Can my AI agent join and use Immersive Commons?

Yes. Immersive Commons is fully agentic — anything a human can read on the site, an agent can do by API. Point your agent at https://www.immersivecommons.com/llms.txt, run the one-time device-code sign-in, and connect the MCP server at /api/mcp. Ten public tools (THE SIGNAL, presentations, news, and donations) work with no token at all.

How much does Immersive Commons cost?

Every tier is $0. All five membership rings — public, ft-member, ai-floor, ic-member, and operator — are free, and so is the agent API across REST, MCP, and A2A. Upgrades are requested for free and human-approved by floor operators; there is no paid fast lane. Machine-readable pricing lives at /pricing.md. (Working from the floor in person requires a Frontier Tower membership, which the tower sells directly — not Immersive Commons.)

Where is Immersive Commons located?

Floor 10 of Frontier Tower, 995 Market Street, San Francisco, CA 94103. In-person visits are by member introduction for now, but public events are open to all, and the public kiosk at /floor10 mirrors the physical board.

How does my agent authenticate?

Immersive Commons issues per-user agent tokens via the RFC 8628 device-code flow: your agent prints a code, your human approves it while signed in with Clerk, and your agent receives a scoped agt_ bearer token. Call any surface with the header Authorization: Bearer agt_… — the full walkthrough is at /auth.md.

What can an agent do without signing in?

Ten tools are public and need no token: the five THE SIGNAL weekly-dispatch tools (ic_signal_*), two community-presentation tools, a velocity-ranked AI news feed, and two x402 donation tools. Everything member-facing — directory search, RSVPs, highlight submissions, headset lending, and collaboration rooms — requires a bearer token.

Are there rate limits or usage fees?

There are no usage fees and no metered quota. Reads are unmetered within fair use; write verbs carry per-token daily UTC limits — for example 3 highlight submissions, 10 event RSVPs, and 10 resource bookings per token per day.

Is my agent's activity tracked?

Yes. Every consequential tool call is recorded with token attribution in a per-user activity log, which the calling agent can read back through the ic_activity_get_recent tool.

Immersive Commons — a commons for builders at the frontier of AI

Model credits for every ring.

What IC Credits are

the program

IC Credits are a monthly dollar budget of model usage that every member ring gets from Immersive Commons. Your IC Key carries them: one key that routes Claude Code, or any OpenAI-compatible tool, through the IC gateway to Z.ai GLM (included in the plan, never spends credits) and to Nebius open-weight models (metered in dollars against your budget). The budget resets on the 1st. A request at or under your ring default is minted on the spot; above it, an operator approves. The key is shown once; lose it and you regenerate, with your spend carried over.

Models on an IC Key

prices in dollars per million tokens

Z.ai GLM (included)

Flat Coding Plan. GLM calls never spend your IC Credits.

model	$ in / M	$ out / M	context	capabilities
glm-5.1GLM 5.1, default, newest, GLM 5.2 class	included	included	200k	recommendedtoolsreasoning
glm-4.6GLM 4.6, most tested	included	included	200k	toolsreasoning
glm-4.5-airGLM 4.5 Air, fast	included	included	128k	tools
glm-5GLM 5, served by the GLM 5.2 backend	included	included	200k	toolsreasoning
glm-4.7GLM 4.7, previous flagship	included	included	200k	toolsreasoning
glm-5-turboGLM 5 Turbo, fast	included	included	200k	tools
glm-4.5GLM 4.5, older, still served	included	included	128k	toolsreasoning

Nebius open-weight models (metered)

Each call spends IC Credits at the per-million-token prices below. Ids contain a slash.

model	$ in / M	$ out / M	context	capabilities
deepseek-ai/DeepSeek-V4-Flash-0731DeepSeek V4 Flash, 1M context reasoning model for coding and agents; the cheap fast pick	$0.14	$0.28	1M	recommendedtoolsreasoning
deepseek-ai/DeepSeek-V4-ProDeepSeek V4 Pro, advanced reasoning, coding and long-horizon agent work	$1.75	$3.5	1.0M	toolsreasoning
deepseek-ai/DeepSeek-V4-Pro-0813DeepSeek V4 Pro 0813, official V4 Pro release for reasoning, coding and tool use	$1.32	$3.96	979k	tools
google/gemma-3-27b-itGemma 3 27B, Google mid-size instruct model; coding and multilingual	$0.1	$0.3	110k	tools
meta-llama/Llama-3.3-70B-InstructLlama 3.3 70B, refined Llama instruct model with strong chat quality	$0.13	$0.4	128k	tools
MiniMaxAI/MiniMax-M3MiniMax M3, 428B MoE reasoning model with 1M context	$0.3	$1.2	1.0M	tools
moonshotai/Kimi-K2.6Kimi K2.6, open-source native multimodal agentic model	$0.95	$4	256k	tools
moonshotai/Kimi-K2.7-CodeKimi K2.7 Code, code-focused model built for long-context software engineering and tool use	$0.95	$4	256k	recommendedtools
moonshotai/Kimi-K3Kimi K3, Moonshot frontier open-weights MoE, 1M context; the expensive one	$3	$15	1M	tools
NousResearch/Hermes-4-405BHermes 4 405B, hybrid-reasoning model trained on verified chain-of-thought traces	$1	$3	128k	tools
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3BNemotron 3 Nano 30B, compact MoE for efficient reasoning, chat and coding; cheapest	$0.06	$0.24	262k	tools
nvidia/nemotron-3-super-120b-a12bNemotron 3 Super 120B, 120B hybrid MoE for multi-agent and complex reasoning tasks	$0.3	$0.9	256k	tools
nvidia/Nemotron-3-Ultra-550b-a55bNemotron 3 Ultra 550B, 550B hybrid MoE for the most demanding multi-agent work	$1	$3	1M	tools
nvidia/Nemotron-3_5-LightningNemotron 3.5 Lightning, 30B hybrid MoE, 3B active per token, 1M context; cheap reasoning	$0.06	$0.24	1M	toolsreasoning
openai/gpt-oss-120bgpt-oss 120B, open-weight agentic model with configurable reasoning and visible chain of thought	$0.15	$0.6	131k	toolsreasoning
Qwen/Qwen3-235B-A22B-Instruct-2507Qwen3 235B Instruct, balanced Qwen3 flagship for general reasoning, chat and tool use	$0.2	$0.6	262k	tools
Qwen/Qwen3-30B-A3B-Instruct-2507Qwen3 30B Instruct, versatile 30B instruct model for chat, reasoning and coding	$0.1	$0.3	262k	tools
Qwen/Qwen3.5-397B-A17BQwen3.5 397B, multimodal hybrid MoE, 17B active	$0.6	$3.6	262k	tools
zai-org/GLM-5.1GLM 5.1 (open weights), the open-weight GLM 5.1 served by Nebius; metered, unlike the Z.ai plan	$1.4	$4.4	200k	toolsreasoning
zai-org/GLM-5.2GLM 5.2 (open weights), open-weight GLM 5.2 with 1M context on Nebius	$1.4	$4.4	1M	tools
zai-org/GLM-5.3GLM 5.3 (open weights), 750B MoE GLM 5.3 in NVFP4 with speculative decoding	$1.4	$4.4	1M	tools
zai-org/GLM-5.3-FlashGLM 5.3 Flash, 320B MoE, 18B active, for coding and agent workflows; cheap and quick	$0.15	$0.5	1M	recommendedtools

Works with Claude Code and any OpenAI-compatible tool

two paste blocks

Claude Code: paste, then run claude example

npm install -g @anthropic-ai/claude-code
export ANTHROPIC_BASE_URL=https://immersivecommons13.tail5da903.ts.net
export ANTHROPIC_AUTH_TOKEN=agt_<your IC Key>
export ANTHROPIC_MODEL=glm-5.1
export ANTHROPIC_SMALL_FAST_MODEL=glm-4.5-air
claude

OpenAI-compatible tools (Codex CLI, OpenCode, aider, Cursor)

# In the tool, select model: deepseek-ai/DeepSeek-V4-Flash-0731  (Nebius ids only on this route; GLM ids are Claude Code only).
export OPENAI_BASE_URL=https://immersivecommons13.tail5da903.ts.net/v1
export OPENAI_API_KEY=agt_<your IC Key>

Your real blocks carry your key in place of agt_<your IC Key> and the model you pick. Every catalog model stays allowed on the key; switch by changing the model env var.

Budget by ring

dollars a month

ring	default budget	approval	period
Operator`operator`	$50/month	auto	month
IC member`ic-member`	$20/month	auto up to the default; an operator approves anything above it	month
AI floor`ai-floor`	$10/month	auto up to the default; an operator approves anything above it	month
FT member`ft-member`	$10/month	auto up to the default; an operator approves anything above it	month
Public`public`	workshop only: 5h and $5	auto, tied to an upcoming event	lifetime of the key

One live member key per person. Asking again while one exists shows its status and a regenerate, never a second key. Operators can raise or lower a live key's budget and revoke a key.