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....
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
No provider description is available for this model yet.
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...
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
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...
No provider description is available for this model yet.
No provider description is available for this model yet.
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).
KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...
KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...
Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
This model always redirects to the latest model in the DeepSeek V4 Flash family.
No provider description is available for this model yet.
No provider description is available for this model yet.
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. This...
KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...
No provider description is available for this model yet.
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...
This model always redirects to the latest model in the Claude Opus family.
KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...
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...
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
[GPT-5.4](https://openrouter.ai/openai/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, allowing users to seamlessly move between reasoning, coding, and...
Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode Note: As of September...
Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).
MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.
OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...
The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...
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...
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...
Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
No provider description is available for this model yet.
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...
No provider description is available for this model yet.
No provider description is available for this model yet.
UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.
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.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b | 8.192K | $0.04 | $0.05 | — | |||
| ap-south-1/moonshotai.kimi-k2.5bedrock/ap-south-1/moonshotai.kimi-k2.5 | 262.144K | $0.72 | $3.6 | — | |||
| Nous: Hermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405b | 131.072K | $1 | $1 | — | |||
| Reka Edgerekaai/reka-edge | 16.384K | $0.1 | $0.1 | — | |||
| Tencent: Hy3 (free)tencent/hy3:free | Tencent |
262.144K | Free | Free | — | ||
| LiquidAI: LFM2.5-2.6B (free)liquid/lfm-2.5-2.6b:free | 65.536K | Free | Free | — | |||
| Nous: Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70b | 131.072K | $0.7 | $0.7 | — | |||
| nvidia/Nemotron-3-Labs-Ultra-Math-RLnvidia/Nemotron-3-Labs-Ultra-Math-RL | NVIDIA |
Not documented | — | — | — | ||
| ap-south-1/moonshotai.kimi-k2-thinkingbedrock/ap-south-1/moonshotai.kimi-k2-thinking | 262.144K | $0.71 | $2.94 | — | |||
| Sao10K: Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b | 131.072K | $0.85 | $0.85 | — | |||
| Kwaipilot: KAT-Coder-Pro V2kwaipilot/kat-coder-pro-v2 | 262.144K | $0.3 | $1.2 | — | |||
| Kwaipilot: KAT-Coder-Air V2.5kwaipilot/kat-coder-air-v2.5 | 256K | $0.15 | $0.6 | — | |||
| TheDrummer: Rocinante 12Bthedrummer/rocinante-12b | 65.536K | $0.25 | $0.5 | — | |||
| Qwen: Qwen3 30B A3B Thinking 2507qwen/qwen3-30b-a3b-thinking-2507 | Alibaba Qwen |
81.92K | $0.2 | $2.4 | — | ||
| DeepSeek: DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest | Deepseek |
1.04858M | $0.03 | $0.07 | — | ||
| ap-south-1/minimax.minimax-m2.5bedrock/ap-south-1/minimax.minimax-m2.5 | 1M | $0.36 | $1.44 | — | |||
| nvidia/Nemotron-3-Labs-Ultra-Math-SFTnvidia/Nemotron-3-Labs-Ultra-Math-SFT | NVIDIA |
Not documented | — | — | — | ||
| Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420 | Alibaba Qwen |
1M | $0.3 | $1.8 | — | ||
| Kwaipilot: KAT-Coder-Air V2.5 (free)kwaipilot/kat-coder-air-v2.5:free | 256K | Free | Free | — | |||
| nvidia/Riva-Translate-4B-Instruct-v1.1nvidia/Riva-Translate-4B-Instruct-v1.1 | NVIDIA |
Not documented | — | — | — | ||
| Amazon: Nova Micro 1.0amazon/nova-micro-v1 | Amazon |
128K | $0.035 | $0.14 | — | ||
| Anthropic: Claude Opus Latest~anthropic/claude-opus-latest | Anthropic |
1M | $5 | $25 | — | ||
| Kwaipilot: KAT-Coder-Pro V2.5 (free)kwaipilot/kat-coder-pro-v2.5:free | 256K | Free | Free | — | |||
| Amazon: Nova Lite 1.0amazon/nova-lite-v1 | Amazon |
300K | $0.06 | $0.24 | — | ||
| Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct | Meta |
131.072K | $0.1 | $0.32 | — | ||
| OpenAI: GPT-5.4 Image 2openai/gpt-5.4-image-2 | OpenAI |
272K | $8 | $15 | — | ||
| Anthropic: Claude Opus 4.8 (Fast)anthropic/claude-opus-4.8-fast | Anthropic |
1M | $10 | $50 | — | ||
| Sao10K: Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b | 131.072K | $0.65 | $0.75 | — | |||
| MiniMax: MiniMax-01minimax/minimax-01 | MiniMax |
1.00019M | $0.2 | $1.1 | — | ||
| Mistral: Mistral Small 4mistralai/mistral-small-2603 | Mistral AI |
262.144K | $0.15 | $0.6 | — | ||
| OpenAI: GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-0613 | OpenAI |
4.095K | $1 | $2 | — | ||
| WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22b | Microsoft |
65.535K | $0.62 | $0.62 | — | ||
| DeepSeek: R1 Distill Llama 70Bdeepseek/deepseek-r1-distill-llama-70b | DeepSeek |
8.192K | $0.8 | $0.8 | — | ||
| Mistral: Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct | Mistral AI |
65.536K | $2 | $6 | — | ||
| Mancer: Weaver (alpha)mancer/weaver | 8K | $0.4 | $0.75 | — | |||
| OpenAI: o3 Mini Highopenai/o3-mini-high | OpenAI |
200K | $1.1 | $4.4 | — | ||
| Pareto Code Routeropenrouter/pareto-code | Openrouter |
2M | — | — | — | ||
| Qwen: Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct | Alibaba Qwen |
131.072K | $0.117 | $0.455 | — | ||
| Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-2501 | Mistral AI |
32.768K | $0.05 | $0.08 | — | ||
| Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct | Alibaba Qwen |
32.768K | $0.1 | $0.2 | — | ||
| us-gov.nvidia.nemotron-super-3-120bbedrock_converse/us-gov.nvidia.nemotron-super-3-120b | 256K | $0.18 | $0.78 | — | |||
| Magnum v4 72Banthracite-org/magnum-v4-72b | 32.768K | $2.5 | $5 | — | |||
| Mistral: Sabamistralai/mistral-saba | Mistral AI |
32.768K | $0.2 | $0.6 | — | ||
| kimi-k3fireworks_ai/kimi-k3 | Fireworks_Ai |
1.04858M | $3 | $15 | — | ||
| glm-5p2-fast-usfireworks_ai/glm-5p2-fast-us | Fireworks_Ai |
1.04858M | $2.1 | $6.6 | — | ||
| TheDrummer: UnslopNemo 12Bthedrummer/unslopnemo-12b | 1.024M | $0.4 | $0.4 | — | |||
| FW-Kimi-K2.5azure_ai/fw-kimi-k2.5 | 262.144K | $0.66 | $3.3 | — | |||
| us-gov.openai.gpt-oss-20b-1:0bedrock_converse/us-gov.openai.gpt-oss-20b-1:0 | 128K | $0.084 | $0.36 | — | |||
| nvidia/Riva-Translate-4B-Instruct-v2nvidia/Riva-Translate-4B-Instruct-v2 | NVIDIA |
Not documented | — | — | — | ||
| us-gov.nvidia.nemotron-nano-9b-v2bedrock_converse/us-gov.nvidia.nemotron-nano-9b-v2 | 128K | $0.072 | $0.276 | — |