Integrations
Pi
Use BlazeInfer models in Pi, the minimal extensible terminal coding agent.
SupportedTested with: Pi 1.5.0 · Last verified: 2026-11-02
Pi is a minimal, extensible terminal coding agent. BlazeInfer plugs in as an
openai-completions provider.
Prerequisites
- A BlazeInfer account with credits and an API key.
BLAZE_API_KEYset in the shell that starts Pi. A model only appears in Pi's/modelpicker if its key resolves, so the variable must be present.- Node ≥ 22.19 for the recommended install.
Install
npm i -g @earendil-works/pi-coding-agentConfigure
File: ~/.pi/agent/models.json
{
"$schema": "https://pi.dev/schemas/models.schema.json",
"providers": {
"blaze": {
"name": "BlazeInfer",
"baseUrl": "https://blaze.e2enetworks.net/v1",
"api": "openai-completions",
"apiKey": "$BLAZE_API_KEY",
"models": [
{
"id": "deepseek-ai/deepseek-v4.1-flash",
"name": "DeepSeek V4.1 Flash (BlazeInfer)",
"reasoning": true,
"input": ["text", "image"],
"contextWindow": 1048576,
"maxTokens": 16384,
"compat": { "supportsReasoningEffort": false }
},
{
"id": "zai-org/glm-5.3-flash",
"name": "GLM 5.3 Flash (BlazeInfer)",
"input": ["text"],
"contextWindow": 1048576,
"maxTokens": 16384
}
]
}
}
}Then start Pi and choose the model with /model, or launch directly:
pi --provider blaze --model deepseek-ai/deepseek-v4.1-flashChoose a model
| Model ID | Context | Notes |
|---|---|---|
deepseek-ai/deepseek-v4.1-flash | 1,048,576 | The largest context window, for long coding-agent sessions. Reasoning is on by default and comes back in the reasoning field. Accepts images. Use up to 1,048,576 tokens of context. |
zai-org/glm-5.3-flash | 1,048,576 | A 1,048,576-token context window, for long coding-agent sessions. Supports tool calling. Does not accept images. |
See the console for every model, including ones that are not recommended for coding agents.