Search the modelsyour product can ship.

mistralai/mistral-large-2512

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.

allenai/olmo-3-7b-instruct

Olmo 3 7B Instruct is a supervised instruction-fine-tuned variant of the Olmo 3 7B base model, optimized for instruction-following, question-answering, and natural conversational dialogue. By leveraging high-quality instruction data and an open training pipeline, it delivers strong performance across everyday NLP tasks while remaining accessible and easy to integrate. Developed by Ai2 under the Apache 2.0 license, the model offers a transparent, community-friendly option for instruction-driven applications.

openrouter/sherlock-think-alpha

This model was an early snapshot of Grok 4.1 Fast with reasoning enabled. Try the official launch of Grok 4.1 Fast [here](/x-ai/grok-4.1-fast) This is a cloaked model provided to the community to gather feedback. A frontier reasoning model that excels at tool calling, with a 1.8M context window and multimodal support. **Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.

openrouter/sherlock-dash-alpha

This model was an early snapshot of Grok 4.1 Fast with reasoning disabled. Try the official launch of Grok 4.1 Fast [here](/x-ai/grok-4.1-fast) This is a cloaked model provided to the community to gather feedback. A frontier non-reasoning model that excels at tool calling, with a 1.8M context window and multimodal support. **Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.

openrouter/polaris-alpha

This model was an early snapshot of GPT-5.1 with reasoning effort set to minimal. Try the official launch of GPT-5.1 [here](/openai/gpt-5.1) This is a cloaked model provided to the community to gather feedback. A powerful, general-purpose model that excels across real-world tasks, with standout performance in coding, tool calling, and instruction following. **Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.

deepcogito/cogito-v2.1-671b

Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning to reach state-of-the-art performance on multiple categories (instruction following, coding, longer queries and creative writing). This advanced system demonstrates significant progress toward scalable superintelligence through policy improvement.

intfloat/multilingual-e5-large

The multilingual-e5-large embedding model encodes sentences, paragraphs, and documents across over 90 languages into a 1024-dimensional dense vector space, delivering robust semantic embeddings optimized for multilingual retrieval, cross-language similarity, and large-scale data search.

intfloat/e5-base-v2

The e5-base-v2 embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, similarity scoring, retrieval and clustering.

intfloat/e5-large-v2

The e5-large-v2 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-accuracy semantic embeddings optimized for retrieval, semantic search, reranking, and similarity-scoring tasks.

thenlper/gte-large

The gte-large embedding model converts English sentences, paragraphs and moderate-length documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for information retrieval, semantic textual similarity, reranking and clustering tasks. Trained via multi-stage contrastive learning on a large domain-diverse relevance corpus, it offers excellent performance across general-purpose embedding use-cases.

thenlper/gte-base

The gte-base embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, delivering efficient and effective semantic embeddings optimized for textual similarity, semantic search, and clustering applications.

baai/bge-m3

The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.

baai/bge-large-en-v1.5

The bge-large-en-v1.5 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-fidelity semantic embeddings optimized for semantic search, document retrieval, and downstream NLP tasks in English.

sentence-transformers/multi-qa-mpnet-base-dot-v1

The multi-qa-mpnet-base-dot-v1 embedding model transforms sentences and short paragraphs into a 768-dimensional dense vector space, generating high-quality semantic embeddings optimized for question-and-answer retrieval, semantic search, and similarity-scoring across diverse content.

baai/bge-base-en-v1.5

The bge-base-en-v1.5 embedding model converts English sentences and paragraphs into 768-dimensional dense vectors, delivering efficient, high-quality semantic embeddings optimized for retrieval, semantic search, and document-matching workflows. This version (v1.5) features improved similarity-score distribution and stronger retrieval performance out of the box.

sentence-transformers/all-minilm-l12-v2

The all-MiniLM-L12-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, clustering, and similarity-scoring.

sentence-transformers/paraphrase-minilm-l6-v2

The paraphrase-MiniLM-L6-v2 embedding model converts sentences and short paragraphs into a 384-dimensional dense vector space, producing high-quality semantic embeddings optimized for paraphrase detection, semantic similarity scoring, clustering, and lightweight retrieval tasks.

sentence-transformers/all-minilm-l6-v2

The all-MiniLM-L6-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, enabling high-quality semantic representations that are ideal for downstream tasks such as information retrieval, clustering, similarity scoring, and text ranking.

sentence-transformers/all-mpnet-base-v2

The all-mpnet-base-v2 embedding model encodes sentences and short paragraphs into a 768-dimensional dense vector space, providing high-fidelity semantic embeddings well suited for tasks like information retrieval, clustering, similarity scoring, and text ranking.

qwen/qwen3-embedding-0.6b

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.

amazon/nova-premier-v1

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.

mistralai/mistral-embed-2312

Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively capture semantic relationships in text.

google/gemini-embedding-001

gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark (MTEB) Multilingual leaderboard since the experimental launch in March.

mistralai/codestral-embed-2505

Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.

mistralai/voxtral-small-24b-2507

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio is priced at $100 per million seconds.

qwen/qwen3-embedding-8b

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.

qwen/qwen3-embedding-4b

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.

openrouter/andromeda-alpha

This model has been revealed as NVIDIA Nemotron Nano 2 VL. It continues to be offered for free by NVIDIA [here](https://openrouter.ai/nvidia/nemotron-nano-12b-v2-vl:free). This is a small reasoning VLM trained for image understanding. It's strengths include multi-image comprehension (6+ images), especially those containing charts and text. This is a cloaked model provided to the community to gather feedback. Note: All prompts and output are logged to improve the provider’s model and its product and services. Please do not upload any personal, confidential, or otherwise sensitive information. This is a trial use only. Do not use for production or business-critical systems.

ibm-granite/granite-4.0-h-micro

Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long context tool calling.

deepcogito/cogito-v2-preview-llama-405b

Cogito v2 405B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. It represents a significant step toward frontier intelligence with dense architecture delivering performance competitive with leading closed models. This advanced reasoning system combines policy improvement with massive scale for exceptional capabilities.

qwen/qwen3-vl-8b-instruct

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon temporal reasoning, DeepStack for fine-grained visual-text alignment, and text-timestamp alignment for precise event localization. The model supports a native 256K-token context window, extensible to 1M tokens, and handles both static and dynamic media inputs for tasks like document parsing, visual question answering, spatial reasoning, and GUI control. It achieves text understanding comparable to leading LLMs while expanding OCR coverage to 32 languages and enhancing robustness under varied visual conditions.

relace/relace-apply-3

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 tokens/sec on average. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update> Zero Data Retention is enabled for Relace. Learn more about this model in their [documentation](https://docs.relace.ai/api-reference/instant-apply/apply)

openrouter/sonoma-dusk-alpha

This is a cloaked model provided to the community to gather feedback. A fast and intelligent general-purpose frontier model with a 2 million token context window. Supports image inputs and parallel tool calling. Note: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.

openrouter/sonoma-sky-alpha

This is a cloaked model provided to the community to gather feedback. A maximally intelligent general-purpose frontier model with a 2 million token context window. Supports image inputs and parallel tool calling. Note: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.

deepcogito/cogito-v2-preview-llama-70b

Cogito v2 70B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. Built with iterative policy improvement, it delivers strong performance across reasoning tasks while maintaining efficiency through shorter reasoning chains and improved intuition.

openrouter/horizon-beta

This is a cloaked model provided to the community to gather feedback. This is an improved version of [Horizon Alpha](/openrouter/horizon-alpha) Note: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.

openrouter/horizon-alpha

This was a cloaked model provided to the community to gather feedback. It has been deprecated - see [Horizon Beta](/openrouter/horizon-beta). Note: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.

switchpoint/router

Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library. As the world of LLMs advances, our router gets smarter, ensuring you always benefit from the industry's newest models without changing your workflow. This model is configured for a simple, flat rate per response here on OpenRouter. It's powered by the full routing engine from [Switchpoint AI](https://www.switchpoint.dev).

morph/morph-v3-large

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update> Zero Data Retention is enabled for Morph. Learn more about this model in their [documentation](https://docs.morphllm.com/quickstart)

morph/morph-v3-fast

Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update> Zero Data Retention is enabled for Morph. Learn more about this model in their [documentation](https://docs.morphllm.com/quickstart)

openrouter/cypher-alpha

This is a cloaked model provided to the community to gather feedback. It's an all-purpose model supporting real-world, long-context tasks including code generation. Note: All prompts and completions for this model are logged by the provider and may be used to improve the model and other products and services. You remain responsible for any required end user notices and consents and for ensuring that no personal, confidential, or otherwise sensitive information, including data from individuals under the age of 18, is submitted.

morph/morph-v2

Morph Apply is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 4000+ tokens per second. The model requires the prompt to be in the following format: <code>${originalCode}</code>\n<update>${updateSnippet}</update> Learn more about this model in their [documentation](https://docs.morphllm.com/)

openrouter/optimus-alpha

This is a cloaked model provided to the community to gather feedback. It's geared toward real world use cases, including programming. **Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.

openrouter/quasar-alpha

This is a cloaked model provided to the community to gather feedback. It’s a powerful, all-purpose model supporting long-context tasks, including code generation. **Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.

perplexity/sonar-reasoning-pro

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for advanced use cases, it supports in-depth, multi-step queries with a larger context window and can surface more citations per search, enabling more comprehensive and extensible responses.

perplexity/sonar-pro

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like double the number of citations per search as Sonar on average. Plus, with a larger context window, it can handle longer and more nuanced searches and follow-up questions.

perplexity/sonar-deep-research

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers information. This enables comprehensive report generation across domains like finance, technology, health, and current events. Notes on Pricing ([Source](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-deep-research)) - Input tokens comprise of Prompt tokens (user prompt) + Citation tokens (these are processed tokens from running searches) - Deep Research runs multiple searches to conduct exhaustive research. Searches are priced at $5/1000 searches. A request that does 30 searches will cost $0.15 in this step. - Reasoning is a distinct step in Deep Research since it does extensive automated reasoning through all the material it gathers during its research phase. Reasoning tokens here are a bit different than the CoTs in the answer - these are tokens that we use to reason through the research material prior to generating the outputs via the CoTs. Reasoning tokens are priced at $3/1M tokens

perplexity/r1-1776

R1 1776 is a version of DeepSeek-R1 that has been post-trained to remove censorship constraints related to topics restricted by the Chinese government. The model retains its original reasoning capabilities while providing direct responses to a wider range of queries. R1 1776 is an offline chat model that does not use the perplexity search subsystem. The model was tested on a multilingual dataset of over 1,000 examples covering sensitive topics to measure its likelihood of refusal or overly filtered responses. [Evaluation Results](https://cdn-uploads.huggingface.co/production/uploads/675c8332d01f593dc90817f5/GiN2VqC5hawUgAGJ6oHla.png) Its performance on math and reasoning benchmarks remains similar to the base R1 model. [Reasoning Performance](https://cdn-uploads.huggingface.co/production/uploads/675c8332d01f593dc90817f5/n4Z9Byqp2S7sKUvCvI40R.png) Read more on the [Blog Post](https://perplexity.ai/hub/blog/open-sourcing-r1-1776)