Meta: Llama 3.3 70B Instruct

OpenRouter

DeepSeek

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.

Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

DeepSeek: DeepSeek V3.2

Google

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It introduces notable enhancements in multimodal understanding, coding capabilities, complex instruction following, and function calling. These advancements come together to deliver more seamless and robust agentic experiences.

Google: Gemini 2.0 Flash

Qwen

Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks.

Qwen: Qwen-Turbo

Z.AI

GLM 4 32B is a cost-effective foundation language model.

It can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-related intelligent tasks.

It is made by the same lab behind the thudm models.

Z.AI: GLM 4 32B 

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. 

Google: Gemini 2.5 Flash Lite

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks such as text generation, speech recognition, translation, and image analysis. Leveraging innovations like Per-Layer Embedding (PLE) caching and the MatFormer architecture, Gemma 3n dynamically manages memory usage and computational load by selectively activating model parameters, significantly reducing runtime resource requirements.

This model supports a wide linguistic range (trained in over 140 languages) and features a flexible 32K token context window. Gemma 3n can selectively load parameters, optimizing memory and computational efficiency based on the task or device capabilities, making it well-suited for privacy-focused, offline-capable applications and on-device AI solutions. [Read more in the blog post](https://developers.googleblog.com/en/introducing-gemma-3n/)

Google: Gemma 3n 4B

Mistral

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.

The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. [Read the blog post about the model here.](https://mistral.ai/news/mistral-small-3/)

Mistral: Mistral Small 3

The first multi-modal, text+image-to-text model from Mistral AI. Its weights were launched via torrent: https://x.com/mistralai/status/1833758285167722836.

Mistral: Pixtral 12B

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.

Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.

Meta: Llama 4 Scout

Amazon

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon Nova Micro excels at tasks such as text summarization, translation, content classification, interactive chat, and brainstorming. It has  simple mathematical reasoning and coding abilities.

Amazon: Nova Micro 1.0

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.

Amazon: Nova Lite 1.0

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of 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 both visual and textual information and at analyzing financial documents.

**NOTE**: Video input is not supported at this time.

Amazon: Nova Pro 1.0

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.

Amazon: Nova 2 Lite

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

[Blog Post](https://mistral.ai/news/codestral-25-08)

Mistral: Codestral 2508

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages.

Trained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings.

Click here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).

Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).

Meta: Llama 3.2 3B Instruct

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong task performance.

Supporting eight core languages and fine-tunable for more, Llama 1.3B is ideal for businesses or developers seeking lightweight yet powerful AI solutions that can operate in diverse multilingual settings without the high computational demand of larger models.

Click here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).

Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).

Meta: Llama 3.2 1B Instruct

The Llama 90B Vision model is a top-tier, 90-billion-parameter multimodal model designed for the most challenging visual reasoning and language tasks. It offers unparalleled accuracy in image captioning, visual question answering, and advanced image-text comprehension. Pre-trained on vast multimodal datasets and fine-tuned with human feedback, the Llama 90B Vision is engineered to handle the most demanding image-based AI tasks.

This model is perfect for industries requiring cutting-edge multimodal AI capabilities, particularly those dealing with complex, real-time visual and textual analysis.

Click here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD_VISION.md).

Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).

Meta: Llama 3.2 90B Vision Instruct

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.

Llama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.

Meta: Llama Guard 4 12B

Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual question answering, bridging the gap between language generation and visual reasoning. Pre-trained on a massive dataset of image-text pairs, it performs well in complex, high-accuracy image analysis.

Its ability to integrate visual understanding with language processing makes it an ideal solution for industries requiring comprehensive visual-linguistic AI applications, such as content creation, AI-driven customer service, and research.

Click here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD_VISION.md).

Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).

Meta: Llama 3.2 11B Vision Instruct

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.

Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.

Meta: Llama 4 Maverick

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.

It has demonstrated strong performance compared to leading closed-source models in human evaluations.

To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Meta: Llama 3.1 8B Instruct

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This is the base 405B pre-trained version.

It has demonstrated strong performance compared to leading closed-source models in human evaluations.

To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Meta: Llama 3.1 405B (base)

Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.

Llama Guard 3 was aligned to safeguard against the MLCommons standardized hazards taxonomy and designed to support Llama 3.1 capabilities. Specifically, it provides content moderation in 8 languages, and was optimized to support safety and security for search and code interpreter tool calls.


Llama Guard 3 8B

The highly anticipated 400B class of Llama3 is here! Clocking in at 128k context with impressive eval scores, the Meta AI team continues to push the frontier of open-source LLMs.

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 405B instruct-tuned version is optimized for high quality dialogue usecases.

It has demonstrated strong performance compared to leading closed-source models including GPT-4o and Claude 3.5 Sonnet in evaluations.

To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Meta: Llama 3.1 405B Instruct

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.

It has demonstrated strong performance compared to leading closed-source models in human evaluations.

To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Meta: Llama 3.1 70B Instruct

This safeguard model has 8B parameters and is based on the Llama 3 family. Just like is predecessor, [LlamaGuard 1](https://huggingface.co/meta-llama/LlamaGuard-7b), it can do both prompt and response classification.

LlamaGuard 2 acts as a normal LLM would, generating text that indicates whether the given input/output is safe/unsafe. If deemed unsafe, it will also share the content categories violated.

For best results, please use raw prompt input or the `/completions` endpoint, instead of the chat API.

It has demonstrated strong performance compared to leading closed-source models in human evaluations.

To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Meta: LlamaGuard 2 8B

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases.

It has demonstrated strong performance compared to leading closed-source models in human evaluations.

To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Meta: Llama 3 70B Instruct

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases.

It has demonstrated strong performance compared to leading closed-source models in human evaluations.

To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Model	Cost
Google: Gemma 3n 4B	-85%
Mistral: Mistral Small 3	-69%
Mistral: Pixtral 12B	-60%
Z.AI: GLM 4 32B	-58%
Meta: Llama 4 Scout	-55%

Model	Latency
Amazon: Nova Micro 1.0	-231%
Amazon: Nova Lite 1.0	-206%
Amazon: Nova Pro 1.0	-191%
Amazon: Nova 2 Lite	-187%
Mistral: Codestral 2508	-90%

Model	Score
DeepSeek: DeepSeek V3.2	+22%
Google: Gemini 2.0 Flash	+17%
Qwen: Qwen-Turbo	+11%
Z.AI: GLM 4 32B	+10%
Google: Gemini 2.5 Flash Lite	+14%

Model	Score	Latency	Cost/1M
Meta: Llama 4 Maverick	69.1%	4.7s	$0.38
Meta: Llama 4 Scout	66.0%	6.8s	$0.19
Meta: Llama 3.1 405B Instruct	54.1%	48.9s	$3.50
Meta: Llama 3.1 70B Instruct	44.6%	14.5s	$0.40
Meta: Llama 3 70B Instruct	40.0%	20.1s	$0.63
Meta: Llama 3.2 3B Instruct	37.1%	31.7s	$0.02
Meta: Llama 3.2 1B Instruct	30.2%	31.9s	$0.11
Meta: Llama 3.1 8B Instruct	30.0%	32.2s	$0.03
Meta: Llama 3 8B Instruct	25.0%	8.8s	$0.04
Meta: Llama 3.2 11B Vision Instruct	22.5%	44.8s	$0.05
Meta: LlamaGuard 2 8B	15.7%	708ms	$0.20
Meta: Llama 3.1 405B (base)	5.8%	36.1s	$4.00
Llama Guard 3 8B	3.1%	6.6s	$0.04
Meta: Llama Guard 4 12B	0.0%	513ms	$0.18
Meta: Llama 3.2 3B Instruct	0.0%	1.4s	Free
Meta: Llama 3.2 90B Vision Instruct	—	—	$0.38
Meta: Llama 3.1 405B Instruct	—	—	Free

Benchmark	Score	Rank
Venture Capital Terms Benchmark	90.0%	18 / 25
Spatial Reasoning: Germany	81.4%	28 / 35
Niederstetten Benchmark	58.0%	17 / 41
Character Frequency Bench	54.5%	30 / 35
Money Boy Cultural Literacy Test	17.1%	25 / 35
German Memelord Bench	7.2%	29 / 35

Meta: Llama 3.3 70B Instruct

Alternatives

Same Quality, Cheaper

Same Quality, Faster

Same Cost, Better

Other Models from Meta

Benchmark Performance

Price vs Performance

Score Over Time

Benchmark Activity

Quickstart