OpenCode

OpenCode is an open source AI coding assistant that runs in your terminal. It supports OpenAI-compatible APIs.

Configuration

Add Kyma as a custom provider in opencode.json (in your project, or ~/.config/opencode/opencode.json for every project):

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "kyma": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Kyma",
      "options": {
        "baseURL": "https://api.kymaapi.com/v1",
        "apiKey": "{env:KYMA_API_KEY}"
      },
      "models": {
        "qwen-3.6-plus": { "name": "Qwen 3.6 Plus" },
        "qwen-3-coder": { "name": "Qwen 3 Coder" },
        "deepseek-v4-flash": { "name": "DeepSeek V4 Flash" }
      }
    }
  }
}

Then export your key and run OpenCode:

export KYMA_API_KEY="kyma-your-api-key"
opencode

Pick the model with /models — OpenCode lists them under the kyma provider. Every id in the models block must match an id from GET /v1/models.

Recommended Models

Model	Alias	Best For	Free tier
`qwen-3.6-plus`	`best`	Recommended — highest quality	Yes
`qwen-3-coder`	`code`	Best alias for code-focused tasks	Yes
`kimi-k2.6`	`agent`	Best tool calling, 262K context	No, needs a top-up
`qwen-3-32b`	—	Small, quick coding model (32K context)	Yes
`deepseek-v4-flash`	`cheap`	1M context, value tier. Everyday completions where speed matters.	Yes

A new account’s signup credit is added once your email is verified and spends on free tier models only. Models outside it return 402 model_requires_paid until your first top-up.

curl "https://kymaapi.com/v1/models/recommend?agent=opencode"

See all model aliases for shortcuts.

Prompt Caching

Some models cache a repeated prompt prefix. pricing.cached on /v1/models is the rate Kyma publishes for cached input on that model — usually below its input rate, but not always, so compare the two for the model you use. Every chat completion reports usage.cost, what the request was charged, and usage.cache_discount, Kyma’s figure for what caching saved on it. Whether a prefix is cached automatically or needs a cache_control marker depends on the model’s creator. See Prompt Caching for details.

Guides

Use Cases

Integrations

Configuration

Recommended Models

Prompt Caching

​Configuration

​Recommended Models

​Prompt Caching

Configuration

Recommended Models

Prompt Caching