Model Catalog

ai& currently serves the open-weight models below. The list is dynamic — each organization sees only what it has access to, so the source of truth is always GET /v1/models.

Quick picks

Free to prototype

google/gemma-3-27b-it and qwen/qwen3.5-9b — no charges, ideal for evals.

Best price-to-performance

openai/gpt-oss-120b at $0.15 / $0.60 per 1M tokens — reasoning + tool calling.

Multimodal

google/gemma-4-31b-it for image + video, moonshotai/kimi-k2.6 for image + document.

Largest context

Every Qwen3.5 variant, google/gemma-4-31b-it, and moonshotai/kimi-k2.6 — 262K tokens.

Available models

Model ID	Capabilities	Context	Input / 1M	Output / 1M
`google/gemma-3-27b-it`	—	131K	Free	Free
`qwen/qwen3.5-9b`	reasoning, tool_calling	262K	Free	Free
`openai/gpt-oss-120b`	reasoning, tool_calling	131K	$0.15	$0.60
`google/gemma-4-31b-it`	reasoning, tool_calling, vision, video, document	262K	$0.20	$0.50
`qwen/qwen3.5-27b`	reasoning, tool_calling	262K	$0.25	$1.80
`deepseek-ai/deepseek-v3.2`	reasoning, tool_calling	164K	$0.50	$1.50
`qwen/qwen3.5-397b-a17b`	reasoning, tool_calling	262K	$0.55	$3.50
`moonshotai/kimi-k2.6`	reasoning, tool_calling, vision, document	262K	$0.85	$3.50
`zai-org/glm-5`	reasoning, tool_calling	203K	$0.95	$2.90
`zai-org/glm-5.1`	reasoning, tool_calling	203K	$1.40	$4.40

Sorted by output price, low to high. Prices are USD per million tokens — see Pricing for how the formula computes a per-request cost.

Capability values

Capability	Meaning
`reasoning`	Supports `reasoning_effort` and emits internal reasoning tokens (charged as output).
`tool_calling`	Accepts `tools` / `tool_choice`. See Tool Calling.
`vision`	Accepts image inputs (`image_url` or `file_id`). See Vision.
`video`	Accepts video inputs by `file_id`. See Video Understanding.
`document`	Accepts PDF / document inputs.

A capability absent from the list means requests using that feature will be rejected at validation time.

Listing your models programmatically

curl https://api.aiand.com/v1/models \
  -H "Authorization: Bearer sk-your-api-key"

from openai import OpenAI

client = OpenAI(base_url="https://api.aiand.com/v1", api_key="sk-...")
for m in client.models.list().data:
    print(m.id, m.context_window, m.capabilities)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.aiand.com/v1", apiKey: "sk-..." });
const { data } = await client.models.list();
for (const m of data) console.log(m.id, m.context_window, m.capabilities);

Response shape (OpenAI surface)

{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-oss-120b",
      "object": "model",
      "name": "openai/gpt-oss-120b",
      "owned_by": "ai&",
      "provider": "openai",
      "context_window": 131072,
      "capabilities": ["reasoning", "tool_calling"],
      "description": "OpenAI GPT OSS 120B",
      "input_per_1m": "0.150000",
      "output_per_1m": "0.600000",
      "created": 1775474514
    }
  ]
}

Field	Type	Meaning
`id`	string	The value to pass as `"model"` in chat / responses / messages.
`provider`	string	The lab that released the open weights (`openai`, `google`, `qwen`, …). All models are hosted on ai& infrastructure regardless of provider.
`context_window`	int	Max combined input + output tokens.
`capabilities`	string[]	Supported features — see the table above.
`input_per_1m`	string	USD per 1 million input tokens. Numeric stored as a string for precision.
`output_per_1m`	string	USD per 1 million output tokens.

Anthropic surface

GET /v1/models with an anthropic-version header returns the Anthropic shape — data[].display_name, created_at, has_more, first_id, last_id. Pricing and capabilities are only on the OpenAI surface.