{"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":731,"limit":100,"offset":0,"updated_at":"2026-09-25T06:13:51.255Z"},"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":"2026-09-25T06:10:57.380Z"},{"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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"inclusionai/ling-3.0-flash-fin:free","display_name":"inclusionAI: Ling 3.0 Flash Fin (free)","description":"Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total.","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"],"tags":["fast"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"inclusionai/ling-3.0-flash-sante:free","display_name":"inclusionAI: Ling 3.0 Flash Sante (free)","description":"Ling 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total.","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"],"tags":["fast"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"nex-agi/nex-n2.5-mini:free","display_name":"Nex AGI: Nex-N2.5-Mini (free)","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,"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","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":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"nex-agi/nex-n2.5-pro:free","display_name":"Nex AGI: Nex-N2.5-Pro (free)","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,"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","vision"],"tags":["flagship","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"nvidia/nemotron-3-super-120b-a12b:free","display_name":"NVIDIA: Nemotron 3 Super (free)","description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.","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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"nvidia/nemotron-3.5-content-safety:free","display_name":"NVIDIA: Nemotron 3.5 Content Safety (free)","description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.","input":0,"cached_input":null,"output":0,"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","vision"],"tags":["vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"poolside/laguna-s-2.1:free","display_name":"Poolside: Laguna S 2.1 (free)","description":"Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1…","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"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"poolside/laguna-xs-2.1:free","display_name":"Poolside: Laguna XS 2.1 (free)","description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step forward from their Laguna XS.2 model (released in April 2026).","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"],"tags":[],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"qwen/qwen3.8-27b:free","display_name":"Qwen: Qwen3.8 27B (free)","description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can…","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","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":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"stealth/space-bunny-alpha","display_name":"Space Bunny Alpha","description":"Space Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support. It delivers adjustable reasoning effort, and a 1M-token context window.","input":0,"cached_input":null,"output":0,"context_window":1000000,"max_output_tokens":524288,"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":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"thinkingmachines/inkling-small:free","display_name":"Thinking Machines: Inkling Small (free)","description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.","input":0,"cached_input":null,"output":0,"context_window":1048576,"max_output_tokens":262144,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision","audio"],"tags":["reasoning","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"thinkingmachines/inkling:free","display_name":"Thinking Machines: Inkling (free)","description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.","input":0,"cached_input":null,"output":0,"context_window":1048576,"max_output_tokens":262144,"long_context_threshold":null,"long_input":null,"long_cached_input":null,"long_output":null,"currency":"USD","modality":["text","vision","audio"],"tags":["reasoning","vision"],"source_url":"https://openrouter.ai/api/v1/models","source_kind":"api","model_type":"general","classification_status":"confirmed","capabilities":null,"updated_at":"2026-09-25T06:13:34.752Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"z-ai/glm-5.2:free","display_name":"Z.ai: GLM 5.2 (free)","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,"cached_input":null,"output":0,"context_window":32768,"max_output_tokens":29491,"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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:49.380Z"},{"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":"2026-09-25T06:11:04.859Z"},{"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":"2026-09-25T06:11:04.859Z"},{"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":"2026-09-25T06:11:04.859Z"},{"provider":"openrouter","provider_name":"OpenRouter","model_id":"ibm-granite/granite-4.0-h-micro","display_name":"IBM: Granite 4.0 Micro","description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM.","input":0.017,"cached_input":null,"output":0.112,"context_window":131000,"max_output_tokens":117900,"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":"2026-09-25T06:13:34.752Z"},{"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":0.018,"cached_input":null,"output":0.09,"context_window":131072,"max_output_tokens":32768,"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":"2026-09-25T06:13:34.752Z"},{"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":0.019,"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":"2026-09-25T06:13:51.255Z"},{"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":0.019,"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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:51.255Z"},{"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":"2026-09-25T06:10:57.380Z"},{"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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:13:34.752Z"},{"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":"2026-09-25T06:12:11.591Z"},{"provider":"deepinfra","provider_name":"DeepInfra","model_id":"ibm-granite/granite-4.2-3b","display_name":"ibm-granite/granite-4.2-3b","description":"Granite-4.2-3B is the compact reasoning model in the Granite 4.2 family. Despite its small parameter count, it delivers strong performance on reasoning-intensive tasks by leveraging built-in