Coding Tools
Improved Batch Inference API Released
Together AI Bloghigh confidence
Why it matters
- →The improvements in the Batch Inference API can significantly enhance the efficiency and cost-effectiveness of processing large datasets for AI practitioners.
Together AI has launched an enhanced Batch Inference API featuring a new UI, expanded model support, and a significant increase in rate limits to 30B tokens. This update aims to simplify and reduce costs for large-scale AI workloads.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Together AI Launches Batch API for LLM Requests
Together AI Blog · June 11, 2025 · Same story
- 2Hybrid Approach for LLM Inference Proposed
Google Research Blog · September 11, 2025 · Background
What happened next
- 3Together AI Achieves Fastest Inference for Open-Source Models
Together AI Blog · December 1, 2025 · Related
- 4Titans and MIRAS Enhance AI Long-Term Memory
Google Research Blog · December 4, 2025 · Background
- 5AlphaEvolve: New Coding Agent from DeepMind
AI Explained · December 23, 2025 · Background
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
llama.cpp Releases