Providers
Each provider needs its API key in the run's environment, stored with Pullfrog or in GitHub Actions secrets.
Supported providers
| Provider | API key env var |
|---|---|
| Anthropic | ANTHROPIC_API_KEY (or a Claude subscription) |
| OpenAI | OPENAI_API_KEY (or a Codex subscription) |
GOOGLE_GENERATIVE_AI_API_KEY or GEMINI_API_KEY | |
| xAI | XAI_API_KEY (or a Grok subscription) |
| DeepSeek | DEEPSEEK_API_KEY |
| Moonshot AI | MOONSHOT_API_KEY |
| Meta | META_MODEL_API_KEY, from the Meta Model API, for Muse Spark, Muse Wonder and Muse Ember |
| Kimi Code | KIMI_API_KEY, from a Kimi membership rather than a Moonshot API balance |
| OpenCode | OPENCODE_API_KEY: one key for Zen and Go, also required for the free Zen models |
| OpenRouter | OPENROUTER_API_KEY |
| Vercel AI Gateway | AI_GATEWAY_API_KEY |
| Amazon Bedrock | AWS_BEARER_TOKEN_BEDROCK (or AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY) + AWS_REGION + BEDROCK_MODEL_ID |
| Google Vertex AI | VERTEX_SERVICE_ACCOUNT_JSON + GOOGLE_CLOUD_PROJECT + VERTEX_LOCATION + VERTEX_MODEL_ID |
| Azure OpenAI | AZURE_RESOURCE_NAME + AZURE_API_KEY + AZURE_DEPLOYMENT + AZURE_CONTEXT + AZURE_MAX_OUTPUT |
| Custom › OpenAI-compatible | OPENAI_COMPATIBLE_BASE_URL + OPENAI_COMPATIBLE_API_KEY + OPENAI_COMPATIBLE_MODEL + OPENAI_COMPATIBLE_CONTEXT + OPENAI_COMPATIBLE_MAX_OUTPUT |
Custom providers
The table above lists the providers the console has a card for. Any other provider in the models.dev catalog runs too, through OpenCode: Groq, Mistral, Cerebras, Together, Fireworks and the rest switch on as soon as their API key is in the run's environment.
Set the account to BYOK
Select BYOK in the Providers section of the Billing card. On Pullfrog Router the server hands the run a Router credential before it starts, and it cannot see a key that lives only in GitHub Actions secrets.
Add the key
Add it as a GitHub Actions secret, under the exact name that provider's models.dev page declares.
Map the key and name the model
The specifier must be one models.dev lists; the run checks it against the provider's catalog before starting. Non-secret settings some providers want, such as a region or an endpoint, go straight in env:.
- name: Run agent
uses: pullfrog/pullfrog@v0
with:
prompt: ${{ inputs.prompt }}
model: groq/llama-3.3-70b-versatile
env:
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}Release the console model
A model stored for the repository in the console beats the workflow's model input, so pick Custom (set in workflow), or Inherit from org if your organization has a default. The job log confirms the specifier took:
» "groq/llama-3.3-70b-versatile" is not a curated alias — passing through as a raw model specifierUse OpenAI-compatible endpoints instead when your provider isn't in the catalog, when you front several providers behind one gateway, or when you need a model ID the catalog doesn't carry.
Routers
OpenRouter, OpenCode Zen, OpenCode Go and Vercel AI Gateway are providers like any other, with their own aliases (OpenRouter's "Claude Opus" is openrouter/~anthropic/claude-opus-latest). To pin an exact version instead of the rolling alias, set the model input to the full specifier:
with:
model: openrouter/anthropic/claude-sonnet-5
env:
OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}OpenCode Zen and OpenCode Go
Zen and Go are two OpenCode plans behind one credential. Store OPENCODE_API_KEY once and both groups appear in the picker.
| Plan | Billing | Models |
|---|---|---|
| OpenCode Zen | Pay as you go | Claude, GPT, Gemini, Grok, Kimi, MiniMax, GLM, Qwen, Mistral, MiMo, LongCat, Step, Muse |
| OpenCode Go | $10/month, capped usage | GLM, Qwen, Kimi, MiniMax, MiMo, LongCat, Hy, plus Grok and GPT Luna |
Most of the Go catalog is not served on Zen, so the two groups are different menus.
Models the picker does not carry
The picker is a curated menu. Any other model either endpoint serves runs by its full models.dev specifier:
with:
model: opencode-go/mimo-v2-omni
env:
OPENCODE_API_KEY: ${{ secrets.OPENCODE_API_KEY }}Set the console model to Custom (set in workflow) so a stored pick does not beat the workflow input, as with custom providers.

