Use CoralBricks with OpenCode

Run OpenCode's coding agent on CoralBricks open-model inference — GLM and Kimi with up to 1M context, one JSON stanza to set up.

OpenCode is an open-source terminal coding agent with first-class support for custom OpenAI-compatible providers. CoralBricks plugs in with a single config block — chat, agent mode, and tool calling all route through the Coral gateway.

Coral Inference is currently a design-partner program. To get access, contact us at hello@coralbricks.ai.

1. Get an API key

Create a key from your API keys page (format ak_...), then export it where OpenCode can see it:

export CORAL_API_KEY="ak_..."

Add the export to your shell profile (~/.zshrc / ~/.bashrc) so it persists.

2. Add the provider

Merge this into ~/.config/opencode/opencode.json (create the file if it doesn't exist):

{
  "$schema": "https://opencode.ai/config.json",
  "model": "coral-bricks/glm-5.2-fp4",
  "provider": {
    "coral-bricks": {
      "name": "Coral Bricks",
      "api": "openai",
      "options": {
        "baseURL": "https://inference.coralbricks.ai/v1",
        "apiKey": "{env:CORAL_API_KEY}"
      },
      "models": {
        "glm-5.2-fp4": {
          "name": "GLM 5.2",
          "tool_call": true,
          "reasoning": true,
          "limit": { "context": 1048576, "output": 32768 }
        },
        "kimi-k3": {
          "name": "Kimi K3",
          "tool_call": true,
          "reasoning": true,
          "attachment": true,
          "limit": { "context": 1048576, "output": 32768 }
        },
        "kimi-k2.6": {
          "name": "Kimi K2.6",
          "tool_call": true,
          "reasoning": true,
          "limit": { "context": 262144, "output": 32768 }
        },
        "gpt-oss-120b": {
          "name": "GPT-OSS 120B",
          "tool_call": true,
          "reasoning": true,
          "limit": { "context": 131072, "output": 32768 }
        }
      }
    }
  }
}

3. Run it

opencode                       # interactive TUI, GLM 5.2 by default
opencode run "explain this repo"                    # one-shot
opencode run "fix the failing test" -m coral-bricks/kimi-k3

Switch models any time inside the TUI with /models.

Available models

Model	Slug	Context	Input $/M	Output $/M
GLM 5.2	`glm-5.2-fp4`	1M	$1.40	$4.40
Kimi K3	`kimi-k3`	1M	$3.00	$15.00
Kimi K2.6	`kimi-k2.6`	256K	$0.76	$4.00
GPT-OSS 120B	`gpt-oss-120b`	128K	$0.15	$0.60

Full pricing and the live catalog are on the pricing page.

Notes

Tool calling and agent mode work out of the box — the gateway emits OpenAI-exact streaming tool calls; OpenCode's file edits, shell commands, and multi-step agent loops run unmodified.
Reasoning control: models think by default. Disable per request with "reasoning": {"enabled": false} if you call the API directly; OpenCode manages this itself.
Long context is the point — GLM 5.2 and Kimi K3 take up to 1M tokens, so whole-repo context and long agent sessions fit without pruning.
The API is OpenAI wire-format at https://inference.coralbricks.ai/v1 — the same config shape works in any tool that speaks OpenAI-compatible providers (Cline, Roo Code, Continue, aider). See the API reference for the full surface.