Skip to content
Checking statusStatus
NewClaude Opus 5.5, Claude Fable 5.2, GPT-6 Astra and Gemini Argon 4 are live, plus DeepSeek, Grok, Kimi and more
Claude
Gemini
DeepSeek
Grok
Kimi
Qwen
Mistral
Llama
ChatGPT

Software, evolved to intelligence.

One API key for every Claude, ChatGPT and Gemini model, and DeepSeek, Grok, Kimi and more. Plug it into Claude Desktop, Claude Code, Codex, Cursor, Roblox Studio MCP, Blender MCP or your own code, and switch between 256 models without rewriting a line.

An animation: Claude Code connects with an Evolved key on Claude Opus 5.5 and builds an obby in Roblox Studio, then models a low-poly rocket in Blender and renders it. Next, the Evolved dashboard's chat asks Claude Opus 5.5, Prompt Creator makes a prompt, and the chat switches to GPT-6 Astra.

Live

API keys sold

To developers and teams worldwide, with more every day.

Supported models

  • gpt-astra-6
  • gemini-4-carbon
  • gpt-6.1-terra-pro
  • claude-fable-5-2
  • gpt-6.1-terra
  • gemini-argon-4
  • gpt-6.1-sol-pro
  • gpt-6.1-sol
  • claude-opus-5.5
  • gpt-6-luna-pro
  • gemini-3-pro
  • gpt-6-luna
  • claude-fable-5-1
  • gpt-6-sol-pro
  • gemini-4-hydrogen
  • gpt-6-sol
  • claude-sonnet-5.5
  • gpt-6-astra-pro
  • gemini-2.5-pro
  • gpt-5.6-luna-pro
  • claude-haiku-5.5
  • gpt-5.6-luna
  • gemini-2.5-flash
  • gpt-5.6-terra-pro
  • gpt-5.6-terra
  • gemini-2.5-flash-lite
  • gpt-5.6-sol-pro
  • claude-fable-5
  • gpt-5.6-sol
  • gemini-3.8-flash
  • gpt-5.5-pro
  • claude-mythos-5
  • gpt-5.5
  • gemini-3.7-flash
  • gpt-5
  • claude-sonnet-5.1
  • gpt-5.4-nano
  • gemini-3.6-flash
  • gpt-5.4-mini
  • claude-sonnet-5
  • gpt-5-mini
  • gpt-5.4-pro
  • gemini-3.5-flash-lite
  • gpt-5.4
  • claude-opus-5
  • gpt-5.3-codex
  • gemini-3.5-flash
  • gpt-5.2-codex
  • claude-opus-4.8
  • gpt-5.2-chat
  • gemini-3.1-flash-lite
  • gpt-5.2-pro
  • claude-opus-4.7
  • gpt-5.2
  • gemma-4-26b-a4b-it
  • gpt-5.1-codex-max
  • gpt-5.1
  • claude-sonnet-4.6
  • gpt-5.1-codex
  • gemma-4-31b-it
  • gpt-5.1-codex-mini
  • claude-opus-4.6
  • gpt-oss-safeguard-20b
  • gemini-3.1-flash-lite-preview
  • gpt-5-pro
  • claude-opus-4.5
  • gpt-5-nano
  • gemini-3.1-pro-preview-customtools
  • gpt-oss-120b
  • claude-haiku-4.5
  • gpt-oss-20b
  • gemini-3.1-pro-preview
  • gpt-4.1
  • gpt-4.1-mini
  • gemini-3-flash-preview
  • o3-pro
  • claude-sonnet-4.5
  • o3
  • gemini-2.5-pro-preview
  • gpt-4.1-nano
  • claude-opus-4.1
  • gpt-4o
  • gemma-3-4b-it
  • gpt-4o-mini
  • claude-opus-4
  • gpt-4o-2024-11-20
  • gemma-3-12b-it
  • gpt-4o-2024-08-06
  • claude-sonnet-4
  • gpt-4o-mini-2024-07-18
  • gpt-4o-2024-05-13
  • gemma-3-27b-it
  • gpt-3.5-turbo-0613
  • claude-haiku-3.5
  • gpt-3.5-turbo-16k
  • gemma-2-27b-it
  • gpt-4
  • sonar-pro-search
  • qwen3.8-max-prime
  • muse-ember
  • mistral-large-4-0
  • glm-5.3-flashx-legal
  • qwen3.8-omni-flash
  • deepseek-v4.1-flash-1017
  • kimi-k3.1-pro
  • grok-4.7
  • qwen3.8-max-0902
  • hy4
  • mistral-large-3
  • muse-spark-open
  • qwen3.8-flash
  • glm-5.3-prime
  • nemotron-3.5-super-vl
  • deepseek-v4.1-flash
  • qwen3.8-27b
  • command-a-plus
  • mistral-medium-3-5
  • qwen3.8-2.4t-a95b
  • mimo-v2.6-pro-ultraspeed
  • muse-wonder
  • glm-5.3-flashx
  • qwen-3-max
  • grok-4.6
  • kimi-k2-thinking
  • codestral
  • qwen3.7-flash
  • deepseek-v4
  • hy4-preview
  • glm-5.3-flash
  • qwen3.7-plus
  • muse-spark-1.3-contributor
  • minimax-m3.1-flash
  • devstral-2512
  • qwen3.7-max
  • nemotron-3.5-lightning
  • deepseek-v4-flash-vision-exp
  • sonar-reasoning-pro
  • qwen-3-coder
  • glm-5.3
  • muse-spark-1.3
  • ministral-14b-2512
  • qwen3.5-plus-20260420
  • grok-4
  • command-a
  • hy-mt2-1.8b
  • qwen3.6-flash
  • deepseek-r1
  • glm-5.2
  • ministral-8b-2512
  • qwen3.6-35b-a3b
  • muse-spark-1.2-contributor
  • kimi-k3
  • mimo-v2.6-flash
  • qwen3.6-27b
  • minimax-m3
  • muse-glimmer-30b
  • qwen3.6-plus
  • ministral-3b-2512
  • glm-5.1
  • grok-4.5
  • qwen3.5-9b
  • deepseek-v4-pro-0813
  • nemotron-3.5-content-safety
  • hy-mt2-30b-a3b
  • qwen3.5-35b-a3b
  • mistral-small
  • muse-spark-1.2
  • glm-5v-turbo
  • qwen3.5-27b
  • kimi-k2
  • deepseek-v4-flash-0731
  • sonar-pro
  • qwen3.5-122b-a10b
  • voxtral-small-24b-2507
  • grok-build-0.1
  • glm-5-turbo
  • qwen3.5-flash-02-23
  • muse-spark-1.1
  • command-r7b-12-2024
  • mistral-medium-3.1
  • qwen3.5-plus-02-15
  • mimo-v2.6-pro
  • deepseek-v4-flash
  • kimi-k2.7-code
  • qwen3.5-397b-a17b
  • glm-5
  • llama-4-maverick
  • mistral-small-3.2-24b-instruct
  • qwen3-coder-next
  • hy-mt2-7b
  • nemotron-3-ultra-550b-a55b
  • deepseek-v3
  • qwen3-vl-8b-instruct
  • grok-4.3
  • glm-4.7-flash
  • mistral-medium-3
  • qwen3-vl-30b-a3b-thinking
  • llama-4-scout
  • minimax-m2.7
  • qwen3-vl-30b-a3b-instruct
  • sonar-deep-research
  • kimi-k2.6
  • llama-guard-4-12b
  • qwen3-vl-235b-a22b-instruct
  • mistral-small-3.1-24b-instruct
  • glm-4.7
  • deepseek-v3.2
  • qwen3-coder-flash
  • hy3
  • command-r-08-2024
  • grok-4.20-multi-agent
  • qwen3-next-80b-a3b-instruct
  • mistral-saba
  • llama-3.3-70b-instruct
  • glm-4.6v
  • qwen3-coder-30b-a3b-instruct
  • nemotron-3-super-120b-a12b
  • deepseek-v3.2-exp
  • mimo-v2.5-pro
  • qwen3-30b-a3b-instruct-2507
  • mistral-small-24b-instruct-2501
  • minimax-m2.5
  • llama-3.2-1b-instruct
  • qwen3-235b-a22b-thinking-2507
  • glm-4.6
  • hy3-preview
  • deepseek-v3.1-terminus
  • qwen3-235b-a22b-2507
  • mistral-large-2407
  • grok-4.20
  • kimi-k2.5
  • qwen3-30b-a3b
  • glm-4.5v
  • llama-3.2-3b-instruct
  • sonar
  • qwen3-14b
  • mistral-nemo
  • command-r-plus-08-2024
  • qwen3-32b
  • deepseek-chat-v3.1
  • nemotron-3-nano-30b-a3b
  • glm-4.5
  • qwen2.5-vl-72b-instruct
  • llama-3.1-70b-instruct
  • mixtral-8x22b-instruct
  • hunyuan-a13b-instruct
  • qwen-plus
  • grok-3
  • kimi-k2-0905
  • deepseek-chat-v3-0324
  • qwen-2.5-coder-32b-instruct
  • glm-4.5-air
  • mistral-large
  • llama-3.1-8b-instruct
  • qwen-2.5-72b-instruct
  • mimo-v2.5
models behind one key
256
families: Claude, ChatGPT, Gemini
3
token context window
2M
per 1M input tokens
from $2.00

Claude, ChatGPT and more with one key.

Think of it as Claude Max and ChatGPT Pro in one, with Gemini, DeepSeek, Grok, Kimi and the rest of our 256 models from 16 families on the same balance.See the note about ChatGPT Pro, Claude Max and Google AI Ultra

Animated demo: Claude Code in VS Code, Claude Desktop on the project folder, then Codex, then Cursor, each on an evolved.to key. A prompt is typed into the agent's panel, the agent reads the code, writes a new file, asks before one step and is answered Yes, then sums up. Use the model menu to replay it on another of the newest Claude models.

Or in your own Claude Desktop

Paste your key into Claude Desktop once, then ask Claude to work on the files on your computer.

Animated demo: an Evolved key is added to Claude Desktop under Developer, Configure Third-Party Inference, with the base URL https://api.evolved.to. Then Claude is asked to sort the invoices in the Downloads folder by month; it lists and reads the files, asks before moving them, moves them into a folder per month and gives the total.

Works where you build: Claude Code, VS Code, Roblox Studio, Blender, every MCP server and every Anthropic or OpenAI compatible tool.

Claude, ChatGPT and more

Every model from 16 families. One key.

Frontier reasoning, balanced everyday models and fast lightweight ones, all on the same key, the same balance and one rate table.

Gemini, DeepSeek, Grok, Kimi, Qwen, Mistral, Llama, GLM, MiniMax, MiMo, Nemotron, Sonar, Command and Hunyuan too: 256 models on the same key.

More models

Pricing

Buy credit once. Use it on every model.

Pick Claude, ChatGPT, Gemini or a mix. Credit packs from $20, worth up to 16 times what you pay, on one balance for every model in your plan. No subscription.

Claude All Models

Fable 5.2 & Opus 5.5New

Think of it as Claude Max on a prepaid balance.*

  • Starter

    $50 credit

    $20one-time

    Try every model on a real project.

    • Claude All Models
    • Fable 5.2 & Opus 5.5New
    • โ‰ˆ 12.5M Claude models output tokens
    • No daily or weekly limits
    • Chat on evolved.to, on desktop and mobile
    • Works with Claude Code, Roblox Studio MCP, Blender MCP, VS Code and more clients
    • No logs: your prompts and replies are never stored
    • Maximum API security: encrypted, keys never logged
    Get $50 credit
  • Builder

    $100 credit

    $30one-time

    Daily coding sessions and side projects.

    • Claude All Models
    • Fable 5.2 & Opus 5.5New
    • โ‰ˆ 25M Claude models output tokens
    • No daily or weekly limits
    • Chat on evolved.to, on desktop and mobile
    • Works with Claude Code, Roblox Studio MCP, Blender MCP, VS Code and more clients
    • No logs: your prompts and replies are never stored
    • Maximum API security: encrypted, keys never logged
    Get $100 credit
  • Pro

    Pro choice

    $200 credit

    $40one-time

    For professionals shipping with agents every day.

    • Claude All Models
    • Fable 5.2 & Opus 5.5New
    • โ‰ˆ 50M Claude models output tokens
    • No daily or weekly limits
    • Chat on evolved.to, on desktop and mobile
    • Works with Claude Code, Roblox Studio MCP, Blender MCP, VS Code and more clients
    • No logs: your prompts and replies are never stored
    • Maximum API security: encrypted, keys never logged
    Get $200 credit
  • Power

    Most popular

    $400 credit

    $55one-time

    Heavy agent workloads, all day long.

    • Claude All Models
    • Fable 5.2 & Opus 5.5New
    • โ‰ˆ 100M Claude models output tokens
    • No daily or weekly limits
    • Chat on evolved.to, on desktop and mobile
    • Works with Claude Code, Roblox Studio MCP, Blender MCP, VS Code and more clients
    • No logs: your prompts and replies are never stored
    • Maximum API security: encrypted, keys never logged
    Get $400 credit
  • Scale

    $1,000 credit

    $95one-time

    Teams and long-running automations.

    • Claude All Models
    • Fable 5.2 & Opus 5.5New
    • โ‰ˆ 250M Claude models output tokens
    • No daily or weekly limits
    • Chat on evolved.to, on desktop and mobile
    • Works with Claude Code, Roblox Studio MCP, Blender MCP, VS Code and more clients
    • No logs: your prompts and replies are never stored
    • Maximum API security: encrypted, keys never logged
    Get $1,000 credit
  • Max

    Best value

    $2,000 credit

    $150one-time

    The most credit for every dollar.

    • Claude All Models
    • Fable 5.2 & Opus 5.5New
    • โ‰ˆ 500M Claude models output tokens
    • No daily or weekly limits
    • Chat on evolved.to, on desktop and mobile
    • Works with Claude Code, Roblox Studio MCP, Blender MCP, VS Code and more clients
    • No logs: your prompts and replies are never stored
    • Maximum API security: encrypted, keys never logged
    Get $2,000 credit

Buying for a team, or need more than $2,000 in credit?

Write to our sales team and we will set up the credit and keys that fit.

sales@evolved.to

* ChatGPT Pro, Claude Max and Google AI Ultra are subscription plans sold by OpenAI, Anthropic and Google. evolved.to is independent and does not sell those plans; your credit pays for API access to the same Claude, ChatGPT and Gemini model families.

Why evolved.to

Built for the way you already ship

Keep your tools, your SDKs and your prompts. Change one base URL and every model is on the table.

One key, every model

A single key replaces separate provider accounts, keys and invoices. Manage it, add credit and revoke it from one dashboard.

โ€ขโ€ขโ€ขโ€ขโ€ขโ€ขโ€ขโ€ขโ€ขโ€ขโ€ขโ€ขโ€ขโ€ข3f9aactive
  • claude-fable-5-2
  • claude-opus-5.5
  • gpt-astra-6
  • gemini-argon-4
  • claude-sonnet-5
  • gpt-5
  • gemini-3-pro
  • claude-haiku-4.5
  • gemini-2.5-flash
  • gpt-5-mini
  • +246 more

The right model per task

Plan with a frontier model, build with a balanced one, fan out sub-agents on a fast one. Just by name.

  • Planclaude-fable-5-2
  • Buildclaude-sonnet-5
  • Reviewgpt-5
  • Sub-agentsclaude-haiku-4.5

Native protocols

Anthropic and OpenAI wire formats, served as-is. Official SDKs and clients work without shims.

/v1/messagesAnthropic
/v1/responsesOpenAI
/v1/chat/completionsAll models

Built for momentum

Swap to a newer or cheaper model without touching your integration. It is a one-line change.

  client.messages.create({-   model: "claude-sonnet-4.5",+   model: "claude-sonnet-5",    max_tokens: 16000,  })

Balance, usage, history

See your balance, token usage and request history per key, and add credit in seconds.

Balance$84.20

How it works

Two minutes from key to first token

No new SDK, no proxy to run, no prompt rewrites.

  1. Get your key

    Buy a credit pack and your key is ready in the dashboard. It is shown once, in full, so store it like a password.

  2. Point your client at evolved.to

    Set the base URL to api.evolved.to and use your key. Claude Code, Codex, Cursor and the SDKs all support it.

  3. Pick any model by name

    Send claude-opus-5, gpt-5 or any other model ID. Switch whenever you like; your integration stays the same.

export ANTHROPIC_BASE_URL="https://api.evolved.to"
export ANTHROPIC_AUTH_TOKEN="$EVOLVED_API_KEY"
export ANTHROPIC_MODEL="claude-opus-5"

claude
# ~/.codex/config.toml
model = "gpt-5"
model_provider = "evolved"

[model_providers.evolved]
name = "evolved.to"
base_url = "https://api.evolved.to/v1"
env_key = "EVOLVED_API_KEY"
wire_api = "responses"
import os
import anthropic

client = anthropic.Anthropic(
    base_url="https://api.evolved.to",
    api_key=os.environ["EVOLVED_API_KEY"],
)

message = client.messages.create(
    model="claude-opus-5",
    max_tokens=16000,
    messages=[{"role": "user", "content": "Hello, Claude"}],
)

for block in message.content:
    if block.type == "text":
        print(block.text)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.evolved.to/v1",
  apiKey: process.env.EVOLVED_API_KEY,
});

const response = await client.responses.create({
  model: "gpt-5",
  input: "Hello!",
});

console.log(response.output_text);

Compatible clients

Works where you already work

Terminal agents, editors, desktop apps, automations, games and SDKs. Every guide takes a couple of minutes.

Security

Private by design, not by policy page

Your requests, your keys and your usage data are handled on a least-exposure principle, end to end over TLS 1.3.

Keys you control

Keys are hashed before they are stored and shown in full only once. Revoke or rotate one in a click, without touching the others.

Checked before routing

Every request is validated (key, balance and rate limits) before it reaches a model. Inactive keys are rejected at the edge.

Private by default

Request content is kept encrypted for at most 7 days for support, then deleted. Full keys and authorization headers are never logged.

FAQ

Questions, answered

Something else? Our docs cover every client and error code, and support answers from your dashboard.

evolved.to is an API gateway that gives you one key for 256 models: Claude, ChatGPT and Gemini, and DeepSeek, Grok, Kimi, Qwen, Mistral, Llama, GLM, MiniMax, MiMo, Nemotron, Sonar, Command and Hunyuan. You point your tools at our base URL, and we route each request to the model's provider for you, with no separate provider accounts, keys or invoices.

Anything that speaks the Anthropic Messages API or the OpenAI API: Claude Code (terminal and IDE), Codex, Cursor, Cline, Roo Code, n8n, and the official Python and Node SDKs. Our docs have a step-by-step guide for each one.

Yes, on any plan with more than one family: Claude & ChatGPT, an Optional pack with the families you pick, or the Full Pack with every family. The same key works on our Anthropic-compatible and OpenAI-compatible endpoints, and to switch models you change the model name in your request or client settings. The Claude and ChatGPT plans cover one family each, for less.

Pick a plan and buy a credit pack. Claude packs run from $50 of credit for $20 up to $2,000 for $150; ChatGPT packs from $20 to $150; Claude & ChatGPT packs from $25 to $155; an Optional pack of the families you choose, priced like one or two families, plus a step for each family past two ($2.50 on the smallest pack up to $15 on the largest; three families from $27.50 to $170), never more than the Full Pack; and the Full Pack, every family, from $32.50 to $200. Each request draws from your credit at the published rates on our Models page, so you only use what you need. There are no subscriptions and no per-seat fees.

Your key's credit is checked before each request runs. When it is used up, requests are rejected with an insufficient_balance error instead of running up a bill. Buy another credit pack from your dashboard and we add the credit to your key.

Crypto, through a secure hosted checkout: USDC and USDT, Bitcoin, Ethereum and more than 100 other coins. Once the payment confirms, your API key is shown once in your dashboard, and we email you when it is ready.

No. Our servers pass requests through without storing their content, and we never log API keys or authorization headers. Chats in your dashboard are saved only in your own browser.

No. evolved.to is an independent service. Claude is a trademark of Anthropic, and ChatGPT and GPT are trademarks of OpenAI.

Your next model is one line away.

Get a key, set a base URL, and ship with every Claude, ChatGPT and Gemini model today.

Already have a key?

Open your dashboard to check your balance, token usage and request history, or add credit in seconds.

Open dashboard