OpenRouter is a unified API gateway providing access to 500+ AI models from 60+ providers through a single OpenAI-compatible endpoint. Developers can seamlessly switch between GPT, Claude, Gemini, Llama, and more without managing multiple API keys. Features include provider fallback, cost optimization, free tier access, and a built-in chat interface for model experimentation with transparent pay-as-you-go pricing.

Microsoft's Microsoft-Decision-1 is a specialized decision-scoring model for engineering teams building routing, classification, and verification logic into their AI systems. Announced on October 9, 2026, it returns calibrated scores for a fixed set of choices rather than generating free-form text, which makes it predictable to drop into production pipelines. It targets teams that already run m...

Saluki 27B is a 2-bit compressed build by Underdog of Alibaba's Qwen3.8-27B that gives local agents a tool-calling model in a 7.89 GB file, beating the full 54 GB original at function calling. Released on October 7, 2026 by Conway Research's Underdog project, an a16z-backed on-device assistant effort, it is licensed under Apache 2.0 and runs on stock llama.cpp — making it a practical agent brai...

Liquid AI Open d1 is a family of open-weight decision models for developers and edge engineers who need fast, structured answers on device instead of token-by-token generation. Released on October 7, 2026, the d1 models do not produce text at all; they score a fixed set of answer options in a single forward pass, which makes them a fit for real-time routing, moderation, and agent control loops....

Claude Haiku 5.5 is Anthropic's smallest and fastest model in the Claude 5.5 family, built for teams that need high-volume, cheapest, low-latency inference. Released on October 7, 2026, it targets the repetitive but important jobs: document summarization, classification, routing, and the helper sub-agents that feed larger models such as Sonnet 5.5 and Opus 5.5. Core Features Prompt-length tiere...

Aleph Alpha Kolibri is a sovereign open-weight MoE model from Aleph Alpha, a German company that released it in Germany on October 3, 2026 under the Apache 2.0 license. It is built for public-sector and regulated-industry teams that must run capable language models on their own infrastructure under EU data rules. Core Features Mixture-of-experts architecture with 78.1B total parameters but only...

Cloudflare Clef is Cloudflare's first in-house open-weight decision model family, built for AI agents that need to make fast, structured choices — route a ticket, block a request, or escalate — without generating free-form text. It launched on Workers AI on October 1, 2026. Core Features Two sizes: Clef at 27B parameters (built on Qwen3.8-27B) and Clef-flash at 9B (built on Qwen3.5-9B), both Ap...

Mistral Large 4 (ML4, codename leChonk) is Mistral AI's native multimodal frontier model for enterprises that need a Europe-hosted, high-capability model for reasoning, coding, and document-heavy knowledge work. It entered public preview on Mistral Studio on October 6, 2026. Core Features 1 trillion total parameters with 49 billion active per token, trained from scratch on 3,800 Nvidia Grace Bl...

Grok 4.7 is xAI's frontier model launched on September 21, 2026 for coding, agentic tasks, and knowledge work, giving developers a 500K-token context window plus image input and configurable reasoning. It is the new flagship behind Grok Bot and is served through the xAI API, Cursor, Grok Build, and AWS Bedrock. Core Features 500K context window with text and image inputs and text-only output, a...

Cognition SWE-2 is a coding model for engineering teams that want frontier-level software-engineering performance without paying frontier token prices. Released on September 10, 2026 inside Devin Desktop and CLI, SWE-2 is post-trained from Moonshot AI's Kimi K3 and routed through the Devin product rather than sold as a standalone API. Core Features Reinforcement-learning post-training from Kimi...

Google Gemma 4 26B A4B is an open-weight Mixture-of-Experts language model from Google's Gemma family, built for developers who want near-frontier quality at a price they can run locally. The 26B is total parameters on disk; A4B is the roughly 3.88 billion parameters activated per token, so it behaves like a 4B dense model at inference. Community MLX work pushed straight-in-memory inference abo...

DeepSeek V4.1 Flash is DeepSeek's lightweight multimodal flagship of the new Causal Encoder-Decoder family, built for developers and businesses that need frontier reasoning at low latency and long context. Released through the DeepSeek API and Alibaba Cloud ModelStudio on September 13, 2026, it ships native multimodal vision so it can read charts, documents, and screenshots without a separate m...

MiniCPM5-2B is OpenBMB's on-device, 2.5-billion-parameter open-source language model, built for developers who need real agent and coding ability on phones, laptops, and edge devices. Released September 7-8, 2026, it is the second drop in the MiniCPM5 family after the 1B version and ships under an Apache-2.0 license. Core Features A 131,072-token context window (128K) that fits long documents, ...

Claude Mythos 5.1 is Anthropic's restricted frontier model built for vetted cybersecurity defenders and life-science researchers who need fewer safeguards on approved professional work. Launched on September 1, 2026, it shares the same underlying engine as Claude Fable 5.1 but applies more permissive controls for authorized defensive and research tasks. Core Features One-million-token context w...

IBM Granite 4.2-8B is an open-weight reasoning model from IBM that adds step-by-step chain-of-thought thinking, tool calling, and 128K context for enterprises and developers who want to run agents on their own hardware under a permissive license. Released on August 25, 2026, it is the mid-size member of IBM's three-model Granite 4.2 family, sitting between a 3B edge model and a 30B flagship. Co...

Claude Fable 5.1 is Anthropic's long-horizon highest-capability public model for long-running agents, hard coding work, and document-heavy research, released on September 1, 2026, and is built for engineering and knowledge teams that push the same large context through many turns. It accepts text and images, returns text, and keeps a 1,000,000-token window with up to 128,000 output tokens. Core...

GLM-5.3-Flash is a 320-billion-parameter model from Z AI that scores 57 on the Artificial Analysis Intelligence Index while costing about 7.5x less than the larger GLM-5.3. It is built for developers and businesses that need a long-context, low-cost model for agents, retrieval, and high-volume API workloads. Core Features 320B-parameter transformer with a 1-million-token context window for long...

Muse Glimmer 30B is Meta's open-weight local agent model for developers who want a capable AI agent that runs entirely on a single consumer GPU instead of in the cloud. Released on August 10, 2026 under the Apache 2.0 license, it is a 29.6-billion-parameter dense model distilled from the closed Muse Spark 1.2 teacher. Core Features Local-first inference: a 4-bit quantized build fits under 20 GB...

Grok 4.6 is xAI's flagship large language model, built for developers and teams running long-horizon agents, coding workflows, and knowledge work. Released on August 12, 2026, it is the default model inside Grok Build and the coding agent, and it is available through the xAI API, Cursor, OpenRouter, Vercel, and Cloudflare. The model carries roughly 1.5 trillion parameters and runs at about 80 t...

Qwen3.8-Max is Alibaba's flagship large language model and the largest open-weight release to date, built for developers and enterprises that want frontier-level multimodal reasoning without per-seat vendor lock-in. Tongyi Lab shipped it on August 3, 2026, with the full 2.4-trillion-parameter weights (about 95B active per token) scheduled to open-source the following week. It runs a 1M-token co...