecosystem-standard
`qwen3-embedding-8b`	41k	$0.10	—	—	Multilingual embeddings

Also available: qwen3-reranker-8b (reranking), whisper-v3 (audio), image models via /v1/images/generations.

OpenAI / Anthropic compatibility

OpenAI SDK: swap base_url to https://api.runaii.cloud/v1 — done
Anthropic SDK clients: POST /api/messages accepts the Anthropic /v1/messages dialect and translates automatically