llama-index-llms-linkrra

LlamaIndex LLM integration for Linkrra Synap — an OpenAI-compatible inference API for open models (Qwen, gpt-oss, Gemma, GLM, DeepSeek and more), billed per token.

Not to be confused with other products named "Synap". This package talks to https://synap402.com/v1, operated by Linkrra.

Install

pip install llama-index-llms-linkrra
export LINKRRA_API_KEY="your-api-key"   # get one at https://synap402.com

Use

from llama_index.llms.linkrra import Linkrra
from llama_index.core.llms import ChatMessage

llm = Linkrra(model="qwen3-coder-30b")

print(llm.complete("Write a haiku about open models."))
print(llm.chat([ChatMessage(role="user", content="Say hello.")]))

for chunk in llm.stream_complete("Count from 1 to 5."):
    print(chunk.delta, end="")

model="synap-v1" (the default) lets Synap pick the cheapest model that can do the job. The live list of model ids, context lengths and per-token prices is at https://synap402.com/v1/models. Set context_window= to match the model you use (default: a conservative 32768).

Use it as the default LLM:

from llama_index.core import Settings
Settings.llm = Linkrra(model="qwen3-coder-30b")

Configuration

Tests

pip install -e ".[test]"
pytest tests            # offline; the live test runs only if LINKRRA_API_KEY is set

License

Apache-2.0