ReqLLM 1.0.0-rc.7 Released
I’ve published the 1.0.0-rc.7 release of ReqLLM with Elixir 1.19 support on Hex.
It’s been a journey to build this package. LLM Providers are all over the place - but with this release, I’ve been able to successfully prove that the high level API now supports 136 models via a custom fixture testing system I developed.
Several companies and projects have already begun integrating and battle testing this package. With this release, I’m now focused on getting to a stable 1.0 release.
What’s New
Test Coverage: 136 models validated across 10 providers with fixture-based testing against 10 scenarios:
- Core: basic generation, streaming, token limits, usage metrics
- Capabilities: multi-tool calling, tool round-trip, tool avoidance, object generation (streaming/non-streaming), reasoning tokens
Providers: Added Amazon Bedrock (streaming, multi-model, AWS SigV4 auth) and Z.AI (GLM-4.5/4.6, 204K context).
Architecture: Simplified tool call handling with ReqLLM.ToolCall helpers, provider normalize_model_id/1 callback, improved Context API with append/2 and prepend/2.
Examples: Full agent implementation and 16+ runnable scripts covering embeddings, multimodal analysis, tool calling, object generation, reasoning tokens, context reuse.
Validation: Run mix mc to see coverage status. Use REQ_LLM_FIXTURES_MODE=record to test against live APIs.
