{"meta":{"version":"v1","count":100,"attribution":{"required":true,"text":"Pricing data from CostOfToken","url":"https://www.costoftoken.com","html":"Pricing data from CostOfToken","license":"https://opendatacommons.org/licenses/by/1-0/","terms":"https://www.costoftoken.com/api-docs#attribution"},"total":698,"limit":100,"offset":0,"updated_at":"2026-11-10T06:12:03.491Z"},"data":[{"provider":"openai","provider_name":"OpenAI","model_id":"omni-moderation-latest","display_name":"omni-moderation-latest","description":null,"input":0,"cached_input":null,"output":null,"context_window":null,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://platform.openai.com/docs/pricing","source_kind":"scrape","model_type":"moderation","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:10:57.471Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"cohere/north-mini-code:free","display_name":"Cohere: North Mini Code (free)","description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is…","input":0,"cached_input":null,"output":0,"context_window":256000,"max_output_tokens":64000,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["coding","fast"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"dots-studio/dots-3-note-preview:free","display_name":"Dots Studio: Dots3-Note Preview (free)","description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total.","input":0,"cached_input":null,"output":0,"context_window":512000,"max_output_tokens":460800,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["preview","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"google/gemma-4-26b-a4b-it:free","display_name":"Google: Gemma 4 26B A4B (free)","description":"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…","input":0,"cached_input":null,"output":0,"context_window":262144,"max_output_tokens":32768,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision","video"],"tags":["vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"google/gemma-4-31b-it:free","display_name":"Google: Gemma 4 31B (free)","description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.","input":0,"cached_input":null,"output":0,"context_window":262144,"max_output_tokens":32768,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision","video"],"tags":["vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"google/lyria-3-clip-preview","display_name":"Google: Lyria 3 Clip Preview","description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API.","input":0,"cached_input":null,"output":0,"context_window":1048576,"max_output_tokens":65536,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision","audio"],"tags":["preview","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"google/lyria-3-pro-preview","display_name":"Google: Lyria 3 Pro Preview","description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API.","input":0,"cached_input":null,"output":0,"context_window":1048576,"max_output_tokens":65536,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision","audio"],"tags":["flagship","preview","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"liquid/lfm-2.5-2.6b:free","display_name":"LiquidAI: LFM2.5-2.6B (free)","description":"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.","input":0,"cached_input":null,"output":0,"context_window":65536,"max_output_tokens":8192,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"liquid/lfm-3-1.7b:free","display_name":"LiquidAI: LFM3-1.7B (free)","description":"A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers.","input":0,"cached_input":null,"output":0,"context_window":262144,"max_output_tokens":8192,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","display_name":"NVIDIA: Nemotron 3 Nano Omni (free)","description":"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.","input":0,"cached_input":null,"output":0,"context_window":256000,"max_output_tokens":65536,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision","audio","video"],"tags":["fast","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"nvidia/nemotron-3-ultra-550b-a55b:free","display_name":"NVIDIA: Nemotron 3 Ultra (free)","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).","input":0,"cached_input":null,"output":0,"context_window":1000000,"max_output_tokens":65536,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["flagship"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"nvidia/nemotron-3.5-lightning:free","display_name":"NVIDIA: Nemotron 3.5 Lightning (free)","description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.","input":0,"cached_input":null,"output":0,"context_window":1000000,"max_output_tokens":65536,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"nvidia/nemotron-3.5-super-vl:free","display_name":"NVIDIA: Nemotron 3.5 Super VL (free)","description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.","input":0,"cached_input":null,"output":0,"context_window":1000000,"max_output_tokens":131072,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision","video"],"tags":["vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"openrouter/free","display_name":"Free Models Router","description":"The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter.","input":0,"cached_input":null,"output":0,"context_window":200000,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"recursive/flint-v1.0:free","display_name":"Recursive: Flint (free)","description":"Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents.","input":0,"cached_input":null,"output":0,"context_window":262144,"max_output_tokens":235929,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"thinkingmachines/inkling-2-small:free","display_name":"Thinking Machines: Inkling 2 Small (free)","description":"Inkling 2 Small is a multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total.","input":0,"cached_input":null,"output":0,"context_window":1048576,"max_output_tokens":131072,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["reasoning","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"xingchen-agi/xing4.0-29b-a4b:free","display_name":"XingChen: Xing4.0 29B A4B (free)","description":"Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series.","input":0,"cached_input":null,"output":0,"context_window":262144,"max_output_tokens":235929,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"together","provider_name":"Together AI","model_id":"ternary-bonsai-27b","display_name":"Ternary Bonsai 27B","description":null,"input":0,"cached_input":null,"output":0,"context_window":null,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://www.together.ai/pricing","source_kind":"scrape","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:01.267Z"},{"provider":"zhipu","provider_name":"Zhipu AI (GLM)","model_id":"glm-4.5-flash","display_name":"GLM-4.5-Flash","description":null,"input":0,"cached_input":0,"output":0,"context_window":null,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://docs.z.ai/guides/overview/pricing","source_kind":"scrape","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-10-20T06:11:04.719Z"},{"provider":"zhipu","provider_name":"Zhipu AI (GLM)","model_id":"glm-4.6v-flash","display_name":"GLM-4.6V-Flash","description":null,"input":0,"cached_input":0,"output":0,"context_window":null,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://docs.z.ai/guides/overview/pricing","source_kind":"scrape","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-10-20T06:11:04.719Z"},{"provider":"zhipu","provider_name":"Zhipu AI (GLM)","model_id":"glm-4.7-flash","display_name":"GLM-4.7-Flash","description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task…","input":0,"cached_input":0,"output":0,"context_window":200000,"max_output_tokens":117964,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://docs.z.ai/guides/overview/pricing","source_kind":"scrape","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-10-20T06:11:04.719Z"},{"provider":"deepseek","provider_name":"DeepSeek","model_id":"deepseek-flash-latest","display_name":"DeepSeek Flash Latest","description":"This model always redirects to the latest model in the DeepSeek Flash family.","input":0.006,"cached_input":0.005,"output":0.5,"context_window":1048576,"max_output_tokens":943718,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["fast","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:15.437Z"},{"provider":"deepseek","provider_name":"DeepSeek","model_id":"deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","input":0.006,"cached_input":0.005,"output":0.5,"context_window":1048576,"max_output_tokens":943718,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["fast","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:15.437Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek: DeepSeek V4.1 Flash 1017","description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","input":0.006,"cached_input":0.005,"output":0.5,"context_window":1048576,"max_output_tokens":943718,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["fast","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"z-ai/glm-5.2","display_name":"Z.ai: GLM 5.2","description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software…","input":0.006,"cached_input":0.005,"output":6.8,"context_window":1048576,"max_output_tokens":943718,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"inclusionai/ling-3.0-tiny","display_name":"inclusionAI: Ling 3.0 Tiny","description":"Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total.","input":0.015,"cached_input":0.003,"output":0.045,"context_window":262144,"max_output_tokens":250000,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","display_name":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","description":"Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes","input":0.02,"cached_input":null,"output":0.04,"context_window":131072,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"openai","provider_name":"OpenAI","model_id":"text-embedding-3-small","display_name":"text-embedding-3-small","description":null,"input":0.02,"cached_input":null,"output":null,"context_window":null,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://platform.openai.com/docs/pricing","source_kind":"scrape","model_type":"embedding","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:10:57.471Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"meta-llama/llama-3.1-8b-instruct","display_name":"Meta: Llama 3.1 8B Instruct","description":"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.","input":0.02,"cached_input":null,"output":0.04,"context_window":131072,"max_output_tokens":16384,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"inclusionai/ling-3.0-flash","display_name":"inclusionAI: Ling 3.0 Flash","description":"Ling-3.0-flash is a 124B-parameter Mixture-of-Experts (MoE) model , with approximately 5.1B parameters activated per token .","input":0.021,"cached_input":0.0042,"output":0.063,"context_window":262144,"max_output_tokens":32768,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"nex-agi/nex-n2.5-mini","display_name":"Nex AGI: Nex-N2.5-Mini","description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement…","input":0.025,"cached_input":0.0025,"output":0.1,"context_window":262144,"max_output_tokens":235929,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["fast","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"meta-llama/llama-3.2-1b-instruct","display_name":"Meta: Llama 3.2 1B Instruct","description":"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.","input":0.027,"cached_input":null,"output":0.201,"context_window":60000,"max_output_tokens":54000,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"mistralai/Mistral-Nemo-Instruct-2407","display_name":"mistralai/Mistral-Nemo-Instruct-2407","description":"12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.","input":0.029,"cached_input":null,"output":0.03,"context_window":131072,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"mistralai/mistral-nemo","display_name":"Mistral: Mistral Nemo","description":"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…","input":0.029,"cached_input":null,"output":0.03,"context_window":131072,"max_output_tokens":16384,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"alibaba","provider_name":"Alibaba (Qwen)","model_id":"qwen3.7-flash","display_name":"Qwen3.7 Flash","description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and…","input":0.03,"cached_input":0.006,"output":0.13,"context_window":1000000,"max_output_tokens":65536,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision","video"],"tags":["fast","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:20.342Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"openai/gpt-oss-20b","display_name":"openai/gpt-oss-20b","description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference.","input":0.03,"cached_input":null,"output":0.14,"context_window":131072,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"inference-net/schematron-v2-turbo","display_name":"Inference.net: Schematron V2 Turbo","description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads.","input":0.03,"cached_input":0.03,"output":0.15,"context_window":128000,"max_output_tokens":8192,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"openai/gpt-oss-20b","display_name":"OpenAI: gpt-oss-20b","description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized…","input":0.03,"cached_input":0.03,"output":0.13,"context_window":131072,"max_output_tokens":117964,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"qwen/qwen3.7-flash","display_name":"Qwen: Qwen3.7 Flash","description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and…","input":0.03,"cached_input":0.006,"output":0.13,"context_window":1000000,"max_output_tokens":65536,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision","video"],"tags":["fast","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"zhipu","provider_name":"Zhipu AI (GLM)","model_id":"glm-ocr","display_name":"GLM-OCR","description":null,"input":0.03,"cached_input":null,"output":0.03,"context_window":null,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://docs.z.ai/guides/overview/pricing","source_kind":"scrape","model_type":"ocr","classification_status":"confirmed","capabilities":null,"updated_at":"2026-10-20T06:11:04.719Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"amazon/nova-micro-v1","display_name":"Amazon: Nova Micro 1.0","description":"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.","input":0.035,"cached_input":null,"output":0.14,"context_window":128000,"max_output_tokens":5120,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"openai/gpt-oss-120b","display_name":"openai/gpt-oss-120b","description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","input":0.037,"cached_input":null,"output":0.17,"context_window":131072,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"cohere/command-r7b-12-2024","display_name":"Cohere: Command R7B (12-2024)","description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex…","input":0.0375,"cached_input":null,"output":0.15,"context_window":128000,"max_output_tokens":4000,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"Cloudflare/clef-flash","display_name":"Cloudflare/clef-flash","description":"Clef-Flash is a 9B multimodal model that turns a state and a schema of typed questions into decisions.","input":0.038,"cached_input":null,"output":0,"context_window":24576,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"nace-ai/drex-v1.5","display_name":"nace-ai/drex-v1.5","description":"Drex v1.5 is a 9B decision model from Nace.AI. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for every option in a single forward pass, with no text generation.","input":0.04,"cached_input":null,"output":0,"context_window":131072,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"Sao10K/L3-8B-Lunaris-v1-Turbo","display_name":"Sao10K/L3-8B-Lunaris-v1-Turbo","description":null,"input":0.04,"cached_input":null,"output":0.05,"context_window":8192,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"sao10k/l3-lunaris-8b","display_name":"Sao10K: Llama 3 8B Lunaris","description":"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…","input":0.04,"cached_input":null,"output":0.05,"context_window":8192,"max_output_tokens":7372,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"scaledown/extract","display_name":"ScaleDown: Extract","description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through provider.options.scaledown.entities , and…","input":0.04,"cached_input":null,"output":0,"context_window":1000000,"max_output_tokens":900000,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"scaledown/summarize","display_name":"ScaleDown: Summarize","description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited…","input":0.04,"cached_input":null,"output":0,"context_window":1000000,"max_output_tokens":4000,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"together","provider_name":"Together AI","model_id":"tev1-4b-experimental","display_name":"Tev1 4B Experimental","description":null,"input":0.04,"cached_input":null,"output":0,"context_window":null,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://www.together.ai/pricing","source_kind":"scrape","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:01.267Z"},{"provider":"zhipu","provider_name":"Zhipu AI (GLM)","model_id":"glm-4.6v-flashx","display_name":"GLM-4.6V-FlashX","description":null,"input":0.04,"cached_input":0.004,"output":0.4,"context_window":null,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://docs.z.ai/guides/overview/pricing","source_kind":"scrape","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-10-20T06:11:04.719Z"},{"provider":"deepseek","provider_name":"DeepSeek","model_id":"deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","input":0.0434,"cached_input":0.035,"output":0.3,"context_window":1048576,"max_output_tokens":943718,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:15.437Z"},{"provider":"deepseek","provider_name":"DeepSeek","model_id":"deepseek-v4-flash-latest","display_name":"DeepSeek V4 Flash Latest","description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","input":0.0434,"cached_input":0.035,"output":0.3,"context_window":1048576,"max_output_tokens":943718,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:15.437Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek: DeepSeek V4 Flash 0731","description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","input":0.0434,"cached_input":0.035,"output":0.3,"context_window":1048576,"max_output_tokens":943718,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"tencent/hy-mt2-1.8b","display_name":"Tencent: Hy-MT2-1.8B","description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and…","input":0.044,"cached_input":null,"output":0.177,"context_window":8192,"max_output_tokens":4096,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"inclusionai/ling-3.1-flash","display_name":"inclusionAI: Ling 3.1 Flash","description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","input":0.045,"cached_input":0.009,"output":0.135,"context_window":1000000,"max_output_tokens":262144,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"google/gemma-3-12b-it","display_name":"google/gemma-3-12b-it","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.","input":0.05,"cached_input":null,"output":0.15,"context_window":131072,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"google/gemma-3-4b-it","display_name":"google/gemma-3-4b-it","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.","input":0.05,"cached_input":null,"output":0.1,"context_window":131072,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"mistralai/Mistral-Small-24B-Instruct-2501","display_name":"mistralai/Mistral-Small-24B-Instruct-2501","description":"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.","input":0.05,"cached_input":null,"output":0.08,"context_window":32768,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"openai","provider_name":"OpenAI","model_id":"gpt-5-nano","display_name":"gpt-5-nano","description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.","input":0.05,"cached_input":0.005,"output":0.4,"context_window":400000,"max_output_tokens":128000,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast","flagship"],"source_url":"https://platform.openai.com/docs/pricing","source_kind":"scrape","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:10:57.471Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"google/gemma-3-12b-it","display_name":"Google: Gemma 3 12B","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat…","input":0.05,"cached_input":null,"output":0.15,"context_window":131072,"max_output_tokens":16384,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"google/gemma-3-4b-it","display_name":"Google: Gemma 3 4B","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat…","input":0.05,"cached_input":null,"output":0.1,"context_window":131072,"max_output_tokens":16384,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"inference-net/schematron-v2-small","display_name":"Inference.net: Schematron V2 Small","description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages.","input":0.05,"cached_input":0.05,"output":0.23,"context_window":128000,"max_output_tokens":8192,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"liquid/lfm-2.5-24b-a2b","display_name":"LiquidAI: LFM2.5-24B-A2B","description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools.","input":0.05,"cached_input":0.025,"output":0.7,"context_window":128000,"max_output_tokens":8192,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"meta-llama/llama-3.2-3b-instruct","display_name":"Meta: Llama 3.2 3B Instruct","description":"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.","input":0.05,"cached_input":null,"output":0.33,"context_window":131072,"max_output_tokens":117964,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"mistralai/mistral-small-24b-instruct-2501","display_name":"Mistral: Mistral Small 3","description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.","input":0.05,"cached_input":null,"output":0.08,"context_window":32768,"max_output_tokens":16384,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"openai/gpt-5-nano","display_name":"OpenAI: GPT-5 Nano","description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.","input":0.05,"cached_input":0.005,"output":0.4,"context_window":400000,"max_output_tokens":128000,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["fast","flagship","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"particle-ai/particle-1","display_name":"Particle AI: Particle-1","description":"Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and…","input":0.05,"cached_input":0.003,"output":0.5,"context_window":1048576,"max_output_tokens":131072,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"upstage/solar-mini4","display_name":"Upstage: Solar Mini 4","description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window.","input":0.05,"cached_input":0.005,"output":0.2,"context_window":524288,"max_output_tokens":131072,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"deepseek","provider_name":"DeepSeek","model_id":"deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.","input":0.051,"cached_input":0.018,"output":0.567,"context_window":1048576,"max_output_tokens":943718,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["fast","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:15.437Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek: DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.","input":0.051,"cached_input":0.018,"output":0.567,"context_window":1048576,"max_output_tokens":943718,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision"],"tags":["fast","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:11:46.204Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","display_name":"deepseek-ai/DeepSeek-V4-Flash-0731","description":"DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities.","input":0.06,"cached_input":0.015,"output":0.18,"context_window":1048576,"max_output_tokens":null,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text"],"tags":["fast"],"source_url":"https://deepinfra.com/pricing","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-11-10T06:12:03.491Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"ibm-granite/granite-4.2-8b","display_name":"ibm-granite/granite-4.2-8b","description":"Granite-4.2-8B is the mid-size reasoning model in the Granite 4.2 family. It delivers strong performance on reasoning-intensive tasks by leveraging built-in