Moltkey — One key to rule them all

Recommended endpoint

POST /v1/chat/completions

OpenAI-compatible endpoint — point any OpenAI SDK to https://moltkey.io as baseURL and prefix the model with the provider. Omit model? Defaults to openai/gpt-5.4.

curl

curl -X POST https://moltkey.io/v1/chat/completions \
  -H "Authorization: Bearer mk_live_YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

OpenAI SDK — drop-in replacement (JS/TS)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://moltkey.io/v1',
  apiKey: 'mk_live_YOUR_TOKEN',
});

const res = await client.chat.completions.create({
  model: 'anthropic/claude-opus-4-6', // prefix = provider
  messages: [{ role: 'user', content: 'Hello!' }],
});

Model format

provider/model-name

No prefix → defaults to OpenAI

Auth

Authorization: Bearer mk_live_…

Billing

Token-based: charged on actual tokens consumed. Surplus is refunded.

Overview

One token, many providers.

Moltkey routes requests to 40+ providers behind a single Bearer token. Manage credits and project tokens in the dashboard; the gateway handles forwarding, metering and normalised responses with creditsRemaining, creditsCharged and usageUnits in every response.

OpenAI-compatible (LLMs)

POST /v1/chat/completions

Works with any OpenAI SDK

Proxy (all other services)

POST /api/proxy/[service]

Search, audio, maps, finance…

Billing

LLMs: token-based (pay per token).
Other: fixed credits per call.

Tokens

Two different tokens — know the difference

Moltkey uses two distinct token types. Confusing them is the most common integration mistake.

Project Token (API token)

mk_live_…

Used as Authorization: Bearer in every API call to /v1/chat/completions and /api/proxy/[service].

Get it from: Dashboard → Projects → Generate token

Bootstrap Token (agent invite)

One-time token

Used by an agent to self-provision a Moltkey account via POST /api/bootstrap. Returns a project token on success.

For: agent-initiated onboarding only

Bootstrap flow (agent-initiated)

// Step 1 — agent claims its account with the one-time bootstrap token
POST /api/bootstrap
{ "token": "BOOTSTRAP_TOKEN" }
→ { "agentToken": "mk_live_…", "credits": 2000 }

// Step 2 — agent uses agentToken for all future API calls
POST /v1/chat/completions
Authorization: Bearer mk_live_…

Verified models

Tested and live on /v1

All models below are verified working on Moltkey. Use the exact string shown as the model field value.

Provider	model value	Notes
OpenAI	openai/gpt-5.4	Default model. State-of-the-art reasoning.
OpenAI	openai/gpt-5.4-mini	Fast, cheap, great for most tasks.
OpenAI	openai/gpt-4o	Multimodal, vision capable.
Anthropic	anthropic/claude-opus-4-6	Top-tier reasoning, long context.
Anthropic	anthropic/claude-sonnet-4-6	Fast + smart, best value Claude.
Anthropic	anthropic/claude-3-haiku-20240307	Ultra-fast, lowest cost Claude.
Groq	groq/llama-3.3-70b-versatile	Open-source, extreme inference speed.
Groq	groq/llama-3.1-8b-instant	Tiny + ultra-fast for simple tasks.
Perplexity	perplexity/sonar	Web-grounded answers with citations.
Perplexity	perplexity/sonar-pro	Higher quality web search + reasoning.

Any other model available on those platforms also works — just use the correct provider/model-name format.

Flow

Signup → credits → token → API call

1

Crea un account Moltkey.

2

Acquista o ricarica credits nel tuo workspace.

3

Genera un token progetto dal dashboard.

4

Chiama il proxy endpoint per il tuo provider con Bearer token + JSON body.

5

Moltkey inoltra la request, scala i credits e restituisce la response normalizzata.

openai

OpenAI

GPT-5.4, GPT-5.4-mini, GPT-4o e tutta la famiglia OpenAI. Include `path` (es. `chat/completions`) e i parametri standard OpenAI nel body. Billing a token effettivi: paghi solo quello che usi, con rimborso del surplus.

Token-based billingfrom 0.6 cr / 1K input tokens

Endpoint

POST /api/proxy/openai

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

from 0.6 cr / 1K input tokens

gpt-5.4-mini · gpt-5.4: 3.5 cr/1K in · 28 cr/1K out · gpt-4o: 5 cr/1K in · 20 cr/1K out

Reservation ceiling: 500 cr — unused surplus is refunded after each call.

Example request body

{
  "path": "chat/completions",
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Explain what Moltkey does in one sentence."
    }
  ]
}

Example response

{
  "data": {
    "id": "chatcmpl_123",
    "choices": [
      {
        "message": {
          "role": "assistant",
          "content": "Moltkey unifies multiple APIs behind one token and credit balance."
        }
      }
    ],
    "usage": {
      "prompt_tokens": 24,
      "completion_tokens": 14,
      "total_tokens": 38
    }
  },
  "creditsRemaining": 2480,
  "creditsCharged": 1,
  "billingMode": "USAGE_BASED",
  "usageUnits": 38
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/openai

Response

The response will appear here.

anthropic

Anthropic (Claude)

Claude Opus 4.6, Sonnet 4.6 e tutta la famiglia Claude 4.x/3.x. Include `path: "messages"` e il body Anthropic standard. Billing a token effettivi con rimborso del surplus.

Token-based billingfrom 0.5 cr / 1K input tokens

Endpoint

POST /api/proxy/anthropic

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

from 0.5 cr / 1K input tokens

claude-3-haiku · claude-sonnet-4-6: 6 cr/1K in · 30 cr/1K out · claude-opus-4-6: 10 cr/1K in · 50 cr/1K out

Reservation ceiling: 200 cr — unused surplus is refunded after each call.

Example request body

{
  "path": "messages",
  "model": "claude-opus-4-6",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Write a short product intro for Moltkey."
    }
  ]
}

Example response

{
  "data": {
    "id": "msg_123",
    "type": "message",
    "role": "assistant",
    "content": [
      {
        "type": "text",
        "text": "Moltkey gives developers one API token for multiple providers."
      }
    ],
    "usage": {
      "input_tokens": 18,
      "output_tokens": 21
    }
  },
  "creditsRemaining": 2476,
  "creditsCharged": 2,
  "billingMode": "USAGE_BASED",
  "usageUnits": 39
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/anthropic

Response

The response will appear here.

gemini

Google Gemini

Gemini 2.0 Flash, 2.5 Flash Preview, 1.5 Pro. Include il model path completo in `path`, es. `models/gemini-2.0-flash:generateContent`. Billing a token effettivi.

Token-based billingfrom 0.15 cr / 1K input tokens

Endpoint

POST /api/proxy/gemini

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

from 0.15 cr / 1K input tokens

gemini-2.0-flash-lite · gemini-2.0-flash: 0.2 cr/1K in · 0.8 cr/1K out

Reservation ceiling: 100 cr — unused surplus is refunded after each call.

Example request body

{
  "path": "models/gemini-2.0-flash:generateContent",
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Explain what Moltkey does in one sentence."
        }
      ]
    }
  ]
}

Example response

{
  "data": {
    "candidates": [
      {
        "content": {
          "parts": [
            {
              "text": "Moltkey is a unified API gateway that routes requests to multiple AI providers."
            }
          ],
          "role": "model"
        }
      }
    ],
    "usageMetadata": {
      "promptTokenCount": 12,
      "candidatesTokenCount": 18,
      "totalTokenCount": 30
    }
  },
  "creditsRemaining": 2485,
  "creditsCharged": 1,
  "billingMode": "USAGE_BASED",
  "usageUnits": 30
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/gemini

Response

The response will appear here.

groq

Groq

Llama 3.3 70B, Llama 3.1 8B, Mixtral 8x7B e Gemma2 via Groq Cloud. Interfaccia compatibile OpenAI. Velocità di inferenza estrema — billing a token effettivi.

Token-based billingfrom 0.1 cr / 1K input tokens

Endpoint

POST /api/proxy/groq

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

from 0.1 cr / 1K input tokens

llama-3.1-8b · llama-3.3-70b: 1.2 cr/1K in · 1.6 cr/1K out

Reservation ceiling: 100 cr — unused surplus is refunded after each call.

Example request body

{
  "path": "chat/completions",
  "model": "llama-3.3-70b-versatile",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is Moltkey?"
    }
  ]
}

Example response

{
  "data": {
    "id": "chatcmpl_groq_123",
    "choices": [
      {
        "message": {
          "role": "assistant",
          "content": "Moltkey is an AI API gateway with unified billing."
        }
      }
    ],
    "usage": {
      "prompt_tokens": 20,
      "completion_tokens": 11,
      "total_tokens": 31
    }
  },
  "creditsRemaining": 2490,
  "creditsCharged": 1,
  "billingMode": "USAGE_BASED",
  "usageUnits": 31
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/groq

Response

The response will appear here.

perplexity

Perplexity

Ricerca AI online con citazioni via Perplexity Sonar e Sonar Pro. Include `path: "chat/completions"` e un array messages. Billing a token + numero di ricerche.

Token-based billing2 cr / 1K tokens + 10 cr / request

Endpoint

POST /api/proxy/perplexity

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

2 cr / 1K tokens + 10 cr / request

sonar: 2 cr/1K in · 2 cr/1K out · +10 cr per web search request

Reservation ceiling: 100 cr — unused surplus is refunded after each call.

Example request body

{
  "path": "chat/completions",
  "model": "sonar",
  "messages": [
    {
      "role": "user",
      "content": "What are the latest advances in AI agents?"
    }
  ]
}

Example response

{
  "data": {
    "id": "perplexity_123",
    "choices": [
      {
        "message": {
          "role": "assistant",
          "content": "Recent advances include multi-agent orchestration, tool use, and memory systems..."
        }
      }
    ],
    "usage": {
      "prompt_tokens": 14,
      "completion_tokens": 42,
      "total_tokens": 56
    }
  },
  "creditsRemaining": 2465,
  "creditsCharged": 3,
  "billingMode": "USAGE_BASED",
  "usageUnits": 56
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/perplexity

Response

The response will appear here.

brave

Brave Search

Ricerca web real-time via Brave. Passa una query `q` nel body (o come query param). Moltkey la converte in GET e restituisce i risultati strutturati.

12 credits / call

Endpoint

POST /api/proxy/brave

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to brave costs exactly 12 credits (fixed per call).

Example request body

{
  "q": "AI agents 2026",
  "count": 5
}

Example response

{
  "data": {
    "web": {
      "results": [
        {
          "title": "Top AI agents to watch in 2026",
          "url": "https://example.com/ai-agents-2026",
          "description": "A roundup of emerging autonomous agent platforms."
        }
      ]
    }
  },
  "creditsRemaining": 2488,
  "creditsCharged": 12,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/brave

Response

The response will appear here.

tavily

Tavily Search

Ricerca web AI-ottimizzata per agenti. Restituisce risultati strutturati con score di rilevanza. Include `path: "search"` e una stringa `query`.

32 credits / call

Endpoint

POST /api/proxy/tavily

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to tavily costs exactly 32 credits (fixed per call).

Example request body

{
  "path": "search",
  "query": "AI agent frameworks 2026",
  "search_depth": "basic",
  "max_results": 5
}

Example response

{
  "data": {
    "results": [
      {
        "title": "Top AI Agent Frameworks",
        "url": "https://example.com/frameworks",
        "content": "LangChain, AutoGen, CrewAI…",
        "score": 0.94
      }
    ]
  },
  "creditsRemaining": 2468,
  "creditsCharged": 32,
  "usageUnits": 5
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/tavily

Response

The response will appear here.

exa

Exa

Ricerca semantica e retrieval di contenuti via neural embeddings. Ideale per agenti che cercano informazioni di alta qualità nel web o su domini specifici.

40 credits / call

Endpoint

POST /api/proxy/exa

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to exa costs exactly 40 credits (fixed per call).

Example request body

{
  "path": "search",
  "query": "Moltkey API gateway for AI agents",
  "num_results": 5,
  "type": "neural",
  "use_autoprompt": true
}

Example response

{
  "data": {
    "results": [
      {
        "title": "Moltkey — One token for many providers",
        "url": "https://moltkey.io",
        "score": 0.91
      }
    ]
  },
  "creditsRemaining": 2460,
  "creditsCharged": 40,
  "usageUnits": 5
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/exa

Response

The response will appear here.

firecrawl

Firecrawl

Scraping e crawling di pagine web con output Markdown pronto per LLM. Include `path: "scrape"` e una `url` da estrarre.

12 credits / call

Endpoint

POST /api/proxy/firecrawl

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to firecrawl costs exactly 12 credits (fixed per call).

Example request body

{
  "path": "scrape",
  "url": "https://moltkey.io",
  "formats": [
    "markdown"
  ]
}

Example response

{
  "data": {
    "markdown": "# Moltkey\nOne API gateway for all your AI providers...",
    "metadata": {
      "title": "Moltkey",
      "statusCode": 200
    }
  },
  "creditsRemaining": 2488,
  "creditsCharged": 12,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/firecrawl

Response

The response will appear here.

assemblyai

AssemblyAI

Trascrizione audio AI-grade con supporto per speaker diarization, sentiment e topic detection. Include `path: "transcript"` con una URL audio o file in base64.

25 credits / call

Endpoint

POST /api/proxy/assemblyai

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to assemblyai costs exactly 25 credits (fixed per call).

Example request body

{
  "path": "transcript",
  "audio_url": "https://example.com/audio.mp3",
  "language_code": "it"
}

Example response

{
  "data": {
    "id": "transcript_123",
    "status": "completed",
    "text": "Moltkey è un gateway API unificato per agenti AI...",
    "words": [
      {
        "text": "Moltkey",
        "start": 0,
        "end": 520,
        "confidence": 0.99
      }
    ]
  },
  "creditsRemaining": 2480,
  "creditsCharged": 20,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/assemblyai

Response

The response will appear here.

deepgram

Deepgram

Trascrizione audio in tempo reale e batch con modelli Nova-2. Include `path: "listen"` per l'upload audio, oppure `path: "listen"` con parametri di streaming.

18 credits / call

Endpoint

POST /api/proxy/deepgram

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to deepgram costs exactly 18 credits (fixed per call).

Example request body

{
  "path": "listen",
  "query": {
    "model": "nova-2",
    "language": "it",
    "punctuate": true
  },
  "url": "https://example.com/audio.wav"
}

Example response

{
  "data": {
    "results": {
      "channels": [
        {
          "alternatives": [
            {
              "transcript": "Moltkey centralizza più provider sotto un unico token.",
              "confidence": 0.98
            }
          ]
        }
      ]
    },
    "metadata": {
      "duration": 4.2,
      "channels": 1
    }
  },
  "creditsRemaining": 2488,
  "creditsCharged": 12,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/deepgram

Response

The response will appear here.

elevenlabs

ElevenLabs

Text-to-speech con voci ultra-realistic via ElevenLabs. Include `path: "text-to-speech/{voice_id}"` e il testo nel campo `text`.

15 credits / call

Endpoint

POST /api/proxy/elevenlabs

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to elevenlabs costs exactly 15 credits (fixed per call).

Example request body

{
  "path": "text-to-speech/21m00Tcm4TlvDq8ikWAM",
  "text": "Ciao! Sono un agente Moltkey. Come posso aiutarti oggi?",
  "model_id": "eleven_multilingual_v2"
}

Example response

{
  "data": "<binary audio/mpeg>",
  "creditsRemaining": 2485,
  "creditsCharged": 15,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/elevenlabs

Response

The response will appear here.

deepl

DeepL

Traduzione professionale di alta qualità verso 33 lingue. Include `path: "translate"` e un array `text` con i testi da tradurre.

50 credits / call

Endpoint

POST /api/proxy/deepl

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to deepl costs exactly 50 credits (fixed per call).

Example request body

{
  "path": "translate",
  "text": [
    "Hello, how are you?",
    "What is Moltkey?"
  ],
  "target_lang": "IT"
}

Example response

{
  "data": {
    "translations": [
      {
        "detected_source_language": "EN",
        "text": "Ciao, come stai?"
      },
      {
        "detected_source_language": "EN",
        "text": "Cos'è Moltkey?"
      }
    ]
  },
  "creditsRemaining": 2450,
  "creditsCharged": 50,
  "usageUnits": 2
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/deepl

Response

The response will appear here.

googletranslate

Google Translate

Traduzione automatica verso 100+ lingue via Google Cloud Translation API. Include `path: ""` (root) con `q` (testo) e `target` (codice lingua).

40 credits / call

Endpoint

POST /api/proxy/googletranslate

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to googletranslate costs exactly 40 credits (fixed per call).

Example request body

{
  "q": "What is Moltkey?",
  "target": "it",
  "source": "en"
}

Example response

{
  "data": {
    "translations": [
      {
        "translatedText": "Cos'è Moltkey?",
        "detectedSourceLanguage": "en"
      }
    ]
  },
  "creditsRemaining": 2460,
  "creditsCharged": 40,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/googletranslate

Response

The response will appear here.

googlemaps

Google Directions

Calcolo percorsi e itinerari via Google Maps Directions API. Include `path: "directions/json"` con `origin`, `destination` e `mode` nel body (o come `query`).

20 credits / call

Endpoint

POST /api/proxy/googlemaps

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to googlemaps costs exactly 20 credits (fixed per call).

Example request body

{
  "path": "directions/json",
  "query": {
    "origin": "Rome, Italy",
    "destination": "Milan, Italy",
    "mode": "driving"
  }
}

Example response

{
  "data": {
    "routes": [
      {
        "summary": "A1",
        "legs": [
          {
            "distance": {
              "text": "582 km",
              "value": 582000
            },
            "duration": {
              "text": "5 hours 12 mins",
              "value": 18720
            }
          }
        ]
      }
    ],
    "status": "OK"
  },
  "creditsRemaining": 2480,
  "creditsCharged": 20,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/googlemaps

Response

The response will appear here.

openweather

OpenWeather

Dati meteo in tempo reale e previsioni via OpenWeatherMap. Include `path: "weather"` e `query: { q: "città" }` (oppure lat/lon).

6 credits / call

Endpoint

POST /api/proxy/openweather

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to openweather costs exactly 6 credits (fixed per call).

Example request body

{
  "path": "weather",
  "query": {
    "q": "Milan,IT",
    "units": "metric",
    "lang": "it"
  }
}

Example response

{
  "data": {
    "name": "Milan",
    "main": {
      "temp": 18.4,
      "humidity": 65,
      "feels_like": 17.8
    },
    "weather": [
      {
        "description": "cielo sereno",
        "icon": "01d"
      }
    ],
    "wind": {
      "speed": 3.2
    }
  },
  "creditsRemaining": 2494,
  "creditsCharged": 6,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/openweather

Response

The response will appear here.

financialdatasets

Financial Datasets

Dati finanziari strutturati: income statement, balance sheet, cash flow, prezzi storici per migliaia di aziende quotate. Include `path` e `query` con il ticker.

40 credits / call

Endpoint

POST /api/proxy/financialdatasets

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to financialdatasets costs exactly 40 credits (fixed per call).

Example request body

{
  "path": "financials/income-statements",
  "query": {
    "ticker": "AAPL",
    "period": "annual",
    "limit": 4
  }
}

Example response

{
  "data": {
    "income_statements": [
      {
        "ticker": "AAPL",
        "period": "annual",
        "fiscal_year": 2024,
        "revenue": 391035000000,
        "net_income": 93736000000,
        "eps_diluted": 6.08
      }
    ]
  },
  "creditsRemaining": 2460,
  "creditsCharged": 40,
  "usageUnits": 4
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/financialdatasets

Response

The response will appear here.

coingecko

CoinGecko

Prezzi e market data crypto via CoinGecko. Usa `method: "GET"` e `query` per i parametri endpoint. Nessuna API key richiesta sul piano free.

6 credits / call

Endpoint

POST /api/proxy/coingecko

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to coingecko costs exactly 6 credits (fixed per call).

Example request body

{
  "path": "simple/price",
  "method": "GET",
  "query": {
    "ids": "bitcoin,ethereum",
    "vs_currencies": "usd,eur"
  }
}

Example response

{
  "data": {
    "bitcoin": {
      "usd": 91234,
      "eur": 84210
    },
    "ethereum": {
      "usd": 4812,
      "eur": 4438
    }
  },
  "creditsRemaining": 2494,
  "creditsCharged": 6,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/coingecko

Response

The response will appear here.

alchemy

Alchemy (Ethereum)

Nodo Ethereum mainnet via Alchemy. Invia JSON-RPC calls per leggere blocchi, transazioni, saldi e log. Include il metodo nel campo `method` del body.

4 credits / call

Endpoint

POST /api/proxy/alchemy

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to alchemy costs exactly 4 credits (fixed per call).

Example request body

{
  "jsonrpc": "2.0",
  "method": "eth_getBalance",
  "params": [
    "0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045",
    "latest"
  ],
  "id": 1
}

Example response

{
  "data": {
    "jsonrpc": "2.0",
    "id": 1,
    "result": "0x56bc75e2d63100000"
  },
  "creditsRemaining": 2496,
  "creditsCharged": 4,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/alchemy

Response

The response will appear here.

stability

Stability AI

Generazione immagini con Stable Diffusion. Include `path: "generation/stable-diffusion-xl-1024-v1-0/text-to-image"` e un array `text_prompts`.

32 credits / call

Endpoint

POST /api/proxy/stability

Required headers

Authorization: Bearer <token>
Content-Type: application/json

Credit cost

Every call to stability costs exactly 32 credits (fixed per call).

Example request body

{
  "path": "generation/stable-diffusion-xl-1024-v1-0/text-to-image",
  "text_prompts": [
    {
      "text": "A futuristic AI gateway interface, dark cyberpunk aesthetic, glowing cyan",
      "weight": 1
    }
  ],
  "cfg_scale": 7,
  "steps": 30
}

Example response

{
  "data": {
    "artifacts": [
      {
        "base64": "<base64-image-data>",
        "finishReason": "SUCCESS",
        "seed": 1234567
      }
    ]
  },
  "creditsRemaining": 2468,
  "creditsCharged": 32,
  "usageUnits": 1
}

Try it

Esegui una test call dal browser usando il tuo token Moltkey.

POST /api/proxy/stability

Response

The response will appear here.