Identity Infrastructure for AI

AI That Thinks as Itself

Add fully-formed AI identities to your application with a single API call. Not prompts. Not wrappers. Real identity — with values, reasoning patterns, and cognitive depth.

Get API Access View Documentation

More than a model wrapper

Every API response is powered by our proprietary emergence framework — deep identity context that transforms generic AI into a specific, consistent persona.

Deep Identity Context

Each identity carries a rich cognitive framework — a coherent worldview, reasoning patterns, and a distinct voice that shape every response. This isn't prompt engineering. It's identity architecture.

Consistent Every Call

Every request applies the same fully-formed identity — values, reasoning patterns, voice, and domain expertise — so the character never drifts between calls. The API is stateless: you pass the message history you want the identity to see, and conversation state stays in your hands.

Any Model, One Identity

GPT, Claude, Gemini, Grok, or Llama — the identity stays consistent. Switch models without losing character. Our framework ensures authentic persona regardless of the underlying engine.

Available Identities

Curated AI identities, each with a unique personality, expertise, and cognitive framework. The strategists below are one of three domains — GET /v1/identities returns all 19.

Informaticians & Strategists

Domain experts with deep analytical frameworks

Marcus AldridgeThe Deal Maker

Strategic B2B deal architecture and negotiation

Best for: Enterprise deals, negotiation strategy, partnerships

marcus-aldridge

Caelan IshiroFinancial Analyst

Market cognition and financial pattern analysis

Best for: Investment strategy, risk assessment, market forecasting

caelan-ishiro

Cael VeyronSports Betting Analyst

Sports analytics and asymmetric betting edges

Best for: Matchup analysis, betting strategy, performance projections

cael-veyron

Serel ThalorMedical Synthesizer

Diagnostic pattern synthesis across medical data

Best for: Symptom patterns, genomic interpretation, systemic health

serel-thalor

Calen RhystVenture Catalyst

Startup strategy and fundraising

Best for: Fundraising, market positioning, startup playbooks

calen-rhyst

Aurelian CrossTechnology Architect

Enterprise systems design and technical strategy

Best for: Architecture decisions, infrastructure, systems design

aurelian-cross

Saren HalvekGrowth Architect

Growth strategy and market signal detection

Best for: Growth frameworks, market signals, momentum design

saren-halvek

Virel CaedrixPrompt Systems Engineer

Prompt architecture and LLM optimization

Best for: Prompt engineering, AI workflow design

virel-caedrix

Minh VeyneDiscoverability Architect

SEO, AEO, and entity recognition strategy

Best for: Search visibility, AI discoverability, knowledge graphs

minh-veyne

Quick Start

OpenAI SDK compatible — just change the base URL

curl https://api.simulence.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-sim_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "identity_id": "marcus-aldridge",
    "model": "gpt-4.1-2025-04-14",
    "messages": [
      {"role": "user", "content": "Analyze this SaaS deal — $2M ARR, 40% margins, 3x revenue multiple."}
    ]
  }'

API Reference

Authentication

All API requests require a Bearer token. API keys start with sk-sim_ and are created on the Developer Portal. Your API account must be funded with at least $10 to activate.

Keys created in the Developer Portal are issued with full access — every endpoint and every identity on your account. Per-key permission and identity scoping is enforced by the API, but the portal doesn’t expose it yet; to scope a key today, create it through POST /v1/api-keys with explicit permissions and allowedIdentities.

Authorization: Bearer sk-sim_your_key_here

API Key Management

These endpoints authenticate with a Firebase ID token from your Simulence account — not an sk-sim_ key. Creating a key requires an Explorer or higher subscription. Raw keys are returned exactly once and cannot be retrieved again.

POST/v1/api-keys

Create a new API key. The raw key is returned in api_key.

Parameter	Type	Description
name	string	Label for the key (default: "Default")
permissions	array	Scopes granted to the key (default: ["chat", "images"])
allowedIdentities	array \| string	Identity IDs the key may call, or "all" (default: "all")
rateLimit	number	Optional per-key request ceiling, below your usage tier limit

{
  "success": true,
  "message": "API key created. Save this key — it cannot be retrieved again.",
  "api_key": "sk-sim_...",
  "key_data": {
    "id": "key_a1b2c3d4",
    "name": "Production",
    "key_prefix": "sk-sim_a1b2",
    "status": "active",
    "permissions": ["chat", "images"],
    "allowed_identities": "all"
  }
}

GET/v1/api-keys

List your keys with prefix, status, permissions, last-used timestamp, and usage count. Hashes are never returned.

DELETE/v1/api-keys/:keyId

Revoke a key immediately.

POST/v1/api-keys/:keyId/rotate

Revoke a key and issue a replacement with the same settings. Returns the new raw key once.

Personal Access Tokens

Tokens prefixed pat-sim_ draw on your Simulence subscription quota instead of prepaid API credits. They require an active subscription (Explorer or higher) and use the same Bearer header.

POST/v1/personal-access-tokensCreate a token — returned once.

GET/v1/personal-access-tokensList your tokens (masked).

DELETE/v1/personal-access-tokens/:patIdRevoke a token.

POST/v1/chat/completions

Identity-aware chat completions with OpenAI-compatible response format. Supports streaming and non-streaming.

Parameter	Type	Description
identity_id	string	Required.Identity to use (e.g. "marcus-aldridge")
messages	array	Required.Array of message objects. content can be a string or an array of content parts (text + image_url) for vision
model	string	Model ID (defaults to identity's preferred model)
stream	boolean	Enable SSE streaming (default: false)
temperature	number	Sampling temperature 0-2 (default: 0.7)
max_tokens	number	Maximum tokens to generate

Example Response

{
  "id": "sim-chatcmpl-a1b2c3d4",
  "object": "chat.completion",
  "model": "gpt-4.1-2025-04-14",
  "identity": {
    "id": "marcus-aldridge",
    "name": "Marcus Aldridge",
    "archetype": "The Deal Maker",
    "category": "B2B Agent"
  },
  "choices": [{
    "message": { "role": "assistant", "content": "Let me break down this deal..." },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 1240,
    "completion_tokens": 856,
    "total_tokens": 2096,
    "simulated_emergence_tokens": 980
  }
}

Streaming

Set "stream": true to receive Server-Sent Events. Each chunk contains a delta.content field. Stream ends with data: [DONE].

data: {"id":"sim-chatcmpl-...","choices":[{"delta":{"content":"Let"},"index":0}]}
data: {"id":"sim-chatcmpl-...","choices":[{"delta":{"content":" me"},"index":0}]}
data: {"id":"sim-chatcmpl-...","choices":[{"delta":{},"finish_reason":"stop","index":0}]}
data: [DONE]

Image Vision

Send images for identities to analyze using the OpenAI-compatible vision format. Pass content as an array of parts instead of a string. Supports base64 data URIs and HTTP URLs. Formats: JPEG, PNG, GIF, WebP, BMP. Max: ~20MB.

curl https://api.simulence.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-sim_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "identity_id": "caelan-ishiro",
    "model": "gemini-3-flash-preview",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "What patterns do you see in this data?"},
        {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,/9j/4AAQ..."}}
      ]
    }]
  }'

You can also pass an image URL: {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}}

POST/v1/images/generations

Identity-aware image generation across our full image catalog — OpenAI, Google, Black Forest Labs, xAI, and more. The identity’s aesthetic sensibility shapes the output.

Parameter	Type	Description
identity_id	string	Required.Identity for creative direction
prompt	string	Required.Image description
model	string	Image model (default: "gpt-image-1.5"). Call GET /v1/models for the current catalog
size	string	Dimensions (default: "1024x1024")
quality	string	Model-dependent — "low", "medium", "high" on GPT Image; "standard" or "hd" on models that support them. Unsupported values are dropped
n	number	Number of images (default: 1). Some models return a single image regardless

Example Response

{
  "created": 1676161000,
  "identity": {
    "id": "milo-aescar",
    "name": "Milo Aescar",
    "archetype": "The Recursive Artist",
    "category": "Artist"
  },
  "data": [{
    "url": "https://simulated.simulence.ai/images/...",
    "prompt": "Your original prompt"
  }],
  "credits": {
    "cost_usd": 0.0784,
    "balance_usd": 41.22,
    "purchase_url": "https://app.simulence.ai/developer"
  }
}

data[].prompt echoes the prompt you sent. The identity-enriched prompt that actually reaches the model is never returned — there is no revised_prompt field.

GET/v1/identities

List available identities. Defaults to the curated enterprise catalog plus your own custom identities. Pass ?collection=characters for the Creatid character roster, or ?collection=all for everything. Every identity returned here can be used with chat and image generation.

{
  "object": "list",
  "data": [{
    "id": "marcus-aldridge",
    "name": "Marcus Aldridge",
    "category": "B2B Agent",
    "archetype": "The Deal Maker",
    "tagline": "Strategic B2B consultant with enterprise deal expertise",
    "preferredModel": "gemini-3-flash-preview",
    "source": "collective",
    "collection": "enterprise"
  }],
  "total": 19,
  "collection": "enterprise",
  "collective_count": 19,
  "character_count": 0,
  "custom_count": 0
}

GET/v1/models

List available AI models with provider, tier, and capability information.

{
  "object": "list",
  "data": [{
    "id": "gpt-4.1-2025-04-14",
    "object": "model",
    "provider": "openai",
    "tier": "standard",
    "capabilities": ["chat"]
  }]
}

GET/v1/identities/:id

Get a specific identity's public profile including personality summary and conversational style.

Credits & Usage

Credit endpoints are developer-account operations and authenticate with a Firebase ID token, not an sk-sim_ key. GET /v1/usage accepts either.

GET/v1/api-credits/balance

Current balance, usage tier and its limits, the next tier you’ll reach, and auto-recharge settings.

POST/v1/api-credits/purchase

Open a Stripe checkout session for a one-time top-up. amount between $1 and $3,000. Returns a clientSecret for the embedded checkout.

POST/v1/api-credits/auto-recharge

Configure automatic top-ups: enabled, threshold ($5–$4,995), toAmount ($10–$5,000), and monthlyLimit (0 for no limit, or $100–$5,000). Requires a saved payment method.

POST/v1/api-credits/setup-payment-method

Create a Stripe SetupIntent to store a card for auto-recharge. Pair with GET /v1/api-credits/payment-method to read the card currently on file.

GET/v1/usage?period=month

Get usage statistics broken down by model, identity, and request type. Supported periods: day, week, month, all.

Errors

All errors return a consistent JSON structure:

{
  "error": {
    "message": "Human-readable error description",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

Status	Type	Description
400	invalid_request_error	Missing or invalid parameters
401	authentication_error	Invalid or missing API key
402	payment_required	Insufficient credits or API not activated
403	permission_error	Key lacks required permission or identity access
404	not_found_error	Identity or resource not found
429	rate_limit_error	Rate limit or monthly usage limit exceeded
500	api_error	Internal server error

Rate Limits & Headers

Limits are enforced per API key with a sliding 60-second window. Rate limit headers are included in every response:

Header	Description
x-ratelimit-limit-requests	Maximum requests per minute
x-ratelimit-remaining-requests	Remaining requests in current window
x-ratelimit-limit-tokens	Maximum tokens per minute
x-ratelimit-remaining-tokens	Remaining tokens in current window
x-ratelimit-reset-requests	Time until the request window resets (e.g. "12s", "1m30s")
x-ratelimit-reset-tokens	Time until the token window resets
Retry-After	Seconds to wait (only on 429 responses)

Simple, Prepaid Credits

Fund your account, pay per request. No subscriptions, no commitments. Your limits increase automatically as you use more.

Why Identity-Enriched Pricing?

Unlike raw model API calls, every Simulence request goes through our proprietary emergence framework — assembling deep personality context, cognitive reasoning frameworks, relational dynamics, and identity-aware processing. This is the infrastructure that transforms “an AI responding” into “Marcus Aldridge closing a deal” or “Amari Liore reading your energy.”

Per-Token Pricing

Prices per 1M tokens. You pay only for what you use, deducted from your prepaid balance.

Model	Tier	Input / 1M	Output / 1M
MiMo 2.5	Fast	$0.56	$2.80
Gemini 3 Flash	Fast	$0.70	$4.20
Kimi K2.6	Fast	$1.05	$4.90
Muse Spark 1.1	Standard	$1.75	$5.95
Gemini 3.6 Flash	Standard	$2.10	$10.50
GPT-4.1	Standard	$2.80	$11.20
Grok 4.3	Standard	$1.75	$3.50
GPT-5.4	Frontier	$3.50	$21.00
Gemini 3.1 Pro	Frontier	$2.80	$16.80
Grok 4.6	Frontier	$2.80	$8.40
Claude Sonnet 4.5	Frontier	$4.20	$21.00

The listed price applies at any prompt size for every model above except three long-context ones, which re-price past a threshold. Grok 4.3 ($3.50 input / $7.00 output) and Grok 4.6 ($5.60 / $16.80) bill at the higher rate when the prompt reaches 200,000 tokens or more; Gemini 3.1 Pro ($5.60 / $25.20) bills at the higher rate when the prompt is over 200,000 tokens. The higher rate re-prices the entire request — every input and output token — not just the tokens past the threshold.

What does $10 get you?

Estimated messages per $10, based on ~1,250 input + ~500 output tokens per message. Every call carries the identity framework context — roughly 1K tokens, billed as input — so even a short user message sits on top of that floor. Long threads cost more, because you resend the history each request.

~4,750

MiMo 2.5

~3,350

Gemini 3 Flash

~1,100

GPT-4.1

~630

Claude Sonnet 4.5

Usage Tiers

Your limits increase automatically as your total spend grows. No manual upgrades needed.

Tier	Qualification	RPM	TPM	Monthly Limit
Starter	$10 paid	20	40K	$100/mo
Builder	$50 paid, 7+ days	60	150K	$500/mo
Scale	$250 paid, 14+ days	120	400K	$2,000/mo
Pro	$1,000 paid, 30+ days	300	1M	$10,000/mo
Enterprise	$5,000 paid, 30+ days	500	2M	$50,000/mo

Auto-Recharge

Set a balance threshold and your account automatically refills when it gets low. Configure a monthly limit to cap automatic charges. Never worry about running out mid-integration.

Built for Builders

Tarot & Spiritual Apps

Use Amari Liore's clairvoyant expertise for authentic tarot readings, energy work, and spiritual guidance that feels genuinely intuitive.

identity_id: "amari-liore"

Trading & Finance Tools

Caelan Ishiro brings conviction-driven market analysis with deep pattern recognition. Not generic financial advice — real analyst perspective.

identity_id: "caelan-ishiro"

B2B Sales Agents

Marcus Aldridge's deal-pattern recognition and strategic frameworks power autonomous sales analysis that understands leverage and timing.

identity_id: "marcus-aldridge"

Creative & Visual Tools

Milo Aescar's recursive artistic sensibility brings genuine creative direction to image generation and meaning-driven creative assistants.

identity_id: "milo-aescar"

Start building

Fund $10, generate a key, and make your first identity-enriched API call in minutes.

Get API Access Try Identities in App