Docs

Build with GreenTokens

GreenTokens speaks the OpenAI and Anthropic API formats. Point your SDK or tool at our base URL, use a GreenTokens key, and your existing code keeps working.

Quickstart

Sign in with your email and add funds to your wallet.
Create an API key on the API Keys page. It starts with sk-gt- and is shown once.
Set the base URL to https://api.greentokens.io/v1 for OpenAI SDKs, or https://api.greentokens.io for Anthropic SDKs.
Use a model ID from the models page. Responses echo the same ID.

Authentication

Send your key in either header. Sending both with different keys is rejected with 401.

Authorization: Bearer sk-gt-… (OpenAI style)
x-api-key: sk-gt-… (Anthropic style)

Every response carries an x-request-id header. Include it when you contact support.

SDK examples

Python · OpenAI SDK

from openai import OpenAI

client = OpenAI(base_url="https://api.greentokens.io/v1", api_key="sk-gt-…")

response = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

TypeScript · OpenAI SDK

import OpenAI from "openai"

const client = new OpenAI({ baseURL: "https://api.greentokens.io/v1", apiKey: "sk-gt-…" })

const response = await client.chat.completions.create({
  model: "claude-sonnet-5",
  messages: [{ role: "user", content: "Hello" }],
})
console.log(response.choices[0].message.content)

Python · Anthropic SDK

from anthropic import Anthropic

client = Anthropic(base_url="https://api.greentokens.io", api_key="sk-gt-…")

message = client.messages.create(
    model="claude-sonnet-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

curl

curl https://api.greentokens.io/v1/chat/completions \
  -H "Authorization: Bearer sk-gt-…" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-sonnet-5", "messages": [{"role": "user", "content": "Hello"}]}'

Coding tools

Tools that read the standard environment variables work without other changes.

Claude Code

export ANTHROPIC_BASE_URL="https://api.greentokens.io"
export ANTHROPIC_AUTH_TOKEN="sk-gt-…"
claude

Codex CLI, opencode and other OpenAI-compatible tools

export OPENAI_BASE_URL="https://api.greentokens.io/v1"
export OPENAI_API_KEY="sk-gt-…"

Endpoints

Every route also works without the /v1 prefix, except video, which is /v1 only.

Text

Method	Path	Notes
POST	/v1/chat/completions	OpenAI Chat Completions: streaming, tools, vision
POST	/v1/responses	OpenAI Responses, with streaming
POST	/v1/messages	Anthropic Messages: streaming, tools, prompt caching, thinking
POST	/v1/messages/count_tokens	Anthropic token counting. Free, never billed

Images

Method	Path	Notes
POST	/v1/images/generations	Sync, streamed (stream: true) or async (Prefer: respond-async)
POST	/v1/images/edits	Multipart image edits
GET	/v1/images/jobs/{id}	Async job status; /content for the finished image

Video

Method	Path	Notes
POST	/v1/videos	Create a video job (202). Accepts Idempotency-Key
GET	/v1/videos/{id}	Job status; /content streams the MP4 (kept 7 days)
DELETE	/v1/videos/{id}	Cancel a job

Public (no key)

Method	Path	Notes
GET	/v1/models	Model list (OpenAI shape; Anthropic shape with an anthropic-version header)
GET	/v1/models/pricing	Prices per SKU, with the official price and savings
GET	/v1/status	Per-model status and 90 days of uptime

Errors

OpenAI routes return {"error": {"message", "type", "code"}}; Anthropic routes return {"type": "error", "error": {"type", "message"}}.

Status	Meaning
400	Invalid request
401	Missing, invalid, paused or revoked key
402	Insufficient balance, or the key's daily or monthly spend limit is reached
403	Model not allowed for this key, or account suspended
404	Unknown model or route
409	Idempotency conflict
413	Request too large
502 · 503 · 504	Upstream failure or timeout

Slow responses may start with 200 and keepalives. A failure after that arrives as an error body (or an SSE error event) under the 200.