@pi-vault/pi-providers
Pi extension that adds MiniMax and StepFun custom model providers
Package details
Install @pi-vault/pi-providers from npm and Pi will load the resources declared by the package manifest.
$ pi install npm:@pi-vault/pi-providers- Package
@pi-vault/pi-providers- Version
0.2.0- Published
- Jul 12, 2026
- Downloads
- 128/mo · 45/wk
- Author
- lanhhoang
- License
- MIT
- Types
- extension
- Size
- 29.9 KB
- Dependencies
- 0 dependencies · 2 peers
Pi manifest JSON
{
"extensions": [
"./src/index.ts"
]
}Security note
Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.
README
@pi-vault/pi-providers
Register MiniMax M3 and StepFun Flash reasoning models as custom providers for Pi.
Install, Upgrade, And Reload
pi install npm:@pi-vault/pi-providers
Then reload Pi:
/reload
Quick Start
Set the API keys for the providers you want to use before launching Pi:
# MiniMax global endpoint (minimax-openai)
export MINIMAX_API_KEY="..."
# MiniMax China endpoint (minimax-openai-cn)
export MINIMAX_CN_API_KEY="..."
# StepFun Step Plan endpoint (stepfun-ai)
export STEP_API_KEY="..."
After reloading, the providers appear in Pi's model picker:
- Select
minimax-openai(orminimax-openai-cn) and chooseMiniMax-M3. - Select
stepfun-aiand choose one ofstep-3.7-flash,step-3.5-flash-2603, orstep-3.5-flash.
Ask Pi normally; there is no provider-specific prompt syntax. Image input works with MiniMax-M3 and step-3.7-flash.
Providers And Models
| Provider | Model | Input | Reasoning | Context | Max output | Input / output per 1M tokens | Cache read |
|---|---|---|---|---|---|---|---|
minimax-openai / minimax-openai-cn |
MiniMax-M3 |
text, image | yes | 1,000,000 | 512,000 | $0.60 / $2.40 | $0.12 |
stepfun-ai |
step-3.7-flash |
text, image | low / medium / high | 256,000 | 256,000 | $0.20 / $1.15 | $0.04 |
stepfun-ai |
step-3.5-flash-2603 |
text | low / high | 256,000 | 256,000 | $0.10 / $0.30 | $0.02 |
stepfun-ai |
step-3.5-flash |
text | automatic (shown as high) | 256,000 | 256,000 | $0.10 / $0.30 | $0.02 |
API bases:
minimax-openai:https://api.minimax.io/v1minimax-openai-cn:https://api.minimaxi.com/v1stepfun-ai:https://api.stepfun.ai/step_plan/v1
Cache writes are free for all models.
Known Limits
- Key matching. The provider code passes the corresponding environment-variable reference (
$MINIMAX_API_KEY,$MINIMAX_CN_API_KEY,$STEP_API_KEY) to Pi. If the variable is unset, the provider cannot authenticate. - MiniMax tool-call hardening. MiniMax wraps its stream with a provider-specific pipeline that folds inline
thinkblocks into a properthinkingcontent block, repairs empty{}tool-call arguments via second-chance JSON parse, and reorders tool-result messages to match the order of precedingtool_useblocks. M3 rejects mismatched ordering. - StepFun native stream. StepFun uses Pi's built-in OpenAI-compatible driver directly, without the MiniMax hardening pipeline.
- Deeply nested tool schemas. MiniMax M3 may produce collapsed nested arguments on complex JSON schemas. The package emits a diagnostic message instead of retrying.
Development And Verification
pnpm install
pnpm check
pnpm release:check
Changelog
See CHANGELOG.md for release notes.
License
MIT. See LICENSE.