Topic
AI MODELS
Large language models - benchmarks, capabilities, and how to choose the right one.
148 resources - 131 posts, 16 tools, 1 guide
Blog Posts
View in blog →
Amazon Swapped Sonnet 4.6 for a Decision Model: What It Does and Doesn't Replace
Amazon engineers replaced Sonnet 4.6 on a 20-label ticket classifier with Strands Decider, a small decision model, at about 44x lower list cost. Here is the narrow job it fits and the rollout pattern worth copying.
7 min read
Muse Ember: Meta's $0.10 Subagent Model vs Haiku 5.5 and Luna
Muse Ember lists at $0.10 in and $0.50 out per million tokens, the same sticker as Haiku 5.5 and GPT-6 Luna. Here is what actually separates them.
7 min read
Gemini 4 Carbon: Benchmarks, Pricing, and Access
Gemini 4 Carbon is Google's new frontier model: 59 on the AA Intelligence Index, $2/$10 intro pricing, but cyber-defender access only. What builders do now.
7 min read
Kimi K3.1 Pro: Pricing, Benchmarks, Open Weights Date
Kimi K3.1 Pro costs $2/$10 per million tokens, promises weights by Nov 4, and scores 65.7% on Terminal-Bench 4.0 (vendor-reported). The cost-per-task catch.
7 min read
Mistral Large 4 on Hugging Face: Weights, License, vLLM Setup
Mistral Large 4 weights are on Hugging Face under a modified MIT license. What the license blocks, the vLLM command, and when self-hosting beats the API.
8 min read
Anthropic IPO: What the S-1 Means for Developers
Anthropic filed its S-1 for a Nasdaq listing under ANT. The revenue and loss figures, the risk factors that touch API users, and what to change in your stack on Monday.
7 min read
Flint on Ollama: Best Local Coding LLM for Claude Code?
Recursive's Flint is a 40B open-weight coding model with 2.5B active parameters. How to run it on Ollama and point Claude Code at it, plus the benchmark caveats.
7 min read
AI Model Shutdown Dates 2026-2027: Calendar and Migration Plan
Every scheduled AI model API shutdown through mid 2027 by month: GPT-4o on Jan 14, whisper-1 on Feb 26, Claude Sonnet 4.5 on Nov 30, plus how to migrate.
17 min read
Structured Outputs Across AI APIs: OpenAI, Claude, Gemini (2026)
97 of 167 models we track enforce a JSON schema on output. Request shapes, schema limits and refusal handling for OpenAI, Claude, Gemini and Mistral.
13 min read
DeepSeek V4.1-Flash-1017: Benchmarks vs Opus 5, Pricing, Switch?
DeepSeek V4.1-Flash-1017 jumps 11 points on Terminal-Bench 4.0 at the same deepseek-flash price. Benchmarks vs Opus 5, K3, GLM-5.3 and when to switch.
9 min read
Codex 'gpt-5.5 Model Is Not Supported' Error: The Fix
Codex says gpt-5.5 is not supported with a ChatGPT account because OpenAI retired it from ChatGPT sign-in on October 14. The fix and what still works.
6 min read
LFM2.5-24B-A2B vs Qwen3.6-35B-A3B: Fast Local Agent or Better Coder?
LFM2.5-24B-A2B vs Qwen3.6-35B-A3B for local agents: Liquid wins tool-use benchmarks, Qwen wins SWE-Bench Verified. Which one to run for which job.
7 min read
Ollama Decision Models: Run Nimble Locally with --ask
Ollama 0.40.4 runs decision models locally: ollama run nimble --ask answers yes/no, label and score questions with probabilities. Commands and limits.
7 min read
DeepSeek 4.1 Flash as a Daily Coding Model: Cache, Peak Hours and Limits
DeepSeek 4.1 Flash as a daily coding model: what a session costs, how peak hours double the bill, why caching matters, and where the subsidy argument holds.
8 min read
Cheapest Subagent Model: Haiku 5.5 or GPT-6 Luna? Routing, Compaction and Cost per Task
Which cheap model belongs under your orchestrator? Haiku 5.5 vs GPT-6 Luna as a subagent or worker: routing by prompt length, compaction, tool-call gotchas and cost per agent task.
15 min read
OpenAI Decisions API vs Jev vs Clef: Price, Speed, Which to Pick
OpenAI Decisions API costs $0.10 per million input tokens, 2.4x Jev. Pick Jev for cheap text decisions, Clef-flash for speed, Decisions API for images.
9 min read
Step 5 Preview: Pricing, Benchmarks and the October 15 Open Weights
Step 5 Preview is StepFun's 600B MoE with 27B active and a 1M window. What it scores, what a session costs, and what to check before the October 15 weights.
8 min read
Opus 5.5 vs Sonnet 5.5 vs Haiku 5.5: Which Claude Model to Use
Sonnet 5.5 is the default, Opus 5.5 is for open-ended long-horizon work, and Haiku 5.5 is for bounded steps and subagents. Prices, benchmarks, cost math.
8 min read
Claude Haiku 5.5: Pricing, Migration Changes, and When to Use It
Claude Haiku 5.5 pricing, the cliff above 100K-token prompts, the tokenizer catch, the migration steps from Haiku 4.5, and when to use it instead of Sonnet.
9 min read
Mistral Large 4: Specs, Pricing, Benchmarks and Weights Date
Mistral Large 4 is a 1T-parameter multimodal MoE with 52B active, in public preview at $0.68/$2.09 per million tokens, with open weights due end of October.
14 min read
Kolibri Release Guide: Aleph Alpha's 78B Open Model
Kolibri is an Apache 2.0 English-German MoE with 78B total and 3B active parameters and a 1M context. Benchmarks, the vLLM command, and who should run it.
5 min read
Cloudflare Clef Decision Models: Jev-Compatible, Benchmarked and Priced
Cloudflare Clef and Clef-flash are Jev-compatible decision models on Workers AI. Pricing, latency and benchmarks against Jev, plus the RL fine-tuning service.
5 min read
Gemini 4 Argon: What Developers Can Actually Use
Gemini 4 Argon for developers: what Google shipped, what is verified, why access starts narrow, and what to watch before planning a migration around it.
8 min read
Jeff: Jev-Style Decision Models Trained at Home on One GPU
Jeff fine-tunes Qwen3.5 and Gemma 4 into small Jev-compatible decision models on one GPU. The numbers, run commands, and where the benchmark misses real work.
6 min read
GPT-6.1 Sol Release Guide: Near-Astra Agentic Work at $2/$10 and $0.10 Cache Reads
GPT-6.1 Sol release guide: near-Astra scores at a fifth of Astra's price, $0.10 cache reads, verified pricing, the Astra 6.1 safety hold, and how to run it.
7 min read
Claude Sonnet 5.5 Developer Guide: Pricing and API Changes
Claude Sonnet 5.5 costs $2/$10 per million tokens, and cache reads fell to $0.10 on October 7 - half of Opus 5.5 on every line. Pricing math and API changes.
11 min read
GPT-6 Astra Release Guide: Benchmarks, $10/$50 Pricing, and How to Run It in Codex and OpenCode
GPT-6 Astra release guide: OpenAI's max-capability model, its $10/$50 pricing and 1.05M context, what the benchmarks do and do not say, and commands to try it.
8 min read
GPT-6 in 7 Minutes: Astra, Sol, and Luna Explained for Developers
GPT-6 in 7 minutes: what Astra, Sol and Luna are, what each tier costs per million tokens, the new API features, and how to try each one in Codex and the API.
7 min read
How to Use Jev: Every Way to Call It, the Opus 5.5 Pairing, and Laya vs Kev vs Ollaya
How to use Jev from TypeSafe: every verified way to call it, the Jev + Claude Opus 5.5 coding-agent pattern, and how Laya, Kev, and Ollaya compare.
10 min read
How to Use Claude Code and Codex With Meta Muse: Every Setup That Actually Works
Claude Code and Codex with Meta Muse: run both agents on Muse Spark 1.3 via the Meta Model API, use OpenCode Go, or import your setup into Muse Code.
10 min read
GPT-6 Sol vs Claude Opus 5.5 vs Grok 4.7: The September 2026 Price War
GPT-6 Sol vs Claude Opus 5.5 vs Grok 4.7 pricing: verified per-token rates, cost-per-task math and a decision guide for the September 2026 price war.
9 min read
Claude Opus 5.5 Developer Guide: Pricing, API, Claude Code
Claude Opus 5.5 costs $4/$20 per million tokens with $0.20 cache reads. SDK examples, Claude Code setup, and when to pick it over Sonnet 5.5 or Haiku 5.5.
11 min read
Gemini 3.8 Live and 3.8 Live Extended Thinking: Google's Audio-to-Audio Voice Models, Benchmarked and Priced
Gemini 3.8 Live and 3.8 Live Extended Thinking are Google's audio-to-audio voice models with background tool calls. Benchmarks, pricing and how to build.
8 min read
TypeSafe Jev Pricing, Rate Limits and Benchmarks (2026)
TypeSafe Jev costs $0.042 per million input tokens, output free, at 80 requests/second. Limits, benchmarks, failure modes and every way to call it, re-verified October 9.
7 min read
Gemini's Agentic Video Understanding Cuts Video Tokens by 88%: How It Works and What Breaks
Gemini agentic video understanding lets Flash models pick the frames, audio and transcripts to inspect, cutting tokens up to 88%. How it works and its limits.
7 min read
Tencent Hy4 Preview: 770B Open MoE, Agentic Benchmarks, and Where It Fits in 2026
Tencent Hy4 preview is a 770B open MoE with 49B active under Apache 2.0. Architecture, posted agentic benchmarks, OpenRouter pricing and self-hosting needs.
9 min read
Gemini Omni 1.1 Flash Goes GA: Scene Extension, Keyframe Control, and 4K in the Gemini API
Gemini Omni 1.1 Flash is GA in the Gemini API with 10-second scene extension, first and last frame interpolation, 360p drafts and 4K upscaling, plus pricing.
8 min read
DeepSeek V4 Flash Vision Exp: Experimental Vision, Limits, and How to Run It in OpenCode
DeepSeek V4 Flash Vision Exp guide: supported image formats, three input methods, the 384-token per-image cap, and how to run it in OpenCode today.
7 min read
Ox Alpha on OpenCode: The Free Stealth Model, Specs, Privacy Split, and How to Run It
Ox Alpha is a free stealth model on OpenCode with 1M context. What is confirmed, where OpenCode and OpenRouter differ on retention, and how to run it.
9 min read
Qwen3.8-27B vs Opus 4.6 Max: Local Agentic Coding Benchmarks
Qwen3.8-27B is a 27B dense Apache-2.0 model that beats Opus 4.6 Max on SWE-bench Pro (61.7 vs 53.4). Benchmarks, hardware, cost and when to run it.
10 min read
Grok 4.6: xAI's Agent-Focused Update Matches GPT-5.6 Sol at the Same $2/$6 Price
Grok 4.6 release guide: xAI's agent-focused update matches GPT-5.6 Sol on the AA index at the same $2/$6 pricing, and runs in Cursor and OpenCode.
8 min read
LFM2.5-VL-3B: Liquid AI's 3B Vision Model Reads Screens, Grounds Objects, and Calls Tools on a Laptop
LFM2.5-VL-3B is a 3B open-weights vision model from Liquid AI that reads screens, grounds objects and calls tools on a laptop. What shipped and how to run it.
7 min read
Cactus Needle 2: The 14MB Agentic LLM That Runs on a Raspberry Pi 5
Cactus open-sourced Needle 2, a 45M-parameter agentic LLM in a single 14MB binary that runs a full tool-calling session in 28MB of RAM. 500 tok/s on a Raspberry Pi 5, ESP32-S3 class parts, Apache 2.0. Here is what the benchmarks actually show.
7 min read
Encrypted Chain-of-Thought Is Not Private: New Paper Decodes Reasoning Traces From Anthropic, OpenAI, and Google APIs
Encrypted chain-of-thought from Anthropic, OpenAI and Google APIs can be replayed into weaker models and read verbatim. How the attack works and what leaked.
7 min read
Muse Glimmer 30B: Meta's Open-Weight Local Agent Model, Benchmarks, and Hardware Reality
Muse Glimmer 30B is Meta's Apache 2.0 open-weight multimodal agent model that runs in 24GB. Benchmarks, hardware reality and what the numbers actually say.
8 min read
Grok Imagine Image 2.0 Ships: xAI's Typography-Aware Image Model Is Already on Vercel's AI Gateway
Grok Imagine Image 2.0 is xAI's typography-aware image model, ranked second on text-to-image and editing leaderboards and callable via Vercel's AI Gateway.
6 min read
DeepMind Open-Sources WeatherNext Cyclones After a Nature-Verified Breakthrough
WeatherNext Cyclones, DeepMind's open-source tropical cyclone model, adds a day of forecast lead time. What the Nature paper shows and how to run the weights.
8 min read
Kimi K3 Is GA in GitHub Copilot: Pricing, Rollout, and What It Means for Model Choice
Kimi K3 is GA in GitHub Copilot at $3/$15 per million tokens, off by default for Business and Enterprise. Rollout details and what it means for model choice.
7 min read
Meta Ships Muse Code and Muse Spark 1.2: A Terminal Agent With a 12x Cheaper Contributor Tier
Meta Muse Code is a terminal coding agent co-trained with Muse Spark 1.2. How the harness works and what the $0.10/$0.20 contributor tier asks in return.
7 min read
OpenAI Retunes GPT-5.6 Sol in ChatGPT and Makes Luna the Free Tier Default
OpenAI retuned GPT-5.6 Sol for ChatGPT and made GPT-5.6 Luna the Free and Go default. What changed in chat, what stayed the same in the API, and why.
7 min read
LFM2.5-2.6B: Liquid AI's On-Device Agent Model Runs at 220 Tokens/s in Under 2.5 GB
LFM2.5-2.6B is an open-weight on-device agent model from Liquid AI that runs in under 2.5 GB. How it was trained, what the benchmarks say and how to run it.
7 min read
Qwen 3.8 Max Ships: 2.4T MoE, 1M Context, $2/$6 per MTok, Open Weights Next Week
Qwen 3.8 Max is a 2.4T-parameter MoE with 95B active, a 1M context window and $2/$6 per million tokens on QwenCloud, with open weights promised next week.
8 min read
Gemini 2.5 Pro and Gemini 3 Flash Deprecated in GitHub Copilot: What to Switch To
Gemini 2.5 Pro and Gemini 3 Flash are deprecated in GitHub Copilot. What GitHub suggests instead, the October follow-up deprecations, and how to migrate.
5 min read
Your AI Session Is No Longer Yours: How Providers Seal Reasoning, Search, and Subagent State
AI session portability: sealed reasoning, opaque compaction and hidden subagent messages are replacing portable transcripts. Five tests and seven rules for it.
7 min read
Budget AI Coding Models, October 2026: Haiku 5.5 vs GPT-6 Luna
Claude Haiku 5.5 and GPT-6 Luna both list at $0.10/$0.50 per MTok. The price tie breaks at Haiku's 100K cliff, and Anthropic's benchmarks favor Haiku. Checked Oct 8, 2026.
11 min read
Claude Mythos Preview Explained: Anthropic's Gated Frontier Model and Project Glasswing
Claude Mythos Preview explained: Anthropic's gated frontier model, who got access through Project Glasswing, what it found, and where the model line went next.
7 min read
DeepSeek V4 Flash 0731: The Budget Tier Just Overtook Pro Preview on Agent Benchmarks
DeepSeek V4 Flash 0731 was re-post-trained for agent work. Its benchmark numbers, native Responses API and Codex support, and how to wire it up today.
9 min read
DeepSeek V4 Flash 0731: The Official Release, Benchmarks, and How to Run It in OpenCode
DeepSeek V4 Flash 0731 is the official V4 Flash API release, re-post-trained to beat V4-Pro-Preview on agent benchmarks. How to run it in OpenCode today.
7 min read
Inkling-Small: Thinking Machines Ships a 12B-Active Open Model That Beats Its Big Sibling on Agent Work
Inkling-Small is a 12B-active, Apache 2.0 open-weights MoE that beats the 975B Inkling on agentic coding and tool use at a quarter of the size.
8 min read
MiniMax H3: Omni-Modal Video, Native Audio, Open Weights
MiniMax H3 turns text, image, video and audio into video with native stereo sound. API from 0.80 CNY per second at 2K, and open weights are on Hugging Face.
8 min read
Gemini Robotics 2: Google DeepMind Brings Whole-Body Intelligence to Humanoid Robots
Gemini Robotics 2 from Google DeepMind brings whole-body humanoid control, dexterous hands and multi-robot teamwork. The models, the numbers and the HN debate.
9 min read
OpenAI Cuts GPT-5.6 Luna by 80%: The Price-Performance Frontier Just Shifted
OpenAI slashes GPT-5.6 Luna by 80% to $0.20/M input tokens, cuts Terra by 20%, adds Sol Fast mode at 2.5x speed, and reveals Sol autonomously optimized its own production kernels.
7 min read
Grok 4.5 in 10 Minutes: xAI's Fastest Model, 500K Context, and Build-Mode Integration
Grok 4.5 in 10 minutes: xAI's flagship model with a 500K context window, function calling, structured outputs and build-mode agents, plus verified pricing.
7 min read
Fable 5 Effort Levels vs Switching Models: When to Dial and When to Change
Fable 5 effort levels vs switching models: effort spends more of one model's ceiling, a model switch buys a new one. When to move each dial.
8 min read
Kimi K3 Weights Land on HuggingFace: 2.8T Open Frontier Model You Can Actually Download
Kimi K3 open weights are on HuggingFace: 2.8T parameters, 1M context, native MXFP4 and a ~1.63TB download. The specs, license terms and HN reaction.
7 min read
Claude Opus 5: Near-Fable Intelligence at Half the Cost
Claude Opus 5 benchmarks, pricing and HN reaction: near Fable 5 performance at the Opus 4.8 price, and what it means for choosing a daily-driver model.
12 min read
Claude Opus 5 in 8 Minutes: What Developers Need to Know
Claude Opus 5 for developers: what changed from Opus 4.8, the breaking API changes to migrate, and when Opus 5 is the right default over Fable 5.
7 min read
Echo Claims Fable-Level Results at One-Third the Cost Using Open-Weight Models
A new multi-model orchestration system routes requests across open-weight models to match frontier performance at reduced inference cost. Here is what we know.
7 min read
FLUX 3: Black Forest Labs Ships a Unified Multimodal Foundation Model for Image, Video, Audio, and Robotics
FLUX 3 from Black Forest Labs is one multimodal model for image, video, audio, and robot actions. What it does, how it works, and how to try it.
10 min read
Kimi K3 in 10 Minutes: Moonshot AI's 2.8T Open Model, API Setup, Pricing, and Benchmarks
Kimi K3 from Moonshot AI is a 2.8T open model with a 1M-token context and an OpenAI-compatible API. How to call it, what it costs, and how it benchmarks.
6 min read
Where to Access Kimi K3: Every Provider and Price Compared (2026)
Where to access Kimi K3: Moonshot's API at $3 input and $15 output per million tokens, OpenRouter hosts, inference clouds, and open weights.
13 min read
Kimi K3 Developer Guide: What the 2.8T Open Model Changes
Kimi K3 developer guide: the 2.8T-parameter model's 1M-token context, native vision, API pricing and open-weights timing, and how it fits coding agents.
7 min read
Kimi K3 vs K2.7 Code: Is the Upgrade Worth It for Coding?
Kimi K3 vs K2.7 Code: 1M vs 256K context, $3/$15 vs $0.95/$4 per million tokens, and when the bigger model earns its price on coding work.
6 min read
Kimi K3 Drops: Moonshot's 2.8T Parameter Frontier Model Takes on GPT-5.6 and Fable 5
Kimi K3 is Moonshot's 2.8T-parameter model with a 1M-token context and Delta Attention. Pricing, HN reactions and where it fits among frontier models.
6 min read
Inkling: Thinking Machines Lab Drops a 975B Open-Weights Model
A new American open-weights frontier model with multimodal capabilities, 1M token context, and competitive benchmarks. Here's what the HN community thinks.
7 min read
Bonsai 27B: How PrismML Fit a 27B Model on Your Phone
PrismML's Bonsai 27B uses 1-bit quantization to compress a 27B model to 3.9GB - small enough to run on an iPhone. Here's how it works and what HN thinks.
6 min read
Claude Fable 5 in 7 Minutes: Benchmarks, Pricing, Availability, and Real-World Examples
Claude Fable 5 in 7 minutes: a companion guide to the video review covering benchmarks, pricing, availability, demos and hands-on developer takeaways.
7 min read
GPT-5.6 vs Claude 5: What the New Tiers Mean for Choosing a Coding Model
GPT-5.6 vs Claude 5 for coding: how OpenAI's Sol, Terra, and Luna tiers compare with Claude Fable 5 and Mythos 5 on pricing, benchmarks, and model choice.
9 min read
Grok 4.5 for Developers: What Changed and When to Pick It
Grok 4.5 for developers - $2/$6 per million tokens, a 500k context window, vendor benchmarks with caveats, and when to pick it over Claude, GPT, or Gemini.
7 min read
Tencent Hy3: A 295B Open MoE That Punches Above Its Weight
Tencent's Hy3 ships 295B parameters but activates only 21B per token, matching flagship performance at flash-tier pricing under Apache 2.0.
6 min read
Grok 4.5: xAI Releases Cursor-Trained Coding Model at $2/M Input Tokens
Grok 4.5 coding model from xAI, trained on Cursor data: $2/M input pricing, benchmarks near Opus 4.7, the CursorBench caveat, and the Hacker News reaction.
5 min read
Meta Muse Image: What Developers Can Actually Use Today
Meta Muse Image is live in Meta AI but has no public model API. What the launch confirms, what is still preview-only, and how developers should evaluate it.
8 min read
Meta Muse Spark 1.1 Developer Guide: First Paid Meta API for Agentic Tasks
Meta Muse Spark 1.1 developer guide: Meta's first paid model API, with 1M-token context, OpenAI-compatible endpoints, pricing and setup for agentic tasks.
7 min read
Meta Launches Muse Spark 1.1: A Closed-Weights Agentic Model with Aggressive Pricing
Meta Muse Spark 1.1 is Meta's first paid, closed-weights API model, with $1.25/M input tokens and 1M context. The pricing, benchmarks and HN debate.
5 min read
GLM 5.2 and the AI Margin Collapse Thesis
GLM 5.2 and the AI margin collapse thesis: why open-weights models could squeeze frontier lab margins, where HN pushes back, and what it means for model choice.
7 min read
Claude Sonnet 5 Developer Guide: Migration, API, and Effort Levels
Claude Sonnet 5 migration guide: the three breaking API changes from Sonnet 4.6, the new effort parameter, tokenizer impact and when to use each effort level.
8 min read
Claude Sonnet 5 vs Sonnet 4.6: Should You Upgrade?
Claude Sonnet 5 vs Sonnet 4.6: near-Opus 4.8 results on coding and agents, but a new tokenizer uses about 30% more tokens. The upgrade decision, with numbers.
6 min read
Running Fable 5 Agent Fleets in Production: The Operations Guide
Fable 5 agent fleet operations: 30-day retention limits, refusal-rate alerting, per-role effort tuning, observability and availability planning for production.
8 min read
Fable 5 Is Back: The Anthropic Model the Government Switched Off
Fable 5 is back after a US export-control suspension. What the Anthropic model is, the specs and refusal behavior to handle, and when to pick Opus 4.8.
6 min read
Fable 5 vs Opus 4.8: Which Should Orchestrate Your Agents?
Fable 5 vs Opus 4.8 as your agent fleet orchestrator: a fair head-to-head with a decision matrix by run length, budget, compliance and refusal tolerance.
8 min read
GLM 5.2 in 9 Minutes: The Open-Weight Rival to GPT-5.5
GLM 5.2 in 9 minutes: a companion guide to the video on the open-weight GPT-5.5 rival, covering benchmarks, pricing and a live OpenCode demo.
6 min read
GPT-5.5 in 7 Minutes: Benchmarks, Codex Agents, Context Window, and Pricing
GPT-5.5 in 7 minutes: a companion guide to the video review of the new OpenAI model in ChatGPT and Codex - benchmarks, Codex agents, context window and pricing.
6 min read
Claude Sonnet 5 Launch Analysis: The Most Agentic Sonnet Yet
Anthropic releases Claude Sonnet 5 with improved agentic capabilities, better tool use, and an introductory pricing deal. Here's what developers need to know.
6 min read
Apertus: Europe's Answer to AI Sovereignty - and Why HN Is Skeptical
Switzerland's fully open foundation model promises transparent training data and EU compliance. The HN crowd has questions about actual performance.
6 min read
Fugu Ultra's Frontier Performance Claim, Explained Without the Hype
Sakana Fugu Ultra claims frontier performance by orchestrating models instead of one giant model. What the benchmarks show, what is novel, what needs proof.
11 min read
Sakana Fugu and the Case for Not Betting Everything on One Proprietary Model
Sakana Fugu makes a timely argument for model routing: frontier performance should come from swappable systems, not a hard dependency on one proprietary API.
9 min read
Sakana Fugu Ultra: The Model Router Making the Frontier Look Less Proprietary
Sakana Fugu Ultra is a learned orchestration layer routing work across expert models behind one API - a serious case for multi-model AI over one giant model.
10 min read
Codex Custom Model Providers: GLM-5.3, Mistral and Ollama
Codex only speaks the Responses API now. Tested config.toml blocks for GLM-5.3, Mistral Large 4 through a gateway, local Ollama and an internal proxy.
14 min read
The Router Era: Why Not Owning a Frontier Model Became an Advantage
Model routers turn having no single winning model into an advantage: how routing works, why open weights and neoclouds make it cheap, and the counter-argument.
11 min read
GLM-5.2 Cost Math: When Open-Weights Coding Models Actually Save You Money
GLM-5.2 cost math: when Z.ai's open-weights coding model actually saves money, with per-token pricing, a worked cost-per-task example and a decision guide.
9 min read
Model Routing Recipes: Practical Config Patterns to Cut AI Spend
Model routing recipes with paste-ready OpenRouter and LiteLLM configs for task tiers, fallback chains, cost ceilings and cache-aware routing that cut AI spend.
11 min read
OpenRouter Fusion Makes Model Panels Real. Use Them Like Escalation, Not Autopilot
OpenRouter Fusion turns multi-model panels into an API feature. Use it as an escalation lane for prompts where a wrong answer is expensive, not as the default.
8 min read
The Claude Tokenizer Change: What ~30% More Tokens Means for Your Bill
Anthropic's docs say the tokenizer introduced with Opus 4.7 can use up to 35% more tokens for the same text. Here is what that does to per-request cost, max_tokens, and cross-model comparisons.
8 min read
Fable 5 with 1M Context: What Actually Works in Practice
Fable 5 1M context workflows that actually work: whole-repo reviews, log archaeology, multi-doc synthesis - plus the honest math on when RAG still wins.
10 min read
Claude Effort Levels Explained: Fable 5, Opus 5.5, Haiku 5.5
Claude effort levels explained: what low, medium, high, xhigh and max change on Fable 5, Opus 5.5 and Haiku 5.5, each default, and what a level costs.
14 min read
Handling Long-Running Fable 5 Requests: Timeouts, Streaming, and Background Patterns
Fable 5 long-running requests can run for minutes per turn and hours per run. Configure client timeouts, streaming keepalive, batch polling and background jobs.
8 min read
Fable 5 Orchestrator Playbook: Smart Model, Cheap Workers
A practical playbook for running Claude Fable 5 as the orchestrator over Sonnet and Haiku workers, with verified cost math on when the premium pays off.
10 min read
The Frontier Model Landscape, July 2026 Edition
Frontier AI model directory for July 2026 covering Claude Fable 5, Opus 5, GPT-5.6, Sonnet 5, Gemini 3.1 Pro, Kimi K3 and DeepSeek V4, with verified pricing.
12 min read
How to Use Claude Fable 5: Every Access Path Explained
How to use Claude Fable 5 via claude.ai plans, the Claude API, Amazon Bedrock, Vertex AI and Microsoft Foundry, with model IDs, setup effort and prompt tips.
8 min read
Is Claude Fable 5 Slow? Latency in Practice, and When It Matters
Claude Fable 5 latency measured: 109 seconds to first token at max effort vs 1.4s for Sonnet 4.6. When slow is fine, when it hurts, and how to route around it.
8 min read
Migrating Off Retired GPT Models in 2026: A Working Checklist
Migrating off retired GPT models in 2026: the live retirement table, what maps to what, an eval-before-switch day plan, and when to jump providers.
10 min read
Qwen 3.7 Max Developer Guide: 1M Context, $1.25/MTok, and Agent-First Architecture
Qwen 3.7 Max developer guide: the 1M token context window, pricing, Anthropic and OpenAI-compatible API, benchmarks, and when to pick it over Claude or GPT.
8 min read
12 Ways Developers Are Actually Leveraging Claude Fable 5
Twelve documented Claude Fable 5 use patterns - agent orchestration, overnight runs, 1M-context refactors, effort tuning - each with a how-to seed and doc link.
10 min read
Anthropic Model Names Explained: Fable, Mythos, Opus, Sonnet
Anthropic's model names: Haiku, Sonnet, Opus, then Fable and Mythos. What each tier means, the current model IDs and prices, and which one to pick.
6 min read
Apple's LanguageModel Protocol: Xcode 27 Just Made Model Lock-In Optional
Apple's LanguageModel protocol lets iOS and macOS apps swap Claude, Gemini, or local models with one dependency change. What it means for model lock-in.
8 min read
Fable 5 vs Opus 4.8: A Data-Driven Decision Guide for Engineering Teams
Fable 5 posts an 80.3% SWE-Bench Pro score and costs 2x Opus 4.8 - here is the task-profile scoring guide that tells you when the premium pays off.
7 min read
Claude Mythos 5 Explained: What It Is, Who Can Access It, and Why It's Gated
Claude Mythos 5 explained - how it differs from Fable 5, who gets unrestricted access through Project Glasswing, and what developers should do right now.
7 min read
The Model, IDE, CLI, and Agent Framework Changes That Actually Matter
Which AI coding changes matter: a layer-by-layer filter for model, IDE, CLI, background agent, framework, UI, context, security, and pricing updates.
10 min read
Models.dev Makes Model Routing Feel Like Infrastructure
The models.dev project is trending because AI teams need one boring source of truth for model specs, pricing, context windows, modalities, and tool support.
7 min read
DeepSeek V4 Changes the Coding Agent Cost Equation
DeepSeek V4 brings near-frontier coding at a much lower token price. Where cheap reasoning fits in a coding agent stack, from code review to repo mapping.
8 min read
DeepSeek V4: The Developer's Guide to Flash and Pro
DeepSeek V4 developer guide: Flash vs Pro, pricing, OpenAI SDK setup with thinking mode and tool calling, and when to pick V4 over Claude or GPT.
10 min read
NVIDIA Nemotron 3 Super: A Developer's Guide to the 120B Hybrid MoE
Nemotron 3 Super developer guide: the latent MoE hybrid Mamba architecture, hardware needs, reasoning modes, and code to run NVIDIA's 120B model.
9 min read
Claude Haiku 4.5: Near-Frontier Intelligence at a Fraction of the Cost
Anthropic's Claude Haiku 4.5 delivers Sonnet 4-level coding performance at one-third the cost and twice the speed. Here is what developers need to know.
5 min read
DeepSeek R1 and V3: The Developer's Guide to Open-Source AI
DeepSeek R1 and V3 developer guide: use the MIT-licensed models through the API, run them locally with Ollama and decide when they beat closed-source models.
9 min read
Llama 4: The Complete Developer's Guide to Meta's Open Source Models
Llama 4 developer guide to Scout and Maverick, the open mixture-of-experts models from Meta: run them locally, call them via APIs and know when to pick them.
10 min read
Claude vs GPT for Coding: Which Model Writes Better TypeScript?
Claude vs GPT for real TypeScript work: benchmarks, pricing, model families, and the practical differences that matter when picking a coding model.
9 min read
OpenAI vs Anthropic in 2026 - Models, Tools, and Developer Experience
A developer's comparison of OpenAI and Anthropic ecosystems - models, coding tools, APIs, pricing, and which to choose for different use cases.
18 min read
NVIDIA's Nemotron 3 Super in 6 Minutes
NVIDIA Nemotron 3 Super combines latent mixture of experts with hybrid Mamba layers - 120B total parameters, 12B active per token, 1M context and open weights.
5 min read
Grok 4: xAI's Most Powerful AI Model
xAI has launched Grok 4, claiming the title of the world's most powerful AI model. With a $300/month Super Grok tier, saturated AMI benchmarks, and a coding model on the horizon, this is xAI's bigge...
7 min read
Qwen 3: Alibaba's Open-Source Model That Outclassed Llama 4
Qwen 3 is Alibaba's family of eight Apache 2 licensed models, led by a 235B MoE flagship. How it compares to Llama 4, how hybrid thinking works, how to run it.
8 min read
xAI Grok 3 Launch: The Smartest AI on Earth?
xAI's Grok 3 launch explained: the 200,000-GPU cluster, benchmarks against GPT-4o and Sonnet 3.5, the reasoning modes, and what it all means for developers.
9 min read
Related Tools
All tools →Claude
Daily DriverAnthropic's model family. As of October 2026: Opus 5.5 as the default, Fable 5.1 for the hardest long-horizon work, Sonnet 5.5 for speed, Haiku 5.5 for cost. 1M context. Max from $100/mo.
AI ModelsChatGPT
OpenAI's chat app. As of October 2026 Free and Go run GPT-6 Luna; Plus ($20/mo) adds GPT-6.1 Sol and GPT-6 Astra. Agent mode, Codex, image generation, code interpreter.
AI ModelsOpenRouter
Unified API for hundreds of models. One API key, one billing dashboard. OpenAI, Anthropic, Google, Meta, Mistral, and more. Automatic fallbacks and load balancing.
AI ModelsDeepSeek
Chinese lab shipping open-weight MoE models. The V4 family (previewed April 24, 2026) runs a 1M context on DeepSeek's API; R1 (2025) popularized open reasoning models. Low-cost API.
AI ModelsLlama
Meta's open-weight model family. Llama 4, released April 5, 2025, comes in Scout (109B total, 17B active) and Maverick (400B total, 17B active). Commercial use under the Llama license.
AI ModelsMistral
European open-weight models. Mistral Large for complex tasks, Mistral Small for speed, Codestral for code. Strong multilingual support. Open and API options.
AI ModelsGPT-5
OpenAI's GPT-5 model, released August 2025. Unified fast and reasoning modes in one model. Superseded by the GPT-6 family in September 2026 and now marked deprecated in the API.
AI ModelsGemini
Google's model family. As of October 2026 Gemini 4 Argon (GA October 13, 1M token context) is the flagship for coding and agents, with Gemini 3.8 Flash (free tier in AI Studio) as the fast, cheaper option.
AI ModelsGrok
xAI's model family, now documented under the SpaceXSI (SpaceX Super Intelligence) name. Grok 4.7 (September 21, 2026) has a 500K context at $2/$6 per million tokens. OpenAI-compatible API.
AI ModelsClaude Haiku 4.5
Anthropic's smallest Claude 4.5 model, released October 2025 and succeeded by Haiku 5.5 in October 2026. Sonnet 4-level coding at one-third the cost. $1/$5 per million tokens.
AI ModelsQwen3-Coder
Alibaba's open-weight coding model, released in 2025. 480B total parameters, 35B active (MoE). Native 256K context, extends to 1M. Apache 2.0 license. Built for agentic coding.
AI ModelsDeepSeek V3.2
DeepSeek's reasoning-first model built for agents. First model to integrate thinking directly into tool use. Ships alongside V3.2-Speciale, which rivals GPT-5 and Gemini 3.0 Pro.
AI ModelsClaude Opus 4.7
Anthropic's Opus model released April 2026, since succeeded by Opus 4.8 and Opus 5.5. Strong at coding, long-context analysis, and agentic work. 1M context, $5/$25 per million tokens.
AI ModelsClaude Fable 5
Anthropic's first generally available Mythos-class model, released June 9, 2026. 1M context, 128K max output, $10/$50 per million tokens. Built for long-horizon agentic work.
AI ModelsClaude Opus 4.8
Anthropic's Opus model released May 28, 2026, and its recommended default until Opus 5.5 shipped in September 2026. 1M context, 128K output, $5/$25 per million tokens.
AI ModelsDeepSeek V4
Open weightsDeepSeek's open-weights frontier family, previewed April 24, 2026. V4-Pro is 1.6T total / 49B active params; V4-Flash is 284B / 13B. 1M context standard. Weights on Hugging Face.
AI ModelsKeep exploring
More on AI Models
- - Claude - recommended AI Models tool from the Developers Digest directory
- - Compare Tools - dive deeper across the Developers Digest knowledge base
- - All AI Models articles in the blog archive
- - Developers Digest on YouTube - video tutorials covering AI Models and more
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever
Explore 848 topics
Browse All Topics