Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....
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...
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...
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...
This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
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 upon the UI-TARS framework with reinforcement...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
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...
No provider description is available for this model yet.
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
This model always redirects to the latest model in the Claude Haiku family.
No provider description is available for this model yet.
No provider description is available for this model yet.
This model always redirects to the latest model in the GPT Mini family.
This model always redirects to the latest model in the Gemini Pro family.
No provider description is available for this model yet.
No provider description is available for this model yet.
This model always redirects to the latest model in the Kimi family.
This model always redirects to the latest model in the Gemini Flash family.
No provider description is available for this model yet.
Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
No provider description is available for this model yet.
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, accepting...
Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
No provider description is available for this model yet.
Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...
No provider description is available for this model yet.
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...
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
No provider description is available for this model yet.
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...
No provider description is available for this model yet.
No provider description is available for this model yet.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Sao10K: Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b | 131.072K | $0.85 | $0.85 | — | |||
| Nous: Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70b | 131.072K | $0.7 | $0.7 | — | |||
| Nous: Hermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405b | 131.072K | $1 | $1 | — | |||
| Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b | 8.192K | $0.04 | $0.05 | — | |||
| Meta: Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct | Meta |
131.072K | $0.4 | $0.4 | — | ||
| Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | Meta |
131.072K | $0.05 | $0.08 | — | ||
| Mistral: Mistral Nemomistralai/mistral-nemo | Mistral AI |
131.072K | $0.019 | $0.03 | — | ||
| OpenAI: GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18 | OpenAI |
128K | $0.15 | $0.6 | — | ||
| Google: Gemma 2 27Bgoogle/gemma-2-27b-it | Google |
8.192K | $0.65 | $0.65 | — | ||
| Mistral Largemistralai/mistral-large | Mistral AI |
128K | $2 | $6 | — | ||
| Anthropic: Claude 3 Haikuanthropic/claude-3-haiku | Anthropic |
200K | $0.25 | $1.25 | — | ||
| Qwen: Qwen3 Max Thinkingqwen/qwen3-max-thinking | Alibaba Qwen |
262.144K | $0.78 | $3.9 | — | ||
| ibm/granite-guardian-3-3-8bwatsonx/ibm/granite-guardian-3-3-8b | Watsonx |
8.192K | $0.2 | $0.2 | — | ||
| qwen/qwen3-coder-nextnovita/qwen/qwen3-coder-next | 262.144K | $0.2 | $1.5 | — | |||
| zai-org/glm-5novita/zai-org/glm-5 | 202.8K | $1 | $3.2 | — | |||
| ibm/granite-guardian-3-2-2bwatsonx/ibm/granite-guardian-3-2-2b | Watsonx |
8.192K | $0.1 | $0.1 | — | ||
| ByteDance: UI-TARS 7B bytedance/ui-tars-1.5-7b | 128K | $0.1 | $0.2 | — | |||
| gemma-4-31B-itsambanova/gemma-4-31b-it | 131.072K | $0.38 | $1.15 | — | |||
| deepseek/deepseek-v3.2-expopenrouter/deepseek/deepseek-v3.2-exp | Openrouter |
163.84K | $0.2 | $0.4 | — | ||
| minimax/minimax-m2.5novita/minimax/minimax-m2.5 | 204.8K | $0.3 | $1.2 | — | |||
| qwen/qwen3.5-397b-a17bnovita/qwen/qwen3.5-397b-a17b | 262.144K | $0.6 | $3.6 | — | |||
| ibm/granite-4-h-smallwatsonx/ibm/granite-4-h-small | Watsonx |
20.48K | $0.06 | $0.25 | — | ||
| Meta: Llama Guard 4 12Bmeta-llama/llama-guard-4-12b | Meta |
163.84K | $0.18 | $0.18 | — | ||
| databricks-gemini-3-1-flash-litedatabricks/databricks-gemini-3-1-flash-lite | Databricks |
1.04858M | $0.312 | $1.875 | — | ||
| NVIDIA: Nemotron 3 Nano Omni (free)nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | NVIDIA |
256K | Free | Free | — | ||
| Anthropic: Claude Haiku Latest~anthropic/claude-haiku-latest | Anthropic |
200K | $1 | $5 | — | ||
| databricks-claude-sonnet-4-6databricks/databricks-claude-sonnet-4-6 | Databricks |
1M | $3 | $15 | — | ||
| ibm/granite-3-3-8b-instructwatsonx/ibm/granite-3-3-8b-instruct | Watsonx |
8.192K | $0.2 | $0.2 | — | ||
| OpenAI: GPT Mini Latest~openai/gpt-mini-latest | OpenAI |
400K | $0.75 | $4.5 | — | ||
| Google: Gemini Pro Latest~google/gemini-pro-latest | Google |
1.04858M | $2 | $12 | — | ||
| DeepSeek-V3.2sambanova/deepseek-v3.2 | 32.768K | $3 | $4.5 | — | |||
| databricks-claude-opus-4-6databricks/databricks-claude-opus-4-6 | Databricks |
1M | $5 | $25 | — | ||
| MoonshotAI: Kimi Latest~moonshotai/kimi-latest | Moonshot AI |
1.04858M | $2.1 | $10.95 | — | ||
| Google: Gemini Flash Latest~google/gemini-flash-latest | Google |
1.04858M | $0.75 | $3.75 | — | ||
| ibm/granite-13b-instruct-v2watsonx/ibm/granite-13b-instruct-v2 | Watsonx |
8.192K | $0.6 | $0.6 | — | ||
| Poolside: Laguna XS 2.1 (free)poolside/laguna-xs-2.1:free | Poolside |
262.144K | Free | Free | — | ||
| qwen/qwen3.5-35b-a3bnovita/qwen/qwen3.5-35b-a3b | 262.144K | $0.25 | $2 | — | |||
| NVIDIA: Nemotron 3.5 Content Safety (free)nvidia/nemotron-3.5-content-safety:free | NVIDIA |
128K | Free | Free | — | ||
| Nex AGI: Nex-N2-Pronex-agi/nex-n2-pro | 262.144K | $0.25 | $1 | — | |||
| Mistral: Mistral Medium 3.5mistralai/mistral-medium-3-5 | Mistral AI |
262.144K | $1.5 | $7.5 | — | ||
| qwen/qwen3.5-122b-a10bnovita/qwen/qwen3.5-122b-a10b | 262.144K | $0.4 | $3.2 | — | |||
| IBM: Granite 4.1 8Bibm-granite/granite-4.1-8b | IBM |
131.072K | $0.05 | $0.1 | — | ||
| ibm/granite-13b-chat-v2watsonx/ibm/granite-13b-chat-v2 | Watsonx |
8.192K | $0.6 | $0.6 | — | ||
| Mistral: Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instruct | Mistral AI |
128K | $0.351 | $0.555 | — | ||
| Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:free | Google |
262.144K | Free | Free | — | ||
| Google: Gemma 4 31B (free)google/gemma-4-31b-it:free | Google |
262.144K | Free | Free | — | ||
| DeepSeek-V3.1sambanova/deepseek-v3.1 | 131.072K | $3 | $4.5 | — | |||
| Z.ai: GLM 5 Turboz-ai/glm-5-turbo | Z Ai |
202.752K | $1.2 | $4 | — | ||
| deepseek/deepseek-v3.2openrouter/deepseek/deepseek-v3.2 | Openrouter |
163.84K | $0.28 | $0.4 | — | ||
| meta.llama-3.1-8b-instructoci/meta.llama-3.1-8b-instruct | 128K | $0.72 | $0.72 | — |