# Agentic coding

Google's Gemini 4 Hydrogen is now available on AI Gateway, succeeding Gemini 3.8 Flash. It targets agentic coding, knowledge work and tool use, handling longer engineering tasks and producing better-researched documents, spreadsheets and presentations in fewer agent steps while staying in the same latency class. It follows system instructions, formatting requirements and task boundaries more closely, orchestrates tools more reliably across long conversations, and its gains in visual reasoning and technical problem-solving support multimodal workflows.

Google's Gemini 4 Hydrogen is now available on AI Gateway, succeeding Gemini 3.8 Flash. It targets agentic coding, knowledge work and tool use, handling longer engineering tasks and producing better-researched documents, spreadsheets and presentations in fewer agent steps while staying in the same latency class. It follows system instructions, formatting requirements and task boundaries more closely, orchestrates tools more reliably across long conversations, and its gains in visual reasoning and technical problem-solving support multimodal workflows.

Anthropic introduced Claude Opus 5.5, the first model in its new Claude 5.5 family, which the company says performs at the level of Claude Fable 5.1 on most work while costing 40% less to run than Opus 5. Pricing is $4/$20 per million input/output tokens, 20% lower than Opus 5, with cache pricing at $0.20, 60% lower; Anthropic estimates typical overall costs will drop 40% and speed rise 30%. The model is available with zero data retention, its guardrails are similar to Fable 5.1, and the company highlights agentic coding, security and communication.

Anthropic introduced Claude Opus 5.5, the first model in its new Claude 5.5 family, which the company says performs at the level of Claude Fable 5.1 on most work while costing 40% less to run than Opus 5. Pricing is $4/$20 per million input/output tokens, 20% lower than Opus 5, with cache pricing at $0.20, 60% lower; Anthropic estimates typical overall costs will drop 40% and speed rise 30%. The model is available with zero data retention, its guardrails are similar to Fable 5.1, and the company highlights agentic coding, security and communication.

Google released Gemini 4 Carbon for developers, enterprises, scientists and consumers, pitched at long-horizon agentic workflows and cybersecurity. It ranks first on three independent benchmarks, CursorBench 4.0, Perplexity's WANDR and Zapier's AutomationBench, at more than 2X lower cost per task than the next best external model. API pricing matches Gemini 4 Argon at $2 per million input tokens and $10 per million output tokens.

Google released Gemini 4 Carbon for developers, enterprises, scientists and consumers, pitched at long-horizon agentic workflows and cybersecurity. It ranks first on three independent benchmarks, CursorBench 4.0, Perplexity's WANDR and Zapier's AutomationBench, at more than 2X lower cost per task than the next best external model. API pricing matches Gemini 4 Argon at $2 per million input tokens and $10 per million output tokens.

Mistral has moved Mistral Large 4 on AI Gateway to updated weights and lowered the price of input, cached input and output tokens. According to Mistral's release announcement, the new weights improve agentic coding and defensive cybersecurity, use tokens more efficiently on coding tasks, and also improve spreadsheet creation and editing, web research, and resistance to prompt injection. Users already calling mistral/mistral-large-4 through AI Gateway need no model change to get the new weights and pricing.

Mistral has moved Mistral Large 4 on AI Gateway to updated weights and lowered the price of input, cached input and output tokens. According to Mistral's release announcement, the new weights improve agentic coding and defensive cybersecurity, use tokens more efficiently on coding tasks, and also improve spreadsheet creation and editing, web research, and resistance to prompt injection. Users already calling mistral/mistral-large-4 through AI Gateway need no model change to get the new weights and pricing.

Mixture-of-experts models must hold every expert in memory at inference even though each token uses only a few, so deleting the least important experts is a common compression route. HOPE writes the pruning error as a sum of pairwise expert interaction terms, builds an interaction matrix from calibration data, and solves a quadratic program to choose the prune-set. Across Qwen3.5-122B, Qwen3.5-35B and GLM-4.5-Air, HOPE holds an average rank of 1.58 at 50% pruning versus 2.42 for the next-best method, REAP; Qwen3.5-35B-A3B scores 42.3 on SWE-Bench Pro, matching the unpruned model's 41.8 while REAP falls to 36.2.

Mixture-of-experts models must hold every expert in memory at inference even though each token uses only a few, so deleting the least important experts is a common compression route. HOPE writes the pruning error as a sum of pairwise expert interaction terms, builds an interaction matrix from calibration data, and solves a quadratic program to choose the prune-set. Across Qwen3.5-122B, Qwen3.5-35B and GLM-4.5-Air, HOPE holds an average rank of 1.58 at 50% pruning versus 2.42 for the next-best method, REAP; Qwen3.5-35B-A3B scores 42.3 on SWE-Bench Pro, matching the unpruned model's 41.8 while REAP falls to 36.2.

Mixture-of-experts models must keep every expert in memory at inference even though each token uses only a few, so deleting experts by independent importance scores is a common fix. HOPE writes the pruning error as pairwise interaction terms between experts and selects a whole prune-set with a quadratic program, reaching the best average rank across three models, two calibration datasets and several benchmarks. On Qwen3.5-35B-A3B at 50% pruning it scores 42.3 on SWE-Bench Pro, matching the unpruned model's 41.8 while the first-order method REAP falls to 36.2.

Mixture-of-experts models must keep every expert in memory at inference even though each token uses only a few, so deleting experts by independent importance scores is a common fix. HOPE writes the pruning error as pairwise interaction terms between experts and selects a whole prune-set with a quadratic program, reaching the best average rank across three models, two calibration datasets and several benchmarks. On Qwen3.5-35B-A3B at 50% pruning it scores 42.3 on SWE-Bench Pro, matching the unpruned model's 41.8 while the first-order method REAP falls to 36.2.