GuidesHosting choices

OpenCode pricing: free, Go at $10, Zen, and the plans it takes

OpenCode is free; you pay for the model: Go, Go Plus or Go Teams, pay-as-you-go Zen, ChatGPT, Copilot, an API key, or a Claude plan through Claude Code.

October 9, 2026Updated November 7, 2026The Everpod team
The short answer

OpenCode itself is free and open source (MIT), and comes with free models that have a daily cap. What you pay for is the model. As of November 7, 2026, that is one of: OpenCode’s own Go subscription at $10 a month (Go Plus at $40, or Go Teams at $20 a member for a shared workspace) for a lineup of 32 coding models; its pay-as-you-go catalogue, called Zen on OpenCode’s site and OpenCode Console in the version 2 docs and the app, at the providers’ own token prices plus a card fee; or a plan or key you already have.

Plans you can bring: ChatGPT Plus or Pro (OpenAI lists OpenCode among the apps that can use your plan), GitHub Copilot, GitLab Duo, a SuperGrok subscription, and an API key from almost any provider, OpenRouter included. For a Claude plan, OpenCode’s own route since version 2.2.3 (October 30, 2026) is its Claude Agent provider, which runs your own installed Claude Code, signed in with claude auth login, so the login stays Claude Code’s; whether that use sits within Anthropic’s terms is Anthropic’s call. OpenCode still has no Claude sign-in of its own, and Anthropic’s models otherwise go in by API key.

What is free

The program is free under the MIT licence, with no account needed. The home page’s answer to what it costs: “OpenCode is 100% free to use. It also comes with a set of free models. There might be additional costs if you connect any other provider.” The free models change from week to week, each “for a limited time”; which ones OpenCode offered on October 22, and the catches on each, are in OpenCode’s models. Free use has a daily cap. The Go page gave it as “200 requests/day” until October 22, when OpenCode took the line down, and no page of OpenCode’s now gives a number. Two catches sit in the docs’ privacy notes: on several of them, “During its free period, collected data may be used to improve the model,” and the free Nemotron endpoints say “Trial use only — do not submit personal or confidential data.” Free models are fine for trying OpenCode out; for work you would not paste into a public form, pay for a model.

OpenCode Go and Go Plus

Go is a monthly subscription to a curated lineup of coding models, sold mostly as open models; the list also includes Claude Haiku 5.5, GPT 6 Luna, GPT 5.6 Luna, Grok 4.7 and Gemini 4 Argon.

GoGo Plus
Price
$10 a month$40 a month
Models
The same lineup: 32 in the docs on November 7, three of them free for a limited time, among them Kimi K3.1 Pro, Kimi K3, GLM-5.3, DeepSeek V4.1 Flash, Qwen3.8, MiniMax M3, Hy4, Grok 4.7 and Claude Haiku 5.5
How limits work
A monthly dollar amount per model, with 20% of it usable in any 5 hours and 50% in a week; token prices are the same on both plans
Monthly limit, Kimi K3
$15 (about 110 requests per 5 hours, by OpenCode’s estimate)$60 (about 440)
Monthly limit, DeepSeek V4.1 Flash
$100 (about 43,330 requests per 5 hours)$200 (about 86,670)
At the limit
Fall back to the free models, or switch on paying from your pay-as-you-go balance

A few terms worth knowing before you subscribe. Go and Go Plus are for one person: “Go and Go Plus are for workspaces with a single member.” For a team there is Go Teams, $20 a member a month, which gives every member their own limits, $5 a month higher than Go’s on every model, and starts with paying from your balance at the limit switched on. By default Go blocks paid endpoints that train on what you send, and runs requests in Europe and the United States; both are settings. It isn’t tied to OpenCode: “Yes, you can use Go with any agent,” and the docs list Claude Code, Codex, Hermes and Pi among the clients OpenCode has checked, with no promise they keep working. You can cancel any time, and a refund is possible within 14 days if you haven’t used that period’s allowance. Neither the Go page nor its docs offer a free trial. The docs add that the service “is designed primarily for international users”. Every Go model, with its allowance, is in the full Go lineup.

Pay as you go: Zen, or OpenCode Console

The second offer is a catalogue of models OpenCode has tested, paid per token from a prepaid balance. OpenCode’s site and the version 1 docs called it OpenCode Zen; the version 2 docs and the app call it OpenCode Console, and by November 7 the opencode.ai/zen address opened the Console’s models page. OpenCode adds no markup of its own and passes on the card fee, 4.6% plus $0.31 a purchase ($1.23 on a $20 top-up). You add credit ($10, $50, $100 or an amount you choose), and can have it top up by itself when the balance runs low, at a level and amount you set; you can set monthly limits, and requests fail once the balance hits zero. A few prices per million tokens, input and output, on November 7: Claude Fable 5.1 $10 and $50, Claude Opus 5.5 $4 and $20, Claude Sonnet 5.5 $2 and $10, GPT 6.1 Sol $2 and $10 up to 272,000 tokens of context, Gemini, Grok, Qwen, DeepSeek and the rest beside them.

OpenCode’s docs say its models are “hosted in the US and EU”, and that the providers keep no data and don’t train on it, with listed exceptions: requests to OpenAI’s and Anthropic’s APIs are kept for 30 days.

Two other names turn up on OpenCode’s site. OpenCode Black, a subscription to the frontier models, showed only “Black plan enrollment is temporarily paused” on October 9, and since October 22 its address has opened the Go page. Enterprise is per seat, with no charge for tokens that go through a company’s own model gateway.

Plans and keys you already have

What you haveWorks in OpenCode?How it connects
ChatGPT Plus or Pro
Yes; usage counts against your plan’s limitsSign in with ChatGPT (OpenAI, then the ChatGPT option)
GitHub Copilot
Yes; some models need Pro+Device sign-in at github.com/login/device
GitLab Duo
Yes, experimental; Premium or UltimateGitLab sign-in or a personal access token
SuperGrok or an X plan with Grok API access
YesDevice sign-in
An API key (Anthropic, OpenAI, Google, OpenRouter and 75+ more)
Yes, billed by the provideropencode auth login, or the provider’s environment variable
A local model (Ollama, LM Studio, vLLM)
Yes, freeVersion 2 finds a running Ollama, LM Studio or vLLM by itself
Claude Pro, Max or Ultra
Through your own Claude Code, from OpenCode 2.2.3; Anthropic’s terms, belowInstall Claude Code, run claude auth login, then choose Claude Agent in /connect

On the ChatGPT row, OpenAI’s Sign in with ChatGPT page names OpenCode under its open-source integrations and says “eligible ChatGPT Plus and Pro subscribers can also choose to use their ChatGPT plan for AI requests.” The usage comes out of the same allowance Codex draws on: “Connecting an app does not add a new allowance.” You can cap an app at a share of your weekly usage, and disconnect it under ChatGPT’s Security and login settings. In OpenCode 2 the sign-in is listed as “Sign in with ChatGPT”, beside two older “Codex (legacy)” methods, and 2.2.0 added GPT-6.1 Terra to it; the version 2 providers page names both kinds, and its command-line walkthrough still shows only the legacy one. OpenAI’s pages name Plus and Pro; the ChatGPT plans guide has what each plan includes for Codex.

A Claude plan: through Claude Code

OpenCode used to ship a plugin that signed in with a Claude account. Version 1.3.0 (March 22, 2026) removed it, in a change titled “anthropic legal requests”, and OpenCode 2 offers Anthropic directly by API key or ANTHROPIC_API_KEY and nothing else. What changed on October 30, 2026 is version 2.2.3’s Claude Agent provider. Its release notes: “Install Claude Code, run claude auth login, then select Claude Agent in /connect to use your Claude Code login and models.” In OpenCode’s source, the provider runs the local claude program through Anthropic’s Agent SDK, and its sign-in, labelled “Claude Code login (claude auth login)”, “only records that the user chose Claude Code. The login itself belongs to claude, and the plugin never sees a token.” It needs Claude Code 2.1.248 or newer, takes its models from what Claude Code reports, and OPENCODE_CLAUDE_PATH points it at a Claude Code installed somewhere unusual; the desktop app walks you through the install and sign-in since 2.2.4. OpenCode’s docs don’t cover it yet.

Anthropic’s side is in three pages. Its legal and compliance page says “Anthropic does not permit third-party developers to offer Claude.ai login into their own applications, or to route requests through Free, Pro, Max, or Ultra plan credentials on behalf of their users,” and that this does not prevent “an end user from signing in to the unmodified Claude Code binary with their own Claude subscription.” Its article on the Agent SDK and your plan says that “when you’re signed in with your Claude plan, the Claude Agent SDK and claude -p still draw from your subscription limits.” And its help article on logging in calls an API key the preferred way for other tools, and says Anthropic “may at its discretion allow paid subscribers who have enabled usage credits to use certain third-party tools,” drawn “from usage credits rather than subscription limits”; it names no tool. Whether another app driving your Claude Code falls on the right side of those lines is Anthropic’s call, and your Claude subscription in Hermes, Pi or OpenCode sets each agent’s route beside the same sentences. The route Anthropic calls preferred is an Anthropic API key, billed per token. If you have Max, one thing helps: since October 7, 2026, Max plans include monthly credits for the Claude API, $100 on Max and $200 on Ultra, the plan called Max 20x until late October 2026, and “Everyone with an API key in the linked organization draws from the same balance.” If you want Claude on your Claude plan, Claude Code is the tool that plan covers.

Connecting one

Inside OpenCode, /connect lists the providers and their sign-in methods, and /models picks a model. From a terminal, version 2 does the same with opencode auth login, for example opencode auth login anthropic --method key, and keeps keys and tokens in its local database; version 1 stores them in ~/.local/share/opencode/auth.json. For Go or the pay-as-you-go catalogue you sign in to OpenCode’s console, subscribe or add credit, copy the API key and choose OpenCode Go or OpenCode Console in /connect. For a Claude plan, sign Claude Code in on the same machine first, then choose Claude Agent. On a server with no browser, the ChatGPT, Copilot and Grok sign-ins use device codes, which you finish on your phone; the remote server guide covers reaching OpenCode there once it is signed in.

Two versions, two sets of docs

OpenCode has two release lines. The home page’s install command gives you version 2 (@opencode/cli, 2.2.6 on November 7), whose docs live at opencode.ai/v2/docs; the older line (opencode-ai, 1.19.5) keeps the docs at opencode.ai/docs. opencode --version tells you which you have. For pricing the difference is mostly names (Zen against Console), with one that matters: the Claude Agent provider is in version 2, from 2.2.3.

Run OpenCode on an always-on developer pod.

A developer pod is a permanent cloud computer (VPS), set up and secured for you, with your pick of Claude Code, Codex, OpenCode, Pi, Hermes and OpenClaw installed. Run more agents at once than your laptop can hold, and keep them working when it’s closed. From $24 a month, built in about ten minutes.