{"generated_at":"2026-10-30T20:16:51Z","updated":"2026-10-24","metrics_url":"https://api.thetoken.dev/public/metrics","counts":{"models":11,"providers":4},"billing":{"topup_fee_rate":0.055,"min_topup_usd":5,"starter_credit_usd":0.5,"privacy_group":"us-eu-hosted","privacy_group_ratio":1},"makers":{"baai":{"name":"BAAI","icon":"BAAI"},"deepseek":{"name":"DeepSeek","icon":"DeepSeek"},"google":{"name":"Google","icon":"Google"},"meta":{"name":"Meta","icon":"Meta"},"moonshot":{"name":"Moonshot AI","icon":"Moonshot"},"openai":{"name":"OpenAI","icon":"OpenAI"},"zai":{"name":"Z.ai","icon":"ZAI"}},"providers":[{"name":"DeepInfra","data_location":"US","us_eu_hosted":true,"models":["moonshotai/kimi-k3","deepseek/deepseek-v4.1-flash","openai/gpt-oss-120b","openai/gpt-oss-20b","baai/bge-m3"]},{"name":"Fireworks AI","data_location":"unstated","us_eu_hosted":false,"models":["moonshotai/kimi-k3","zai-org/glm-5.3","zai-org/glm-5.3-flash"]},{"name":"Novita AI","data_location":"US","us_eu_hosted":true,"models":["moonshotai/kimi-k3","zai-org/glm-5.3","zai-org/glm-5.3-flash","deepseek/deepseek-v4-pro","google/gemma-4-31b-it","google/gemma-4-26b-a4b-it","baai/bge-m3","meta-llama/llama-4-maverick"]},{"name":"Z.ai","data_location":"SG","us_eu_hosted":false,"models":["zai-org/glm-5.3","zai-org/glm-5.3-flash"]}],"models":[{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Moonshot AI's Kimi K3 reasoning model with a context window of about 1M tokens.","family":"kimi","maker":"moonshot","maker_name":"Moonshot AI","type":"reasoning","release_date":"2026-07-16","featured":1,"context_length":1040000,"aliases":["kimi-k3"],"price_usd_per_1m":{"input":3.14,"cached_input":0.32,"output":15.68},"primary_precision":"mxfp4","providers_count":3,"single_provider":false,"us_eu_hosted":true,"capabilities":{"input":["text","image","video"],"output":["text"],"reasoning":true,"reasoning_effort":true,"tools":true,"structured_output":true,"max_output":"1,048,576 (default 131,072)"},"links":{"huggingface":"https://huggingface.co/moonshotai/Kimi-K3","maker":"https://www.kimi.com/blog/kimi-k3"},"facts_sources":["https://www.kimi.com/blog","https://www.kimi.com/blog/kimi-k3","https://platform.kimi.ai/docs/guide/kimi-k3-quickstart","https://huggingface.co/moonshotai/Kimi-K3"],"facts_checked":"2026-10-24","served_by":[{"provider":"DeepInfra","precision":"mxfp4","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://deepinfra.com/pricing","checked":"2026-10-19"},{"provider":"Fireworks AI","precision":"mxfp4","full_precision":true,"data_location":"unstated","us_eu_hosted":false,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-10-19"},{"provider":"Novita AI","precision":"not_stated","full_precision":false,"data_location":"US","us_eu_hosted":true,"source_url":"https://novita.ai/pricing","checked":"2026-10-19"}]},{"id":"zai-org/glm-5.3","name":"GLM-5.3","description":"Z.ai's GLM-5.3 reasoning model with a context window of about 1M tokens.","family":"glm","maker":"zai","maker_name":"Z.ai","type":"reasoning","release_date":"2026-08-18","featured":2,"context_length":1040000,"aliases":["glm-5.3"],"price_usd_per_1m":{"input":1.54,"cached_input":0.29,"output":4.84},"primary_precision":"fp8","providers_count":3,"single_provider":false,"us_eu_hosted":true,"capabilities":{"input":["text"],"output":["text"],"reasoning":true,"reasoning_effort":true,"tools":true,"structured_output":true,"max_output":"128K"},"links":{"huggingface":"https://huggingface.co/zai-org/GLM-5.3","maker":"https://docs.z.ai/guides/llm/glm-5.3"},"facts_sources":["https://docs.z.ai/guides/llm/glm-5.3","https://docs.z.ai/release-notes/new-released","https://huggingface.co/zai-org/GLM-5.3"],"facts_checked":"2026-10-24","served_by":[{"provider":"Fireworks AI","precision":"fp8","full_precision":true,"data_location":"unstated","us_eu_hosted":false,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-10-19"},{"provider":"Novita AI","precision":"fp8","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://novita.ai/pricing","checked":"2026-10-19"},{"provider":"Z.ai","precision":"native","full_precision":true,"data_location":"SG","us_eu_hosted":false,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-10-19"}]},{"id":"zai-org/glm-5.3-flash","name":"GLM-5.3 Flash","description":"Z.ai's fast GLM-5.3 Flash model with image input and a context window of about 1M tokens.","family":"glm","maker":"zai","maker_name":"Z.ai","type":"vision","release_date":"2026-08-26","featured":0,"context_length":1040000,"aliases":["glm-5.3-flash"],"price_usd_per_1m":{"input":0.17,"cached_input":0.033,"output":0.55},"primary_precision":"fp8","providers_count":3,"single_provider":false,"us_eu_hosted":true,"capabilities":{"input":["text","image","video"],"output":["text"],"reasoning":true,"reasoning_effort":true,"tools":true,"structured_output":true,"max_output":"128K"},"links":{"huggingface":"https://huggingface.co/zai-org/GLM-5.3-Flash","maker":"https://docs.z.ai/guides/llm/glm-5.3-flash"},"facts_sources":["https://docs.z.ai/guides/llm/glm-5.3-flash","https://docs.z.ai/release-notes/new-released","https://huggingface.co/zai-org/GLM-5.3-Flash"],"facts_checked":"2026-10-24","served_by":[{"provider":"Novita AI","precision":"fp8","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://novita.ai/pricing","checked":"2026-10-19"},{"provider":"Z.ai","precision":"native","full_precision":true,"data_location":"SG","us_eu_hosted":false,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-10-19"},{"provider":"Fireworks AI","precision":"not_stated","full_precision":false,"data_location":"unstated","us_eu_hosted":false,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-10-19"}]},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro, DeepSeek's large reasoning model, with a 1M-token context window.","family":"deepseek","maker":"deepseek","maker_name":"DeepSeek","type":"reasoning","release_date":"2026-08-13","featured":3,"context_length":1048576,"aliases":["deepseek-v4-pro"],"price_usd_per_1m":{"input":1.46,"cached_input":0.049,"output":4.36},"primary_precision":"fp8","providers_count":1,"single_provider":true,"us_eu_hosted":true,"capabilities":{"input":["text"],"output":["text"],"reasoning":true,"reasoning_effort":true,"tools":true,"structured_output":true,"max_output":"384K"},"links":{"huggingface":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","maker":"https://api-docs.deepseek.com/news/news260813"},"facts_sources":["https://api-docs.deepseek.com/news/news260813","https://api-docs.deepseek.com/quick_start/pricing","https://api-docs.deepseek.com/guides/thinking_mode","https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"],"facts_checked":"2026-10-24","served_by":[{"provider":"Novita AI","precision":"fp8","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://novita.ai/pricing","checked":"2026-10-19"}]},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash, a fast and low-cost reasoning model with a 1M-token context window.","family":"deepseek","maker":"deepseek","maker_name":"DeepSeek","type":"reasoning","release_date":"2026-09-10","featured":4,"context_length":1000000,"aliases":["deepseek-v4.1-flash"],"price_usd_per_1m":{"input":0.22,"cached_input":0.007,"output":0.66},"primary_precision":"fp8","providers_count":1,"single_provider":true,"us_eu_hosted":true,"capabilities":{"input":["text","image"],"output":["text"],"reasoning":true,"reasoning_effort":true,"tools":true,"structured_output":true,"max_output":"384K"},"links":{"huggingface":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash","maker":"https://api-docs.deepseek.com/news/news260910"},"facts_sources":["https://api-docs.deepseek.com/news/news260910","https://api-docs.deepseek.com/quick_start/pricing","https://api-docs.deepseek.com/guides/thinking_mode","https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"],"facts_checked":"2026-10-24","served_by":[{"provider":"DeepInfra","precision":"fp8","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://deepinfra.com/pricing","checked":"2026-10-19"}]},{"id":"openai/gpt-oss-120b","name":"gpt-oss-120b","description":"OpenAI's open-weight gpt-oss-120b reasoning model with a 131K-token context window.","family":"gpt-oss","maker":"openai","maker_name":"OpenAI","type":"reasoning","release_date":"2025-08-05","featured":5,"context_length":131072,"aliases":["gpt-oss-120b"],"price_usd_per_1m":{"input":0.041,"cached_input":null,"output":0.19},"primary_precision":"bf16","providers_count":1,"single_provider":true,"us_eu_hosted":true,"capabilities":{"input":["text"],"output":["text"],"reasoning":true,"reasoning_effort":true,"tools":true,"structured_output":true,"max_output":"131,072"},"links":{"huggingface":"https://huggingface.co/openai/gpt-oss-120b","maker":"https://developers.openai.com/api/docs/models/gpt-oss-120b"},"facts_sources":["https://developers.openai.com/api/docs/models/gpt-oss-120b","https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf","https://huggingface.co/openai/gpt-oss-120b"],"facts_checked":"2026-10-24","served_by":[{"provider":"DeepInfra","precision":"bf16","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://deepinfra.com/pricing","checked":"2026-10-19"}]},{"id":"openai/gpt-oss-20b","name":"gpt-oss-20b","description":"OpenAI's open-weight gpt-oss-20b, a smaller reasoning model with a 131K-token context window.","family":"gpt-oss","maker":"openai","maker_name":"OpenAI","type":"reasoning","release_date":"2025-08-05","featured":0,"context_length":131072,"aliases":["gpt-oss-20b"],"price_usd_per_1m":{"input":0.033,"cached_input":null,"output":0.16},"primary_precision":"bf16","providers_count":1,"single_provider":true,"us_eu_hosted":true,"capabilities":{"input":["text"],"output":["text"],"reasoning":true,"reasoning_effort":true,"tools":true,"structured_output":true,"max_output":"131,072"},"links":{"huggingface":"https://huggingface.co/openai/gpt-oss-20b","maker":"https://developers.openai.com/api/docs/models/gpt-oss-20b"},"facts_sources":["https://developers.openai.com/api/docs/models/gpt-oss-20b","https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf","https://huggingface.co/openai/gpt-oss-20b"],"facts_checked":"2026-10-24","served_by":[{"provider":"DeepInfra","precision":"bf16","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://deepinfra.com/pricing","checked":"2026-10-19"}]},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B","description":"Google's open Gemma 4 31B model with image input and a 262K-token context window.","family":"gemma","maker":"google","maker_name":"Google","type":"vision","release_date":"2026-04-02","featured":6,"context_length":262144,"aliases":["gemma-4-31b-it"],"price_usd_per_1m":{"input":0.16,"cached_input":null,"output":0.44},"primary_precision":"bf16","providers_count":1,"single_provider":true,"us_eu_hosted":true,"capabilities":{"input":["text","image","video"],"output":["text"],"reasoning":true,"reasoning_effort":false,"tools":true,"structured_output":true,"max_output":null},"links":{"huggingface":"https://huggingface.co/google/gemma-4-31B-it","maker":"https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/"},"facts_sources":["https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/","https://ai.google.dev/gemma/docs/core","https://huggingface.co/google/gemma-4-31B-it"],"facts_checked":"2026-10-24","served_by":[{"provider":"Novita AI","precision":"bf16","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://novita.ai/pricing","checked":"2026-10-19"}]},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","description":"Google's open Gemma 4 26B A4B mixture-of-experts model (about 4B active parameters) with image input and a 262K-token context window.","family":"gemma","maker":"google","maker_name":"Google","type":"vision","release_date":"2026-04-02","featured":0,"context_length":262144,"aliases":["gemma-4-26b-a4b-it"],"price_usd_per_1m":{"input":0.15,"cached_input":null,"output":0.44},"primary_precision":"bf16","providers_count":1,"single_provider":true,"us_eu_hosted":true,"capabilities":{"input":["text","image","video"],"output":["text"],"reasoning":true,"reasoning_effort":false,"tools":true,"structured_output":true,"max_output":null},"links":{"huggingface":"https://huggingface.co/google/gemma-4-26B-A4B-it","maker":"https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/"},"facts_sources":["https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/","https://ai.google.dev/gemma/docs/core","https://huggingface.co/google/gemma-4-26B-A4B-it"],"facts_checked":"2026-10-24","served_by":[{"provider":"Novita AI","precision":"bf16","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://novita.ai/pricing","checked":"2026-10-19"}]},{"id":"baai/bge-m3","name":"BGE-M3","description":"BAAI's BGE-M3 multilingual text embedding model with an 8K-token input limit and 1024-dimension vectors.","family":"bge","maker":"baai","maker_name":"BAAI","type":"embeddings","release_date":"2024-01-30","featured":0,"context_length":8192,"aliases":["bge-m3"],"price_usd_per_1m":{"input":0.011,"cached_input":null,"output":0},"primary_precision":"fp32","providers_count":2,"single_provider":false,"us_eu_hosted":true,"capabilities":{"input":["text"],"output":["embedding"],"reasoning":false,"reasoning_effort":false,"tools":null,"structured_output":null,"max_output":null},"links":{"huggingface":"https://huggingface.co/BAAI/bge-m3","maker":"https://bge-model.com/bge/bge_m3.html"},"facts_sources":["https://bge-model.com/bge/bge_m3.html","https://github.com/FlagOpen/FlagEmbedding","https://huggingface.co/BAAI/bge-m3"],"facts_checked":"2026-10-24","served_by":[{"provider":"DeepInfra","precision":"fp32","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://deepinfra.com/pricing","checked":"2026-10-19"},{"provider":"Novita AI","precision":"not_stated","full_precision":false,"data_location":"US","us_eu_hosted":true,"source_url":"https://novita.ai/pricing","checked":"2026-10-19"}]},{"id":"meta-llama/llama-4-maverick","name":"Llama 4 Maverick","description":"Meta's Llama 4 Maverick mixture-of-experts model with image input and a 1M-token context window.","family":"llama","maker":"meta","maker_name":"Meta","type":"vision","release_date":"2025-04-05","featured":0,"context_length":1048576,"aliases":["llama-4-maverick"],"price_usd_per_1m":{"input":0.3,"cached_input":null,"output":0.94},"primary_precision":"fp8","providers_count":1,"single_provider":true,"us_eu_hosted":true,"capabilities":{"input":["text","image"],"output":["text"],"reasoning":false,"reasoning_effort":false,"tools":false,"structured_output":null,"max_output":null},"links":{"huggingface":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct","maker":"https://ai.meta.com/blog/llama-4-multimodal-intelligence/"},"facts_sources":["https://ai.meta.com/blog/llama-4-multimodal-intelligence/","https://dev.meta.ai/llama/docs/model-cards-and-prompt-formats/llama4/","https://github.com/meta-llama/llama-models/blob/main/models/llama4/MODEL_CARD.md"],"facts_checked":"2026-10-24","served_by":[{"provider":"Novita AI","precision":"fp8","full_precision":true,"data_location":"US","us_eu_hosted":true,"source_url":"https://novita.ai/pricing","checked":"2026-10-19"}]}]}