Models
66 RohitAI articles on Models: news, explainers and practical guides, newest first.
Liquid d1 Adds Vision: When to Use a Decision Model Instead of Chat
A guide to Liquid d1’s paid vision API, per-question image costs, and the checks needed before replacing chat-based classifiers.
Reflection Beam Enters Waitlisted Beta; Open Weights Planned for October
Reflection’s Beam beta supports text-based coding and agents, but Apache-2.0 weights are pending. What builders can evaluate now—and what must wait.
Kolibri-1 Self-Hosting: GPU Requirements and German-English Evaluation
Assess Kolibri-1 for private German-English assistants: FP8 versus BF16 GPU needs, context limits, vLLM compatibility and pre-deployment checks.
Microsoft MAI-Transcribe-2-Streaming and Voice 2.1: Preview Integration and Pricing
How to integrate Microsoft’s MAI speech previews: handle changing transcripts, choose a voice, and budget recognition and synthesis separately.
Cloudflare Clef on Workers AI: Routing Requests, Probabilities and Costs
How to use Clef and Clef-flash for typed agent routing: Workers AI request formats, review thresholds, hosted limits and input-cost calculations.
Gemini 4 Argon: Access, Pricing and What Builders Can Prepare
Gemini 4 Argon starts with approved cyber defenders. Understand its announced prices, cache-cost tradeoffs and what to prepare before wider access.
Holo4: The Case for Routing Computer Use by Workflow
H Company’s Holo4 combines GUI, code and API actions. Its split licenses, public traces and long-workflow results change how builders should deploy it.
GPT-6 Sol and Luna Cut the Cost of Trying. Build for Acceptance.
GPT-6 Sol and Luna lower API prices and reach Work and Codex. Here is how caching, verification and routing change the economics for builders.
Claude Opus 5.5 Makes Long Agent Runs Cheaper—and Changes the Rules
Claude Opus 5.5 cuts token and cache prices. Here is what builders must change in thinking, tool execution, session state, and completion checks.
Grok 4.7 Is Public. Test the State Contract, Not the 500K Window
Grok 4.7 keeps 4.6’s 500K context and pricing. Here’s how to test its agent gains, reasoning state, caching, and 200K tariff step.
Fugu Max Turns Model Orchestration Into a Spending Policy
Sakana’s Fugu Max and Ultra v2 turn learned routing into an API product. Builders should measure accepted-task cost, drift, and opacity.
Cognition’s SWE-2 Trains Devin to Spend Effort Where It Pays
Cognition’s SWE-2 turns Kimi K3 into a cost-aware Devin worker. Here’s how to read its benchmarks, effort levels and Terminal-Bench 4 gap.