Big Pickle: OpenCode Zen Stealth Model

Updated: 2026-09-07

Everything you need to decide: what Big Pickle does, who it fits, and whether it is free.

Big Pickle is a stealth model from OpenCode Zen—you get the capability without knowing which underlying model powers it. What matters is output quality.

Model ID: big-pickle
Provider: OpenCode Zen
API: openai-completions
Base URL: https://opencode.ai/zen/v1
Context: 200,000 tokens
Max output: 32,000 tokens
Input: text
Reasoning: ✓
Pricing: USD 0 input · USD 0 output · USD 0 cache read · USD 0 cache write

Free right now. Input, output, cache read, and cache write all at USD 0. Limited-time offer—confirm current pricing before committing.

200,000-token context window. Feed it an entire module or small project—it reads and modifies across files.

32,000-token max output. Enough for complete implementation plans, multi-layer patches, or detailed architecture docs.

Reasoning enabled. Built for complex refactors, hard-to-reproduce bugs, and architecture trade-offs—anything that needs multi-step thinking.

Text input. Paste code, describe requirements, provide context—pure text, no image input.

How to use it

1.Select or configure Big Pickle in OpenCode with the model ID big-pickle and your OpenCode Zen API key.
2.Pi records the API as openai-completions and the Base URL as https://opencode.ai/zen/v1; prefer the official OpenCode installer and model-selection flow.
3.Put the task, constraints, and relevant code into your text prompt, use reasoning and the long context for implementation, review, or debugging, then validate the result.

Use cases

Cross-file reading and modification in large codebases—200k context fits.
Debug hard-to-reproduce bugs and document reproduction steps—reasoning breaks down causality.
Compare architecture options, weigh risks, and get an actionable rollout plan.
Draft refactor patches, tests, and migration docs in one pass.

FAQ

What is Big Pickle?

A stealth model from OpenCode Zen. You get the capability without knowing which underlying model powers it.

Is Big Pickle free now?

Yes. Currently USD 0 across the board—limited-time offer, confirm before committing.

When should I use Big Pickle?

When the task needs long context, reasoning, or cross-file understanding—large-codebase refactors, hard-to-reproduce bugs, architecture comparisons.

Configuration

{
  "providers": {
    "opencode": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "big-pickle",
          "name": "Big Pickle",
          "reasoning": true,
          "input": [
            "text"
          ],
          "contextWindow": 200000,
          "maxTokens": 32000,
          "cost": {
            "input": 0,
            "output": 0,
            "cacheRead": 0,
            "cacheWrite": 0
          },
          "compat": {
            "supportsStore": false,
            "supportsDeveloperRole": false,
            "maxTokensField": "max_tokens"
          }
        }
      ],
      "api": "openai-completions",
      "baseUrl": "https://opencode.ai/zen/v1"
    }
  }
}

Compatibility

Feature	Value
supportsStore	No
supportsDeveloperRole	No
supportsReasoningEffort	Yes
supportsUsageInStreaming	Yes
maxTokensField	max_tokens
requiresToolResultName	No
requiresAssistantAfterToolResult	No
requiresThinkingAsText	No
requiresReasoningContentOnAssistantMessages	No
thinkingFormat	openai
openRouterRouting	—
vercelGatewayRouting	—
chatTemplateKwargs	—
zaiToolStream	No
supportsStrictMode	Yes
cacheControlFormat	None
sendSessionAffinityHeaders	No
supportsLongCacheRetention	Yes