@benvargas/pi-synthetic-provider

Synthetic model provider for pi, the AI coding agent.

Features

• Dynamic model discovery -- models fetched live from the Synthetic API at each session start
• OpenAI Completions API -- reuses pi's built-in streaming, no custom implementation
• Tool calling -- full support via OpenAI-compatible tool use
• Vision support -- image input for models that support it (e.g., Kimi-K2.6)
• Reasoning support -- extended thinking for reasoning-capable models
• Cost tracking -- accurate per-token pricing parsed from the API
• Graceful degradation -- fallback model list if the API is unreachable

Installation

pi install npm:@benvargas/pi-synthetic-provider

Or try without installing:

pi -e npm:@benvargas/pi-synthetic-provider

Setup

Option 1: Environment Variable

export SYNTHETIC_API_KEY="syn_your_key_here"
pi

Option 2: Auth Storage (persistent)

Add to ~/.pi/agent/auth.json:

{
  "synthetic": {
    "type": "api_key",
    "key": "syn_your_key_here"
  }
}

Option 3: Runtime CLI Flag

pi --model synthetic/hf:moonshotai/Kimi-K2.6 --api-key syn_your_key_here

Usage

# Interactive model selection
pi /model

# Direct model selection
pi --model synthetic/hf:moonshotai/Kimi-K2.6

# Or use provider + model flags separately
pi --provider synthetic --model hf:moonshotai/Kimi-K2.6

Extension Command

• /synthetic-models -- display all available models with pricing and capabilities
• /synthetic-quota -- display current Synthetic API quota usage, including rolling five-hour, weekly token, and search limits when available

Available Models

Models are fetched at startup from the Synthetic models endpoint. If the startup fetch fails, times out after three seconds, or returns no supported models, the provider falls back to the following hardcoded defaults:

Model	ID	Reasoning	Vision	Context	Max Output
Synthetic Large Text	syn:large:text	Yes	No	524K	65K
Synthetic Small Text	syn:small:text	Yes	No	196K	65K
Synthetic Large Vision	syn:large:vision	Yes	Yes	262K	65K
Synthetic Small Vision	syn:small:vision	Yes	Yes	262K	65K
GLM 5.2	hf:zai-org/GLM-5.2	Yes	No	524K	65K
GLM 5.1	hf:zai-org/GLM-5.1	Yes	No	196K	65K
Kimi K2.6	hf:moonshotai/Kimi-K2.6	Yes	Yes	262K	65K
Qwen 3.6 27B	hf:Qwen/Qwen3.6-27B	Yes	Yes	262K	65K
MiniMax M3	hf:MiniMaxAI/MiniMax-M3	Yes	Yes	524K	65K
GLM 4.7 Flash	hf:zai-org/GLM-4.7-Flash	Yes	No	196K	65K
Nemotron 3 Super 120B	hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4	Yes	No	262K	65K
GLM 4.7	hf:zai-org/GLM-4.7	Yes	No	203K	65K
GPT OSS 120B	hf:openai/gpt-oss-120b	No	No	131K	32K
Qwen 3.5 397B A17B	hf:Qwen/Qwen3.5-397B-A17B	No	Yes	262K	32K

Run /synthetic-models inside pi for the live catalog.

API Key Priority

When multiple sources are configured, pi checks in this order:

1. CLI runtime flag (--api-key)
2. Auth storage (~/.pi/agent/auth.json)
3. OAuth credentials (if configured)
4. Environment variable (SYNTHETIC_API_KEY)

Requirements

• pi v0.70.2 or later
• A Synthetic API key from synthetic.new

Notes

• On newer Synthetic accounts, /synthetic-quota prefers the current rolling five-hour and weekly token limits over the legacy subscription bucket, while still showing search usage when present.
• The provider refresh path is compatible with current pi releases that expect dynamic provider updates to go through pi.registerProvider(...).

Uninstall

pi remove npm:@benvargas/pi-synthetic-provider

License

MIT