Inkling-Small Available on Together AI for Cost-Effective Agentic Coding
togethercompute · x · 2026-07-31
Together AI has announced a high-throughput production API for developers to run the Inkling-Small model on NVIDIA accelerated infrastructure.
The model is specifically designed for multimodal, coding, and agentic workloads. Official benchmarks show it scoring 89.5 on AIME 2025 and handling real-repository software engineering tasks at one-fifth the cost of the original Inkling. It accepts text, images, and audio in a single request and features variable thinking effort to optimize the cost-quality trade-off.
Related event: Inkling-Small: 276B params, 12B active, open-source tops ARC(48 posts)→
More from coding & agent
- 'LLM code is sloppy' rebutted with real ffmpeg code: identical if/else branches in a top library — kingslyj · 2026-10-16
- Office-editing tool calls need file, worktree and unit: lessons from dsh-univer-office — FunDistribution6537 · 2026-10-16
- Architect MD workflow: Gemini one-shot outputs that beat Opus, via 5-lens plan critique — oikk01 · 2026-10-16
- Prove a coding agent actually ran the tests: check artifacts, not approvals — ComprehensiveShake76 · 2026-10-16
- Building an acceptance harness for AI spreadsheet edits: allowlists, recalc checks, idempotency — ukdicha-modakkk · 2026-10-16
- Agent actions need checks outside the model: NVIDIA demos lean on guardrails amid wave of real agent incidents — Creamy-And-Crowded · 2026-10-16