GET
/v1/changes?type=model.updated&cursor=MTc5MzI4ODE0NzoxNjg2NjUwMC1kNmY5LTQ4OGMtOGI5Yi05ZDJmMWM1OTdiYWE%3D
Accept:
count 50order newest firstpage size 50
| when | type | summary | provider |
|---|---|---|---|
| 18d ago | model.updated | reasoning {…} → null reasoningSource reasoning → silent requestMap.thinking {…} → null | mistral |
| 18d ago | model.updated | deprecated true → false pricing.tables.rate.base.cache_read_tokens $0.14/M → $0.07/M pricing.tables.rate.base.input_tokens $1.36/M → $0.7/M pricing.tables.rate.base.output_tokens $4.18/M → $2.1/M +3 more | mistral |
| 18d ago | model.updated | reasoning {…} → null reasoningSource reasoning → silent requestMap.thinking {…} → null | mistral |
| 18d ago | model.updated | capabilities.response_format true → — capabilities.structured_outputs true → false | huggingface |
| 18d ago | model.updated | capabilities.response_format true → — capabilities.structured_outputs true → false pricing.tables.rate.base.input_tokens $0.75/M → $0.8/M pricing.tables.rate.base.output_tokens $3.5/M → $3.4/M | huggingface |
| 18d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.0740805/M → $0.0739355/M pricing.tables.rate.base.input_tokens $0.888966/M → $0.887226/M pricing.tables.rate.base.output_tokens $1.77793/M → $1.77445/M | openrouter |
| 18d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.14/M → $0.07/M pricing.tables.rate.base.input_tokens $1.36/M → $0.7/M pricing.tables.rate.base.output_tokens $4.18/M → $2.1/M | vercel |
| 18d ago | model.updated | capabilities.response_format true → — capabilities.structured_outputs true → false contextWindow 202752 → 204800 pricing.tables.rate.base.input_tokens $0.5/M → $0.55/M +1 more | huggingface |
| 18d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.074356/M → $0.0740805/M pricing.tables.rate.base.input_tokens $0.892272/M → $0.888966/M pricing.tables.rate.base.output_tokens $1.78454/M → $1.77793/M | openrouter |
| 18d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.0306/M → $0.0336/M pricing.tables.rate.base.input_tokens $0.0309/M → $0.0339/M | openrouter |
| 18d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.074501/M → $0.074356/M pricing.tables.rate.base.input_tokens $0.894012/M → $0.892272/M pricing.tables.rate.base.output_tokens $1.78802/M → $1.78454/M | openrouter |
| 19d ago | model.updated | pricing.tables.rate.base.output_tokens $0.1415/M → $0.1487/M | openrouter |
| 19d ago | model.updated | capabilities.response_format — → true capabilities.structured_outputs false → true contextWindow null → 202752 pricing null → card | huggingface |
| 19d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.0279/M → $0.0306/M pricing.tables.rate.base.input_tokens $0.0281/M → $0.0309/M | openrouter |
| 19d ago | model.updated | maxOutput 131072 → 943718 pricing.tables.rate.base.cache_read_tokens $0.001708/M → $0.028/M pricing.tables.rate.base.input_tokens $0.05368/M → $0.0509/M pricing.tables.rate.base.output_tokens $0.16104/M → $0.1415/M | openrouter |
| 19d ago | model.updated | pricingRange.routes.0.model zai/glm-5.3 → tencent/glm-5.3 pricingRange.routes.1.model novita/glm-5.3 → zai/glm-5.3 pricingRange.routes.10.model entrim/glm-5.3 → cloudflare/glm-5.3 pricingRange.routes.10.pricing.inputPerMillion 0.5 → 1.4 +27 more | llmgateway |
| 19d ago | model.updated | pricingRange.inputPerMillion.min 0.435 → 0.66 pricingRange.outputPerMillion.min 0.87 → 1.922 pricingRange.routes.9.pricing.inputPerMillion 0.435 → 0.66 pricingRange.routes.9.pricing.outputPerMillion 0.87 → 1.98 | llmgateway |
| 19d ago | model.updated | pricingRange.routes.10.pricing.inputPerMillion 0.14 → 0.15 pricingRange.routes.10.pricing.outputPerMillion 0.28 → 0.6 | llmgateway |
| 19d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.0028/M → $0.003/M pricing.tables.rate.base.input_tokens $0.14/M → $0.15/M pricing.tables.rate.base.output_tokens $0.28/M → $0.6/M | llmgateway |
| 19d ago | model.updated | pricingRange.routes.1.model deepinfra/mimo-v2.6-flash → tencent/mimo-v2.6-flash pricingRange.routes.2.model consensusprotocol/mimo-v2.6-flash → deepinfra/mimo-v2.6-flash pricingRange.routes.2.pricing.inputPerMillion 0.12 → 0.14 pricingRange.routes.2.pricing.outputPerMillion 0.25 → 0.28 +1 more | llmgateway |
| 19d ago | model.updated | pricingRange.routes.0.model deepseek/deepseek-v4.1-flash → tencent/deepseek-v4.1-flash pricingRange.routes.1.model alibaba/deepseek-v4.1-flash → deepseek/deepseek-v4.1-flash pricingRange.routes.1.pricing.inputPerMillion 0.3 → 0.15 pricingRange.routes.1.pricing.outputPerMillion 1.2 → 0.6 +22 more | llmgateway |
| 19d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.00363/M → $0.022/M pricing.tables.rate.base.input_tokens $0.435/M → $0.66/M pricing.tables.rate.base.output_tokens $0.87/M → $1.98/M | llmgateway |
| 19d ago | model.updated | pricingRange.routes.0.model zai/glm-5.3-flash → tencent/glm-5.3-flash pricingRange.routes.1.model novita/glm-5.3-flash → zai/glm-5.3-flash pricingRange.routes.10.model consensusprotocol/glm-5.3-flash → reka-ai/glm-5.3-flash pricingRange.routes.10.pricing.inputPerMillion 0.1 → 0.09 +26 more | llmgateway |
| 19d ago | model.updated | pricingRange.routes.0.model deepseek/deepseek-v4.1-flash-1017 → tencent/deepseek-v4.1-flash-1017 pricingRange.routes.1.model alibaba/deepseek-v4.1-flash-1017 → deepseek/deepseek-v4.1-flash-1017 pricingRange.routes.1.pricing.inputPerMillion 0.3 → 0.15 pricingRange.routes.1.pricing.outputPerMillion 1.2 → 0.6 +26 more | llmgateway |
| 19d ago | model.updated | contextWindow null → 262144 pricing.tables.rate.base.input_tokens $0.285/M → $0.1/M pricing.tables.rate.base.output_tokens $1.71/M → $0.95/M | huggingface |
| 19d ago | model.updated | contextWindow 131072 → null pricing card → null | huggingface |
| 19d ago | model.updated | maxOutput 943718 → 131072 pricing.tables.rate.base.cache_read_tokens $0.028/M → $0.001708/M pricing.tables.rate.base.input_tokens $0.0539/M → $0.05368/M pricing.tables.rate.base.output_tokens $0.1415/M → $0.16104/M | openrouter |
| 19d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.0254/M → $0.0279/M pricing.tables.rate.base.input_tokens $0.0256/M → $0.0281/M | openrouter |
| 19d ago | model.updated | contextWindow 64000 → 262144 | llmgateway |
| 19d ago | model.updated | contextWindow 64000 → 262144 | llmgateway |
| 19d ago | model.updated | contextWindow 64000 → 262144 | llmgateway |
| 19d ago | model.updated | contextWindow 64000 → 262144 | llmgateway |
| 19d ago | model.updated | maxOutput 131072 → 943718 pricing.tables.rate.base.cache_read_tokens $0.001806/M → $0.028/M pricing.tables.rate.base.input_tokens $0.05676/M → $0.0539/M pricing.tables.rate.base.output_tokens $0.17028/M → $0.1415/M | openrouter |
| 19d ago | model.updated | capabilities.response_format true → — capabilities.structured_outputs true → false | huggingface |
| 19d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.0231/M → $0.0254/M pricing.tables.rate.base.input_tokens $0.0233/M → $0.0256/M | openrouter |
| 19d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.0747765/M → $0.074501/M pricing.tables.rate.base.input_tokens $0.897318/M → $0.894012/M pricing.tables.rate.base.output_tokens $1.79464/M → $1.78802/M | openrouter |
| 19d ago | model.updated | maxOutput 943718 → 131072 pricing.tables.rate.base.cache_read_tokens $0.028/M → $0.001806/M pricing.tables.rate.base.input_tokens $0.057/M → $0.05676/M pricing.tables.rate.base.output_tokens $0.1341/M → $0.17028/M | openrouter |
| 19d ago | model.updated | capabilities.response_format true → — capabilities.structured_outputs true → false pricing.tables.rate.base.input_tokens $2.85/M → $3/M pricing.tables.rate.base.output_tokens $14.25/M → $15/M | huggingface |
| 19d ago | model.updated | pricingRange.outputPerMillion.min 0.15 → 0.19 pricingRange.routes.1.model nanogpt/gpt-oss-20b → together-ai/gpt-oss-20b pricingRange.routes.1.pricing.inputPerMillion 0.04 → 0.05 pricingRange.routes.1.pricing.outputPerMillion 0.15 → 0.2 +6 more | llmgateway |
| 19d ago | model.updated | pricingRange.routes.2.model nanogpt/gpt-oss-120b → bytedance/gpt-oss-120b pricingRange.routes.2.pricing.inputPerMillion 0.05 → 0.1 pricingRange.routes.2.pricing.outputPerMillion 0.25 → 0.5 pricingRange.routes.3.model bytedance/gpt-oss-120b → nebius/gpt-oss-120b +11 more | llmgateway |
| 19d ago | model.updated | capabilities.response_format true → — capabilities.structured_outputs true → false deprecated true → false | huggingface |
| 19d ago | model.updated | contextWindow 131072 → null pricing card → null | huggingface |
| 19d ago | model.updated | pricing.tables.rate.base.input_tokens $0.68/M → $0.95/M pricing.tables.rate.base.output_tokens $3.4/M → $4/M | huggingface |
| 19d ago | model.updated | pricing.tables.rate.base.input_tokens $3/M → $2.85/M pricing.tables.rate.base.output_tokens $15/M → $14.25/M | huggingface |
| 19d ago | model.updated | capabilities.response_format — → true capabilities.structured_outputs false → true | huggingface |
| 19d ago | model.updated | pricing.tables.rate.base.input_tokens $0.7/M → $0.5/M pricing.tables.rate.base.output_tokens $2.5/M → $2.15/M | huggingface |
| 19d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.079605/M → $0.0747765/M pricing.tables.rate.base.input_tokens $0.95526/M → $0.897318/M pricing.tables.rate.base.output_tokens $1.91052/M → $1.79464/M | openrouter |
| 19d ago | model.updated | capabilities.response_format — → true capabilities.structured_outputs false → true pricing.tables.rate.base.input_tokens $0.3/M → $0.26/M pricing.tables.rate.base.output_tokens $2.4/M → $2.6/M | huggingface |
| 19d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.021/M → $0.0231/M pricing.tables.rate.base.input_tokens $0.0212/M → $0.0233/M | openrouter |
| 19d ago | model.updated | capabilities.response_format — → true capabilities.structured_outputs false → true | huggingface |
older →webhook push: POST /v1/subscriptions