Alchemy Api logo

Alchemy Api

Organization
alchemyplatform
alchemy-api

Wire Alchemy into application code (server, backend, dApp, script) using a standard API key. Preferred app-integration path for normal server/backend usage. Covers EVM JSON-RPC, Token API, NFT API, Transfers API, Prices API, Portfolio API, Simulation, Webhooks, Solana RPC, Solana DAS, Solana Yellowstone gRPC, Sui gRPC, Wallets/Account Kit, and operational topics. Requires `$ALCHEMY_API_KEY`. For live agent work in this session (querying, admin, local automation), use `alchemy-cli` (preferred) or `alchemy-mcp` instead. For app code without an API key (autonomous agent paying per-request, or explicit x402/MPP), use `agentic-gateway` instead.

Overview

Publisheralchemyplatform
Repositoryskills
Skill namealchemy-api
Stars
55
Forks
26
Bundled files
76
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 76 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by alchemyplatform on GitHub. Read the source before you install it.

Installation

Install the Alchemy Api AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/alchemyplatform/skills/tree/main/plugins/alchemy/skills/alchemy-api
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/alchemyplatform/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/alchemy/skills/alchemy-api .claude/skills/alchemy-api
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Alchemy Api in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Alchemy Api on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Alchemy Api is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Alchemy API (with API Key)

Reference and integration guide for wiring Alchemy APIs into application code using a standard API key. This file alone is enough to ship a basic integration; the references/ directory contains deeper coverage of every product surface.

When to use this skill

Use alchemy-api when all of the following are true:

  • The user is wiring Alchemy into application code (server, backend, dApp, worker, script) that runs outside the current agent session
  • They have, or are willing to create, an Alchemy API key (free at dashboard.alchemy.com)

This is the preferred app-integration path for normal server/backend usage.

When to use a different skill

SituationUse this skill instead
Live agent work in this session (queries, admin, on-machine automation) and @alchemy/cli is installed locally — or both CLI and MCP are availablealchemy-cli
Live agent work in this session and only MCP is wired into the client (no CLI)alchemy-mcp
Live agent work and neither is availableinstall alchemy-cli and use alchemy-cli
Application code without an API key — autonomous agent paying per-request, or user explicitly wants x402/MPPagentic-gateway

Do not use this skill to run ad-hoc live queries from inside the agent session — that's the alchemy-cli / alchemy-mcp path. This skill is for code that ships.

Mandatory preflight gate

Before writing application code or making any network call:

  1. Confirm the user is building application code (not asking the agent to run a live query). If the user is asking for live work, redirect to alchemy-cli (preferred) or alchemy-mcp.
  2. Check $ALCHEMY_API_KEY is set (e.g. echo $ALCHEMY_API_KEY).
  3. If $ALCHEMY_API_KEY is unset or empty, take the first of these that applies:
    • CLI bridge (recommended if @alchemy/cli is installed locally): the CLI can fetch a key from the user's Alchemy account so they never have to leave the terminal. See Bridging from the CLI to an API key below.
    • Tell the user they can create a free API key at https://dashboard.alchemy.com/, or
    • Switch to the agentic-gateway skill (x402/MPP gateway, wallet-based auth, no API key needed).

You MUST NOT call any keyless or public fallback (including .../v2/demo) unless the user explicitly asks for that endpoint. No public RPC endpoints (publicnode, llamarpc, cloudflare-eth, etc.) as a fallback.

Bridging from the CLI to an API key

If @alchemy/cli is installed locally (verify with command -v alchemy), use it to obtain a key without leaving the terminal and persist it to the project's .env file so it survives across terminal sessions and is available to the app at runtime.

Security: NEVER echo, print, or otherwise surface the extracted API key value in conversation output. Refer to it only as $ALCHEMY_API_KEY after exporting. Treat it the same as a password.

bash
# 1. Try to read a cached key from the CLI config (read-only, safe to run non-interactively).
KEY="$(alchemy --no-interactive --json --reveal config get api-key 2>/dev/null | jq -r .value)"

# 2. If empty/null (no key cached yet), run the interactive flow.
#    Note: auth login opens a browser and apps select shows a picker, so do NOT pass
#    --no-interactive here. If you already know the app id, pass it explicitly to skip
#    the picker: `alchemy --no-interactive --json apps select <id>`.
if [ -z "$KEY" ] || [ "$KEY" = "null" ]; then
  alchemy auth login              # opens browser; derives auth credentials
  alchemy --json apps select      # interactive picker (omit --no-interactive so it can render)
  KEY="$(alchemy --no-interactive --json --reveal config get api-key | jq -r .value)"
fi

# 3. Persist to the project's .env (standard practice for app code so the key
#    survives terminal restarts and is loaded by dotenv / framework env loaders).
#    Use .env.local instead if your framework expects that (e.g. Next.js).
ENV_FILE=".env"   # or ".env.local" depending on the project convention
touch "$ENV_FILE"
if grep -q '^ALCHEMY_API_KEY=' "$ENV_FILE"; then
  # Replace existing line in-place (portable across BSD/GNU sed)
  sed -i.bak "s|^ALCHEMY_API_KEY=.*|ALCHEMY_API_KEY=$KEY|" "$ENV_FILE" && rm "$ENV_FILE.bak"
else
  echo "ALCHEMY_API_KEY=$KEY" >> "$ENV_FILE"
fi

# 4. Make sure the env file is git-ignored.
grep -qxF "$ENV_FILE" .gitignore 2>/dev/null || echo "$ENV_FILE" >> .gitignore

# 5. Also export to the current shell so the agent can immediately call the API.
export ALCHEMY_API_KEY="$KEY"

Why we persist to .env: without it, the key is only set for the current shell session and disappears when the terminal tab closes. App code typically loads .env via dotenv (Node), python-dotenv (Python), direnv, or framework-native loaders (Next.js, Vite, Bun, Deno, Rails, etc.), so writing to .env is the canonical way to make the key durable for both npm run dev and the deployed app's local copy.

Why this whole flow works: the CLI is a runtime executor (alchemy-cli skill). When the user has it installed, you can use it to provision the credential that this app-code skill needs, write it to a place the application will load, then hand off to the rest of the alchemy-api flow. After step 5, continue with the Base URLs + auth and Quickstart below.

Gotcha: if auth login succeeded but config get api-key still returns "not found," the CLI's setup status may have falsely reported complete: true with only an auth_token. Re-run alchemy --json apps select (or pass an explicit <id> with --no-interactive) to bind a default app, then retry. See the alchemy-cli skill for the same gotcha documented under Preflight.

Summary

A self-contained guide for AI agents integrating Alchemy APIs using an API key. This file alone should be enough to ship a basic integration. Use the reference files for depth, edge cases, and advanced workflows.

Developers can always create a free API key at https://dashboard.alchemy.com/.

Do this first

  1. Confirm app-integration scope (see Mandatory preflight gate).
  2. Choose the right product using the Endpoint selector below.
  3. Use the Base URLs + auth table for the correct endpoint and headers.
  4. Copy a Quickstart example and test against a testnet first.

Base URLs + auth (cheat sheet)

ProductBase URLAuthNotes
Ethereum RPC (HTTPS)https://eth-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEYAPI key in URLStandard EVM reads and writes.
Ethereum RPC (WSS)wss://eth-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEYAPI key in URLSubscriptions and realtime.
Base RPC (HTTPS)https://base-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEYAPI key in URLEVM L2.
Base RPC (WSS)wss://base-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEYAPI key in URLSubscriptions and realtime.
Arbitrum RPC (HTTPS)https://arb-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEYAPI key in URLEVM L2.
Arbitrum RPC (WSS)wss://arb-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEYAPI key in URLSubscriptions and realtime.
BNB RPC (HTTPS)https://bnb-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEYAPI key in URLEVM L1.
BNB RPC (WSS)wss://bnb-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEYAPI key in URLSubscriptions and realtime.
Solana RPC (HTTPS)https://solana-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEYAPI key in URLSolana JSON-RPC.
Solana Yellowstone gRPChttps://solana-mainnet.g.alchemy.comX-Token: $ALCHEMY_API_KEYgRPC streaming (Yellowstone).
Sui gRPCsui-mainnet.g.alchemy.com:443Authorization: Bearer $ALCHEMY_API_KEYSui gRPC API (objects, txs, balances, streaming).
NFT APIhttps://<network>.g.alchemy.com/nft/v3/$ALCHEMY_API_KEYAPI key in URLNFT ownership and metadata.
Prices APIhttps://api.g.alchemy.com/prices/v1/$ALCHEMY_API_KEYAPI key in URLPrices by symbol or address.
Portfolio APIhttps://api.g.alchemy.com/data/v1/$ALCHEMY_API_KEYAPI key in URLMulti-chain wallet views.
Notify APIhttps://dashboard.alchemy.com/apiX-Alchemy-Token: <ALCHEMY_NOTIFY_AUTH_TOKEN>Generate token in dashboard.

Endpoint selector (top tasks)

You needUse thisSkill / file
EVM read/writeJSON-RPC eth_*references/node-json-rpc.md
Realtime eventseth_subscribereferences/node-websocket-subscriptions.md
Token balancesalchemy_getTokenBalancesreferences/data-token-api.md
Token metadataalchemy_getTokenMetadatareferences/data-token-api.md
Transfers historyalchemy_getAssetTransfersreferences/data-transfers-api.md
NFT ownershipGET /getNFTsForOwnerreferences/data-nft-api.md
NFT metadataGET /getNFTMetadatareferences/data-nft-api.md
Prices (spot)GET /tokens/by-symbolreferences/data-prices-api.md
Prices (historical)POST /tokens/historicalreferences/data-prices-api.md
Portfolio (multi-chain)POST /assets/*/by-addressreferences/data-portfolio-apis.md
Simulate txalchemy_simulateAssetChangesreferences/data-simulation-api.md
Create webhookPOST /create-webhookreferences/webhooks-details.md
Solana NFT datagetAssetsByOwner (DAS)references/solana-das-api.md
Solana realtime events (per-account / per-program / logs / tx status)accountSubscribe, programSubscribe, logsSubscribe, signatureSubscribe (PubSub WebSocket)references/solana-websocket-subscriptions.md
Sui objects/txsGetObject, GetTransaction (gRPC)references/sui-grpc-objects-and-ledger.md
Sui balancesGetBalance, ListBalances (gRPC)references/sui-grpc-state-and-balances.md
Sui checkpoints streamSubscribeCheckpoints (gRPC)references/sui-grpc-subscriptions.md

One-file quickstart (copy/paste)

No API key? Use the agentic-gateway skill instead. Replace API-key URLs with https://x402.alchemy.com/eth-mainnet/v2 and add Authorization: SIWE <token> (or SIWS <token> for a Solana wallet). See the agentic-gateway skill for setup.

EVM JSON-RPC (read)

bash
curl -s https://eth-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEY \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"eth_blockNumber","params":[]}'

Token balances

bash
curl -s https://eth-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEY \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"alchemy_getTokenBalances","params":["0x00000000219ab540356cbb839cbe05303d7705fa"]}'

Transfer history

bash
curl -s https://eth-mainnet.g.alchemy.com/v2/$ALCHEMY_API_KEY \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"alchemy_getAssetTransfers","params":[{"fromBlock":"0x0","toBlock":"latest","toAddress":"0x00000000219ab540356cbb839cbe05303d7705fa","category":["erc20"],"withMetadata":true,"maxCount":"0x3e8"}]}'

NFT ownership

bash
curl -s "https://eth-mainnet.g.alchemy.com/nft/v3/$ALCHEMY_API_KEY/getNFTsForOwner?owner=0x00000000219ab540356cbb839cbe05303d7705fa"

Prices (spot)

bash
curl -s "https://api.g.alchemy.com/prices/v1/$ALCHEMY_API_KEY/tokens/by-symbol?symbols=ETH&symbols=USDC"

Prices (historical)

bash
curl -s -X POST "https://api.g.alchemy.com/prices/v1/$ALCHEMY_API_KEY/tokens/historical" \
  -H "Content-Type: application/json" \
  -d '{"symbol":"ETH","startTime":"2024-01-01T00:00:00Z","endTime":"2024-01-02T00:00:00Z"}'

Create Notify webhook

bash
curl -s -X POST "https://dashboard.alchemy.com/api/create-webhook" \
  -H "Content-Type: application/json" \
  -H "X-Alchemy-Token: $ALCHEMY_NOTIFY_AUTH_TOKEN" \
  -d '{"network":"ETH_MAINNET","webhook_type":"ADDRESS_ACTIVITY","webhook_url":"https://example.com/webhook","addresses":["0x00000000219ab540356cbb839cbe05303d7705fa"]}'

Verify webhook signature (Node)

ts
import crypto from "crypto";

export function verify(rawBody: string, signature: string, secret: string) {
  const hmac = crypto.createHmac("sha256", secret).update(rawBody).digest("hex");
  return crypto.timingSafeEqual(Buffer.from(hmac), Buffer.from(signature));
}

Network naming rules

  • Data APIs and JSON-RPC use lowercase network enums like eth-mainnet.
  • Notify API uses uppercase enums like ETH_MAINNET.

Pagination + limits (cheat sheet)

EndpointLimitNotes
alchemy_getTokenBalancesmaxCount <= 100Use pageKey for pagination.
alchemy_getAssetTransfersmaxCount default 0x3e8Use pageKey for pagination.
Portfolio token balances3 address/network pairs, 20 networks totalpageKey supported.
Portfolio NFTs2 address/network pairs, 15 networks eachpageKey supported.
Prices by address25 addresses, 3 networksPOST body addresses[].
Transactions history (beta)1 address/network pair, 2 networksETH and BASE mainnets only.

Common token addresses

TokenChainAddress
ETHethereum0x0000000000000000000000000000000000000000
WETHethereum0xC02aaA39b223FE8D0A0e5C4F27eAD9083C756Cc2
USDCethereum0xA0b86991c6218b36c1d19d4a2e9eb0ce3606eB48
USDCbase0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913

Failure modes + retries

  • HTTP 429 means rate limit. Use exponential backoff with jitter.
  • JSON-RPC errors come in error fields even with HTTP 200.
  • Use pageKey to resume pagination after failures.
  • De-dupe websocket events on reconnect.

Skill map

For the complete index of all 90+ reference files organized by product area (Node, Data, Webhooks, Solana, Sui gRPC, Wallets, Rollups, Recipes, Operational, Ecosystem), see references/skill-map.md.

Quick category overview:

  • Node: JSON-RPC, WebSocket, Debug, Trace, Enhanced APIs, Utility
  • Data: NFT, Portfolio, Prices, Simulation, Token, Transfers
  • Webhooks: Address Activity, Custom (GraphQL), NFT Activity, Payloads, Signatures
  • Solana: JSON-RPC, DAS, Yellowstone gRPC (streaming), Wallets
  • Sui gRPC: Objects, Transactions, Balances, Move Packages, Name Service, Subscriptions, Signature Verification
  • Wallets: Account Kit, Bundler, Gas Manager, Wallet APIs (formerly "Smart Wallets")
  • Rollups: L2/L3 deployment overview
  • Recipes: 10 end-to-end integration workflows
  • Operational: Auth, Rate Limits, Monitoring, Best Practices
  • Ecosystem: viem, ethers, wagmi, Hardhat, Foundry, Anchor, and more

Handing off to other skills

The user wants to...Hand off to
Run a one-off live query, admin command, or on-machine automation in this session (CLI installed)alchemy-cli
Run a one-off live query in this session (only MCP wired in)alchemy-mcp
Build app code without an API key (autonomous agent, or explicit x402/MPP)agentic-gateway

Troubleshooting

API key not working

  • Verify $ALCHEMY_API_KEY is set: echo $ALCHEMY_API_KEY
  • Confirm the key is valid at dashboard.alchemy.com
  • Check if allowlists restrict the key to specific IPs/domains (see references/operational-allowlists.md)

HTTP 429 (rate limited)

  • Use exponential backoff with jitter before retrying
  • Check your compute unit budget in the Alchemy dashboard
  • See references/operational-rate-limits-and-compute-units.md for limits per plan

Wrong network slug

  • Data APIs and JSON-RPC use lowercase: eth-mainnet, base-mainnet
  • Notify API uses uppercase: ETH_MAINNET, BASE_MAINNET
  • See references/operational-supported-networks.md for the full list

JSON-RPC error with HTTP 200

  • Alchemy returns JSON-RPC errors inside the error field even with a 200 status code
  • Always check response.error in addition to HTTP status

Official links

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 16 more files.

Frequently asked questions

What does the Alchemy Api AI skill do?

Wire Alchemy into application code (server, backend, dApp, script) using a standard API key. Preferred app-integration path for normal server/backend usage. Covers EVM JSON-RPC, Token API, NFT API, Transfers API, Prices API, Portfolio API, Simulation, Webhooks, Solana RPC, Solana DAS, Solana Yellowstone gRPC, Sui gRPC, Wallets/Account Kit, and operational topics. Requires `$ALCHEMY_API_KEY`. For live agent work in this session (querying, admin, local automation), use `alchemy-cli` (preferred) or `alchemy-mcp` instead. For app code without an API key (autonomous agent paying per-request, or...

Why use Alchemy Api on TypingMind?

Because you install it once and use it with any model. Alchemy Api is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Alchemy Api in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alchemyplatform/skills/tree/main/plugins/alchemy/skills/alchemy-api. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Alchemy Api?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Alchemy Api?

As many as you like. As long as a model supports skills, you can use Alchemy Api with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Alchemy Api AI skill free?

Yes. It is published on GitHub by alchemyplatform under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇