Models

Inkling 2 Small is a multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second Inkling generation. It was trained with reinforcement learning on long-horizon coding tasks across many agent harnesses, and is suited for agentic coding, autonomous research, agentic knowledge work and retrieval-augmented generation, with English and general multilingual support. It accepts text and image input (no audio), supports tool calling and variable reasoning effort, and has a 1M-token context window.

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible software migrations, designed working electronic devices from scratch, and made progress on open problems in physics and mathematics. It communicates more clearly than earlier Fable models and generates output up to 30% faster than Fable 5.1. Adaptive extended thinking is always on, with reasoning effort levels from low to max (default high) and preserved thinking across turns. Anthropic recommends Opus 5.5 as the daily driver for most coding and knowledge work, with Fable 5.2 for the most ambitious, open-ended problems.

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible software migrations, designed working electronic devices from scratch, and made progress on open problems in physics and mathematics. It communicates more clearly than earlier Fable models and generates output up to 30% faster than Fable 5.1. Adaptive extended thinking is always on, with reasoning effort levels from low to max (default high) and preserved thinking across turns. Anthropic recommends Opus 5.5 as the daily driver for most coding and knowledge work, with Fable 5.2 for the most ambitious, open-ended problems.

Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing, extraction, and long document parsing. Muse Ember accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used to train Liquid models.

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used to train Liquid models.

Decisions Fast is Parallel's web-grounded Decisions model. Instead of generating text, it reads the content passed as state (text or JSON), researches the live web, and returns typed answers to named questions: the probability of yes for a yes/no question (noul), a choice with per-option probabilities (choice), or a level on an ordered rubric (score), with per-question refusals and request-level citations to the sources it used. It suits fact checks, entity screening, and classification that depend on current information rather than only on what the caller supplies. A request can carry up to 100 questions about the same state, with up to 32,000 tokens per question including the shared state.

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native audio in 16:9 or 9:16, from 360p drafts up to 4K, and supports text-to-video, image-to-video, first and last frame interpolation, subject and video references with improved reference management, and editing or extending an uploaded video. Multi-turn editing and extension of a prior generation is supported through previous_job_id. Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generation

Auto is OpenRouter’s flagship model router, built for general-purpose usage. It adapts to each request, choosing cost-optimal models and adjusting reasoning effort. It balances task difficulty, benchmark results, live prices, and prompt caching. Use it for apps, chat, and general agents. For agent sessions, it follows progress across turns, keeps the same model while work is going well, and adjusts reasoning effort or switches models when the task gets stuck. It respects all your governance settings, including guardrails, ZDR, and budgets.

Auto Code is OpenRouter’s router built specifically for coding agents and harnesses. It uses the same routing engine as the Auto Router, with every request treated as part of an agent session and model choices guided by coding-task pass rate, completion time, and cost per solved task. It follows edits, test results, and recurring errors across turns, keeping the model while work is going well and trying more reasoning effort before switching when trouble persists. Its default coding tier starts from stronger models and weighs failed code changes more heavily. Your model and provider restrictions still apply.

GPT Image 2.6 Sunburst is OpenAI's image generation and editing model optimized for detail: dense compositions, text-heavy layouts, and edits that keep details consistent from one edit to the next at medium or high quality, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Flare instead when speed matters more than fine detail.

GPT Image 2.6 Flare is OpenAI's image generation and editing model optimized for speed: fast iteration and interactive text-to-image and image-to-image workflows, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Sunburst instead when detail and edit-to-edit consistency matter more than latency.

Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and last frame interpolation, subject and video references (up to three reference clips), and editing or extending an uploaded video, and generates clips from 360p drafts up to 4K with native audio in 16:9 or 9:16. Multi-turn editing and extension of a prior generation is supported through previous_job_id, up to 40 seconds of total video. Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generation

Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity tasks. It also introduces visual understanding for the first time.

Morph's decision model. Answers typed choice, noul and score questions about a state. The state is prefix-cached across requests, so repeat questions on the same state bill at the cached-input rate. 65k context window.

Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). It embeds text, images, and interleaved text and image content into a single vector space and is suited for high-volume query embedding, agent loops, and multilingual semantic search across 100+ languages. It shares its embedding space with Embed 5 Pro, so documents indexed with Pro can be queried with Fast. Output dimensions are selectable from 256 to 2048, and input_type defaults to search_document when not set.

Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family of multimodal embedding models (about 2.4B parameters). It embeds text, images, and interleaved text and image content into a single vector space and is suited for retrieval and RAG over long or domain-specific documents, visual and document search, and multilingual semantic search across 100+ languages. It shares its embedding space with Embed 5 Fast, so a common pattern is to index a corpus with Pro and embed queries with Fast. Output dimensions are selectable from 256 to 2048, and input_type defaults to search_document when not set.

Rerank 5 Fast is the low-latency tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for high-throughput retrieval such as high-volume search, agent tool loops, and first-pass filtering before a more expensive step. Relevance scores are calibrated to a 0-1 range so a fixed threshold behaves consistently across queries. Rerank 5 Pro is the higher-accuracy sibling for complex queries and long or domain-specific documents.

Rerank 5 Pro is the higher-accuracy tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for retrieval pipelines where ranking quality matters most: complex or reasoning-heavy queries, long or domain-specific documents, and RAG systems that feed a small number of passages to a generator. Relevance scores are calibrated to a 0-1 range so a fixed threshold behaves consistently across queries. Rerank 5 Fast is the lower-latency sibling for high-volume search and agent loops.