# OpenRouter > Access Multiple LLMs via OpenRouter API Source: https://tokenmojo.ai/providers/openrouter ## Stats - Models published: 59 - Average quality: 60.5 - Median speed: 30.4 tok/s - Average reliability: 63.1% - Lowest output price: $0.00 per 1M tokens - Total samples: 7137 ## Description OpenRouter provides a unified interface for various large language models. TokenMojo integrates this API to allow users to compare performance and pricing across different providers. ## Models - [aion-3.0](https://tokenmojo.ai/models/openrouter/aion-labs-aion-3-0) - [aion-3.0-mini](https://tokenmojo.ai/models/openrouter/aion-labs-aion-3-0-mini) - [auto-beta](https://tokenmojo.ai/models/openrouter/openrouter-auto-beta) - [claude-fable-5](https://tokenmojo.ai/models/openrouter/anthropic-claude-fable-5) - [claude-fable-latest](https://tokenmojo.ai/models/openrouter/anthropic-claude-fable-latest) - [claude-opus-5](https://tokenmojo.ai/models/openrouter/anthropic-claude-opus-5) - [claude-opus-5-fast](https://tokenmojo.ai/models/openrouter/anthropic-claude-opus-5-fast) - [claude-sonnet-5](https://tokenmojo.ai/models/openrouter/anthropic-claude-sonnet-5) - [deepseek-chat](https://tokenmojo.ai/models/openrouter/deepseek-chat): DeepSeek Chat via OpenRouter: 131K context, 16K max output, JSON mode, $0.2288/Mtok input pricing. - [deepseek-v3.2](https://tokenmojo.ai/models/openrouter/deepseek-v3-2): DeepSeek V3.2 on OpenRouter: 131K context, 65K max output, reasoning, and JSON mode support. - [deepseek-v3.2-speciale](https://tokenmojo.ai/models/openrouter/deepseek-v3-2-speciale): DeepSeek V3.2 Speciale via OpenRouter features 163840 token context, reasoning, and JSON mode support. - [deepseek-v4-flash](https://tokenmojo.ai/models/openrouter/deepseek-v4-flash): DeepSeek V4 Flash delivers 1M context window, reasoning capabilities, and JSON mode via OpenRouter. - [deepseek-v4-pro](https://tokenmojo.ai/models/openrouter/deepseek-v4-pro): DeepSeek V4 Pro delivers 1M context window with reasoning and JSON mode capabilities. - [dolphin-mistral-24b-venice-edition](https://tokenmojo.ai/models/openrouter/cognitivecomputations-dolphin-mistral-24b-venice-edition) - [fugu-ultra](https://tokenmojo.ai/models/openrouter/sakana-fugu-ultra) - [fusion](https://tokenmojo.ai/models/openrouter/openrouter-fusion): OpenRouter Fusion model featuring 128000 token context window - [gemini-3.5-flash-lite](https://tokenmojo.ai/models/openrouter/google-gemini-3-5-flash-lite) - [gemini-3.6-flash](https://tokenmojo.ai/models/openrouter/google-gemini-3-6-flash) - [gemma-4-26b-a4b-it](https://tokenmojo.ai/models/openrouter/gemma-4-26b-a4b-it): Google Gemma 4 26B IT: 262K context, vision, reasoning, and JSON mode support on OpenRouter. - [gemma-4-31b-it](https://tokenmojo.ai/models/openrouter/gemma-4-31b-it): Google Gemma 4 31B IT via OpenRouter offers 262K context, vision, reasoning, and JSON mode capabilities. - [glm-5.2](https://tokenmojo.ai/models/openrouter/z-ai-glm-5-2) - [gpt-4.1](https://tokenmojo.ai/models/openrouter/gpt-4-1): OpenAI GPT-4.1 via OpenRouter with 1M+ context window and vision support - [gpt-4.1-mini](https://tokenmojo.ai/models/openrouter/gpt-4-1-mini): OpenAI GPT-4.1 Mini: 1M context window, vision support, and structured JSON output mode. - [gpt-4.1-nano](https://tokenmojo.ai/models/openrouter/gpt-4-1-nano): OpenAI GPT-4.1 Nano delivers 1M token context window with vision and JSON mode capabilities. - [gpt-5.6-luna](https://tokenmojo.ai/models/openrouter/openai-gpt-5-6-luna) - [gpt-5.6-luna-pro](https://tokenmojo.ai/models/openrouter/openai-gpt-5-6-luna-pro) - [gpt-5.6-sol](https://tokenmojo.ai/models/openrouter/openai-gpt-5-6-sol) - [gpt-5.6-sol-pro](https://tokenmojo.ai/models/openrouter/openai-gpt-5-6-sol-pro) - [gpt-5.6-terra](https://tokenmojo.ai/models/openrouter/openai-gpt-5-6-terra) - [gpt-5.6-terra-pro](https://tokenmojo.ai/models/openrouter/openai-gpt-5-6-terra-pro) - [grok-4.5](https://tokenmojo.ai/models/openrouter/x-ai-grok-4-5) - [grok-latest](https://tokenmojo.ai/models/openrouter/x-ai-grok-latest) - [hy3](https://tokenmojo.ai/models/openrouter/tencent-hy3) - [inkling](https://tokenmojo.ai/models/openrouter/thinkingmachines-inkling) - [kat-coder-air-v2.5](https://tokenmojo.ai/models/openrouter/kwaipilot-kat-coder-air-v2-5) - [kat-coder-pro-v2.5](https://tokenmojo.ai/models/openrouter/kwaipilot-kat-coder-pro-v2-5) - [kimi-k2.5](https://tokenmojo.ai/models/openrouter/kimi-k2-5): Moonshot AI Kimi K2.5: 262144 token context window, vision, reasoning, and JSON mode via OpenRouter. - [kimi-k2.6](https://tokenmojo.ai/models/openrouter/kimi-k2-6): Moonshot AI Kimi K2.6 features a 262K context window, vision, reasoning, and JSON mode capabilities. - [kimi-k2.7-code](https://tokenmojo.ai/models/openrouter/moonshotai-kimi-k2-7-code) - [kimi-k3](https://tokenmojo.ai/models/openrouter/moonshotai-kimi-k3) - [laguna-m.1](https://tokenmojo.ai/models/openrouter/poolside-laguna-m-1) - [laguna-s-2.1](https://tokenmojo.ai/models/openrouter/poolside-laguna-s-2-1) - [laguna-s-2.1:free](https://tokenmojo.ai/models/openrouter/poolside-laguna-s-2-1-free) - [laguna-xs-2.1](https://tokenmojo.ai/models/openrouter/poolside-laguna-xs-2-1) - [laguna-xs-2.1:free](https://tokenmojo.ai/models/openrouter/poolside-laguna-xs-2-1-free) - [ling-3.0-flash:free](https://tokenmojo.ai/models/openrouter/inclusionai-ling-3-0-flash-free) - [llama-4-maverick](https://tokenmojo.ai/models/openrouter/llama-4-maverick): Meta Llama 4 Maverick: 1M context window, vision support, and JSON mode via OpenRouter. - [llama-4-scout](https://tokenmojo.ai/models/openrouter/llama-4-scout): Meta Llama 4 Scout via OpenRouter: 10M context window, vision, and JSON mode support. - [longcat-2.0](https://tokenmojo.ai/models/openrouter/meituan-longcat-2-0) - [minimax-m2.5](https://tokenmojo.ai/models/openrouter/minimax-m2-5): Minimax M2.5 on OpenRouter: 204K context, 196K max output, reasoning, and JSON mode support. - [minimax-m2.7](https://tokenmojo.ai/models/openrouter/minimax-m2-7): Minimax M2.7 on OpenRouter: 204K context, 131K max output, reasoning, and JSON mode support. - [muse-spark-1.1](https://tokenmojo.ai/models/openrouter/meta-muse-spark-1-1) - [nemotron-3.5-content-safety:free](https://tokenmojo.ai/models/openrouter/nvidia-nemotron-3-5-content-safety-free) - [nemotron-3-ultra-550b-a55b](https://tokenmojo.ai/models/openrouter/nvidia-nemotron-3-ultra-550b-a55b) - [nemotron-3-ultra-550b-a55b:free](https://tokenmojo.ai/models/openrouter/nvidia-nemotron-3-ultra-550b-a55b-free) - [nex-n2-mini](https://tokenmojo.ai/models/openrouter/nex-agi-nex-n2-mini) - [nex-n2-pro](https://tokenmojo.ai/models/openrouter/nex-agi-nex-n2-pro) - [north-mini-code:free](https://tokenmojo.ai/models/openrouter/cohere-north-mini-code-free) - [qwen3.7-plus](https://tokenmojo.ai/models/openrouter/qwen-qwen3-7-plus)