Agents + Batch API.
- Batch API support (50% discount!)
- Expressive. Agents are simple Python functions.
- Concise, lightweight.
- Durable by default.
- Built for >1 million parallel requests.
Quickstart
import parallem as pllm # Place OPENAI_API_KEY in .env file with pllm.resume_directory( ".pllm/simplest", provider="openai", strategy="sync", dashboard=True, load_dotenv=True, ) as orch: with orch.agent() as agt: resp = agt.ask_llm("Please name a power of 3.") print(resp.final_answer)
To switch to the Batch API, simply change strategy="sync" to strategy="batch".
Responses are saved and cached. On the subsequent runs, answers are instant.
Compatibility
| Sync/Batch | OpenAI | Anthropic | Amazon Bedrock | |
|---|---|---|---|---|
| Simple | ✅ | ✅ | ✅ | ✅ |
| Structured Output | ✅ | ✅ | ✅ | ✅* |
| Function Calls | ✅ | ✅ | ✅ | ✅ |
| Web Search | ✅ | ✅ | ✅ | ❌ |
| Image Input | ✅ | ✅ | ✅ | ✅* |
| MCP | ✅ | ✅ | ✅ | ✅ |
*supported models only
Examples
- Agents are python functions
- Structured output
- Tool calls
- Web search
- Image input
- Local MCP
- Server MCP
- 1 million requests
- Ollama
Documentation
Please refer to the documentation.





























