OpenRouter

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use, including VQA, document parsing, chart and table extraction, and multilingual OCR. The series emphasizes robust perception, including recognition of diverse real-world and synthetic categories, spatial understanding through 2D/3D grounding, and long-form visual comprehension.

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs.

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba and the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization.

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek. It adds image understanding while matching the base model’s text capabilities, including agents.

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior.

Perceptron Mk1.5 is Perceptron’s embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations such as points, boxes, polygons, and tracks.

Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception.

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek and the cost-efficient tier of the V4.1 family. DeepSeek reports that it exceeds V4 Pro in performance and speed. It is the first model built on the company’s Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input.

GLM-5.3-FlashX is the high-speed variant of Z.ai’s GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. It is built on the same hybrid sparse and linear attention architecture as GLM-5.3-Flash.

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window.

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

GPT-6 Luna is the fast, cost-efficient model in OpenAI’s GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat and classification.

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with a 128k-token context window and optimized for efficient local inference, it supports use cases such as conversational agents.

This model always redirects to the latest model in the DeepSeek Flash family.

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. It is built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, and employs a hybrid attention mechanism.

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Summarize is an abstractive summarization model from ScaleDown.

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks.

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability.

Command A+ is Cohere’s flagship model for enterprise agentic workflows. It accepts text and image inputs, has a 192K context window, and supports native tool calling with strict tool schemas.

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It accepts text and image inputs and returns text. It is designed for agentic workflows and coding.

Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited to frontend development, multilingual programming tasks, and coding-agent workflows.

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world and synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image, multi-turn instructions, video timeline alignments, and GUI automation.

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on combining accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks, including visual question answering (TextVQA) and video understanding (VATEX). Amazon Nova Pro demonstrates strong capabilities in processing visual and textual information and analyzing financial documents. **NOTE**: Video input is not supported.

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in coding and reasoning tasks with improved precision and controllability. It achieves state-of-the-art performance on SWE-bench (72.7%) and balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation.

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture.

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It accepts text, image, video, audio, and PDF inputs.

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy. With an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in coding, STEM reasoning, and enterprise adaptation. It supports hybrid and on-prem deployments.

Qwen3.6 Flash is a fast, efficient language model from Alibaba’s Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Its pricing is tiered.

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. It matches Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, bringing frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line, enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows.

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...

This model always redirects to the latest model in the GLM Flash family.

Mistral Medium 3.1 is an updated version of Mistral Medium 3, a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in coding and STEM reasoning.

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review, bug finding, and visual analysis.

GPT-5.4 Image 2 combines OpenAI’s GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows that let users move seamlessly between reasoning and coding.

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities, accepting text, image, and video inputs.

This model always redirects to the latest model in the Anthropic Claude Sonnet family.

Grok 4.3 is a reasoning model. It accepts text and image inputs with text output and is suited for agentic workflows and instruction-following tasks.

MiniMax-M3 is a multimodal foundation model from MiniMax. It accepts text, image, and video inputs and returns text. It has a 1M-token context window and is suited to long-horizon agentic work and coding.

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work, including long code refactors, front-end work, and visual work.

Claude Opus 4.8 is Anthropic’s most capable generally available model in the Opus family. It accepts text, image, and file inputs and returns text, with reasoning support.

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited to end-to-end software delivery and multi-step task execution.

Qwen3.7-Plus is a cost-effective model in Alibaba’s Qwen3.7 series. It supports text and image input with text output and builds on the series’ text capabilities.

Sonnet 5 is Anthropic’s most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels, including low, medium, high, and max.

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds on the UI-TARS framework with reinforcement learning-based reasoning, enabling robust action planning and execution across virtual interfaces. This model achieves state-of-the-art results on a range of interactive and grounding benchmarks, including OSworld, WebVoyager, AndroidWorld, and ScreenSpot.

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements.

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Grok 4.7 is SpaceXAI’s flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks and verifying its own work.

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning and coding, as well as agentic and tool-use systems.

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.

Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window.

Kimi K2.6 is Moonshot AI’s next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go.

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.

Step 3.7 Flash is StepFun’s latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding and activates roughly 11B parameters.

This model always redirects to the latest model in the Anthropic Claude Haiku family.

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as a smaller, more efficient model.

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.

Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...

This model always redirects to the latest model in the Claude Opus family.

Grok Build 0.1 is a fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output and is optimized for interactive coding.

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks. It features flexible thinking.

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost and surpasses MiMo-V2-Omni in multimodal perception across image and video understanding.

Fugu Max is the cost-performance model in Sakana AI’s Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system built around a language model trained for routing.

MiMo-V2.6-Pro-UltraSpeed is the fast-speed edition of Xiaomi’s flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality.

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for interactive development sessions and long, independent execution of complex engineering tasks. It supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs.

Claude Opus 5.5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases.

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI’s Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts design.

This model always redirects to the latest model in the MoonshotAI Kimi family.

Note: Sonar Pro pricing includes Perplexity search pricing. See details here. For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, including double the number of citations per search on average compared with Sonar. Its larger context window supports longer and more nuanced searches and follow-up questions.

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba’s Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text.

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It has a 1M+ token context window (922K input, 128K output).

Gemini 3.5 Flash-Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step reasoning.

GPT Chat Latest points to OpenAI’s stable API alias `chat-latest`, which always resolves to the latest Instant chat model used in ChatGPT.

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits.

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba’s Qwen team, served as a separate SKU at a higher price point. Its accepted modalities are text, image, and video.

This model always redirects to the latest model in the Claude Fable family.

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features optimized for speed.

Perceptron Mk1 (Mark One) is Perceptron’s highest-quality vision-language model for video and embodied reasoning. It accepts image and video inputs paired with natural-language queries and produces detailed visual understanding.

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI’s GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows. It also provides capable reasoning.

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Gemini 3.5 Flash is Google’s high-efficiency multimodal model, bringing near-Pro-level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution.

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and has a 1M-token context.

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.

Fugu Ultra v2 is the higher-performance model in Sakana AI’s Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system built around a language model.

This model always redirects to the latest model in the OpenAI GPT Sol family.

GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.

This model always redirects to the latest model in the OpenAI GPT Terra family.

GPT-6 Sol is the cost-efficient high-end model in OpenAI’s GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier.

GPT-5.6 Terra is a balanced model in OpenAI’s GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding and reasoning.

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Qwen3.8 Max is the flagship model in Alibaba’s Qwen3.8 series and the general-availability successor to Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning and visual understanding.

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and has a 1M-token context.

This model always redirects to the latest model in the Google Gemini Flash family.

This model always redirects to the latest model in the Google Gemini Pro family.

GPT-6 Astra is OpenAI’s flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation.

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.

Fugu Ultra is the higher-performance model in Sakana AI’s Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system built around a language model trained for routing.

GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware.

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It accepts text, image, and file inputs, returns text, and supports reasoning.

This model always redirects to the latest model in the OpenAI GPT Luna family.

GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Kimi K3 is a 2.8T-parameter open-weight multimodal reasoning model from Moonshot AI. It is suited to complex coding, knowledge work, and long-horizon agentic workflows.

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

This model always redirects to the latest model in the OpenAI GPT Mini family.

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks.

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads. It builds on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks.

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.

GPT-5.6 Sol is the flagship model in OpenAI’s GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks.

This model always redirects to the latest model in the OpenAI GPT Astra family.

Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further by producing shorter reasoning traces.

Extract is a description-driven entity extraction model from ScaleDown.

This model always redirects to the latest model in the Pareto family.

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.