November 12 agent guide: Gemini 4 Hydrogen, Inkling weights, SGLang
November 12, 2026 closed the window with a broad Gemini 4 worker, an Apache 2.0 open-weight drop, and an inference consortium. Google released Gemini 4 Hydrogen, Thinking Machines published Inkling 2 Small weights, LMSYS launched the SGLang Consortium, and Claude Code 2.1.323 added experimental Code Mode.

In this post (8 sections)
November 12, 2026 closes this Bacancy Technology window with three infrastructure-scale moves. Google released Gemini 4 Hydrogen for everyday agentic execution and put Gemini 4 in front of Search users. Thinking Machines opened Inkling 2 Small weights under Apache 2.0. LMSYS launched the SGLang Consortium for open inference. Claude Code 2.1.323 added experimental Code Mode for tool calls through generated JavaScript.
What shipped on November 12
| Release | Source | Status | Builder action |
|---|---|---|---|
| Gemini 4 Hydrogen | API, Search, Gemini app, Antigravity | Migrate 3.8 Flash agent lanes; keep Carbon/Argon for deep work | |
| Inkling 2 Small weights | Thinking Machines | Apache 2.0 on Hugging Face | Bench hosted APIs first; self-host only with 500GB+ VRAM |
| SGLang Consortium | LMSYS Org | Founding members live | Track roadmap notes if you serve open models at scale |
| Claude Code 2.1.323 Code Mode | Anthropic | Experimental opt-in | Pilot in a sandbox; leave org default off until reviewed |
Gemini 4 Hydrogen
Hydrogen is Google’s rapid-execution model for coding and agentic workflows, adapted from Gemini 4 Carbon. Google prices it flat across the entire 1M-token context at $1.50 input and $7.50 output per million tokens. Google reports Artificial Analysis Intelligence Index 51 at default high thinking (54 at xhigh), Terminal-Bench 4.1 at 57% versus 18.2% for Gemini 3.8 Flash, and roughly 2.5x faster task completion at high default versus that prior Flash lane.
Orchestrator and multi-model work
Google Antigravity’s Orchestrator can switch between Carbon and Hydrogen in one session. Google reports near-Carbon Terminal-Bench 4.0 success with about 24% less quota and 19% faster completion on average when Orchestrator mixes models. For parallel agents, Carbon can coordinate while Hydrogen powers workers and verifiers. Four thinking levels (low, medium, high default, xhigh) let teams trade latency and cost without changing model ids.
- Agents’ Last Exam v1.1: 71.6% (model card).
- AutomationBench-AA: 76.1%.
- SWE-sweep: 13.5%.
- Multimodal Knowledge Agent: 53.4%.
- Safety notes include large cuts in agentic overreach/under-service versus 3.8 Flash and stronger indirect prompt-injection resilience on Gray Swan IPI, per Google.
Inkling 2 Small open weights
Thinking Machines Lab launched Inkling 2 Small on November 5 with closed weights and promised Apache 2.0 after external safety testing. On November 12 the weights landed on Hugging Face with NVFP4 and MXFP8 checkpoints, plus serving recipes for Unsloth, SGLang, vLLM, and TokenSpeed. Architecture: 594B total / 17B active MoE, native image input, 1M context. Hardware bar is high: NVFP4 wants at least 500GB aggregate GPU VRAM. Bacancy Technology recommends hosted endpoints for most teams and self-host only where the cluster already exists.
SGLang Consortium and Claude Code Mode
LMSYS Org launched the SGLang Consortium with NVIDIA, AMD, Intel, Google, Meta, Cloudflare, Modal, and RadixArk at the first SGLang Summit. Members join roadmap meetings; maintainers keep merge control. The same day, Claude Code 2.1.323 added experimental Code Mode so Claude can write JavaScript to call tools, plus MCP SDK v1 compatibility mode because the v1 MCP client is removed, and stricter MCP sign-in confirmation even in bypass and auto modes.
Builder checklist
- 01Point everyday Gemini agents at HydrogenKeep Carbon and Argon for deep debugging and research. Measure cost per task before making Hydrogen the Antigravity default.
- 02Add Inkling 2 Small to the open-weight matrixRun the same SWE and document tasks used for Kimi K3.1 Pro weights; skip self-host unless VRAM budget clears 500GB.
- 03Review Claude Code 2.1.323 before fleet upgradeRead Code Mode docs, confirm MCP OAuth confirmation behavior, and leave Code Mode off for org defaults until a sandbox pilot passes.
Conclusion
November 12 gives builders a broad Gemini 4 worker, a serious Apache 2.0 open-weight option, and clearer open-inference governance. Read it with November 9’s Fable/Ember split: frontier for hard jobs, Hydrogen and Ember for volume, open weights where clusters and licenses allow.
Related reading
- November 11 Decisions API and Qwen4-Max: /blog/november-11-gemini-decisions-qwen4-max-2026
- November 9 Fable 5.2 and Muse Ember: /blog/november-09-claude-fable-5-2-muse-ember-2026
- November 4 Kimi weights and Hy4: /blog/november-04-kimi-k31-pro-weights-hy4-2026
- Open-source topic map: /topics/agentic-ai
- Consulting: /consulting/
Need Gemini 4 and open-weight routing reviewed?
Bacancy Technology designs Gemini family routing, open-weight self-host plans, and Claude Code fleet upgrades. Consulting: /consulting/ . Contact: /contact/ .
Sources: Google blog ; thinkingmachines.ai — inkling 2 small ; lmsys.org — 2026 11 12 sglang consortium ; Claude blog .
Agentic AI patterns, delivered Thursdays
What I am shipping, watching, and pruning out of client stacks each week. One email. No fluff.