GET
/v1/changes?type=model.updated&cursor=MTc5Mjg0NTA1Mjo1NTRlNjM5Yy1lMGFlLTQ2YTItODc4Yi1jYmMwN2JhYWE3NDA%3D
Accept:
count 50order newest firstpage size 50
| when | type | summary | provider |
|---|---|---|---|
| 25d ago | model.updated | requestMap {…} → null | nvidia |
| 25d ago | model.updated | requestMap {…} → null | nvidia |
| 25d ago | model.updated | requestMap {…} → null | nvidia |
| 25d ago | model.updated | requestMap {…} → null | nvidia |
| 25d ago | model.updated | requestMap {…} → null | nvidia |
| 25d ago | model.updated | requestMap {…} → null | nvidia |
| 25d ago | model.updated | requestMap {…} → null | nvidia |
| 25d ago | model.updated | providerMetadata.Reasoning reasoning_effort:low / high / max (default max ; thinking cannot be disabled) → reasoning_effort:low / high / max (default high ; thinking cannot be disabled) | kimi-code-plan-global |
| 25d ago | model.updated | providerMetadata.Reasoning reasoning_effort:low / high / max (default max ; thinking cannot be disabled) → reasoning_effort:low / high / max (default high ; thinking cannot be disabled) | kimi-code-plan-global |
| 25d ago | model.updated | providerMetadata.Reasoning reasoning_effort:low / high / max (default max ; thinking cannot be disabled) → reasoning_effort:low / high / max (default high ; thinking cannot be disabled) | kimi-code-plan-cn |
| 25d ago | model.updated | providerMetadata.Reasoning reasoning_effort:low / high / max (default max ; thinking cannot be disabled) → reasoning_effort:low / high / max (default high ; thinking cannot be disabled) | kimi-code-plan-cn |
| 25d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.023925/M → $0.0230695/M pricing.tables.rate.base.input_tokens $0.2871/M → $0.276834/M pricing.tables.rate.base.output_tokens $0.5742/M → $0.553668/M | openrouter |
| 25d ago | model.updated | pricing.tables.rate.base.output_tokens $8.94/M → $7.7001/M | openrouter |
| 25d ago | model.updated | pricing.tables.rate.base.input_tokens $0.0393/M → $0.0492/M | openrouter |
| 25d ago | model.updated | pricing.tables.rate.base.input_tokens $0.0393/M → $0.0492/M | openrouter |
| 25d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.024766/M → $0.023925/M pricing.tables.rate.base.input_tokens $0.297192/M → $0.2871/M pricing.tables.rate.base.output_tokens $0.594384/M → $0.5742/M | openrouter |
| 25d ago | model.updated | maxOutput 32768 → 7168 | sambanova |
| 25d ago | model.updated | maxOutput 131072 → 7168 | sambanova |
| 25d ago | model.updated | deprecated true → false | sambanova |
| 25d ago | model.updated | contextWindow 262144 → 131072 maxOutput 262144 → 131072 | sambanova |
| 25d ago | model.updated | capabilities.response_format — → true capabilities.structured_outputs false → true | huggingface |
| 25d ago | model.updated | pricing.tables.rate.base.input_tokens $0.5/M → $0.7/M pricing.tables.rate.base.output_tokens $2.15/M → $2.5/M | huggingface |
| 25d ago | model.updated | maxOutput 943717 → 131072 pricing.tables.rate.base.input_tokens $0.15/M → $0.0393/M pricing.tables.rate.base.output_tokens $0.5/M → $0.0788/M | openrouter |
| 25d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.025607/M → $0.024766/M pricing.tables.rate.base.input_tokens $0.307284/M → $0.297192/M pricing.tables.rate.base.output_tokens $0.614568/M → $0.594384/M | openrouter |
| 25d ago | model.updated | pricing.tables.rate.base.output_tokens $0.1028/M → $0.0788/M | openrouter |
| 25d ago | model.updated | maxOutput 7168 → 32768 | sambanova |
| 25d ago | model.updated | deprecated true → false | sambanova |
| 25d ago | model.updated | contextWindow 131072 → 262144 maxOutput 131072 → 262144 | sambanova |
| 25d ago | model.updated | maxOutput 7168 → 131072 | sambanova |
| 25d ago | model.updated | pricing.tables.rate.base.input_tokens $0.47/M → $0.32/M pricing.tables.rate.base.output_tokens $3.19/M → $3.2/M | huggingface |
| 25d ago | model.updated | capabilities.response_format true → — capabilities.structured_outputs true → false | huggingface |
| 25d ago | model.updated | capabilities.response_format — → true capabilities.structured_outputs false → true | huggingface |
| 25d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.0264625/M → $0.025607/M pricing.tables.rate.base.input_tokens $0.31755/M → $0.307284/M pricing.tables.rate.base.output_tokens $0.6351/M → $0.614568/M | openrouter |
| 25d ago | model.updated | deprecated true → false | huggingface |
| 25d 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 |
| 25d ago | model.updated | capabilities.response_format true → — capabilities.structured_outputs true → false | huggingface |
| 25d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.0262/M → $0.03/M pricing.tables.rate.base.input_tokens $0.0262/M → $0.0393/M | openrouter |
| 25d ago | model.updated | pricing.tables.rate.base.cache_read_tokens $0.0281445/M → $0.0264625/M pricing.tables.rate.base.input_tokens $0.337734/M → $0.31755/M pricing.tables.rate.base.output_tokens $0.675468/M → $0.6351/M | openrouter |
| 25d ago | model.updated | contextWindow null → 65536 pricing null → card | huggingface |
| 25d ago | model.updated | contextWindow 327680 → 890000 pricing.tables.rate.base.input_tokens $0.1/M → $0.09/M pricing.tables.rate.base.output_tokens $0.3/M → $0.29/M | huggingface |
| 25d ago | model.updated | contextWindow null → 262144 pricing.tables.rate.base.input_tokens $0.855/M → $0.09/M pricing.tables.rate.base.output_tokens $2.565/M → $0.55/M | huggingface |
| 25d ago | model.updated | pricing null → card | fal |
| 25d ago | model.updated | pricing null → card | fal |
| 25d ago | model.updated | pricing.examples.0.params.duration 10 → 1 pricing.examples.0.params.num_samples 2 → 1 pricing.examples.0.quote two 10-second samples cost $0.20 during the promotion → $0.010 per second through December 13, 2026 (33% off the standard $0.015 per second), then $0.015 per second. Billed per second of generated audio, per sample. pricing.examples.0.usd 0.2 → 0.01 +3 more | fal |
| 25d ago | model.updated | pricing.examples.2.params.seconds 120 → 10 pricing.examples.2.usd 6.24 → 3.12 pricing.inputs.resolution.default other → standard pricing.inputs.resolution.values.1 other → 1080p +6 more | fal |
| 25d ago | model.updated | pricing.examples.0.quote Speech costs **$0.03** per **1,000 characters** of input text. → speech costs $0.015 per 1,000 characters of input text pricing.examples.0.usd 0.03 → 0.015 pricing.price.*.1 0.000029999999999999997 → 0.000015 pricing.source.expiresAt — → 2026-10-31T23:59:59Z | fal |
| 25d ago | model.updated | pricing.examples.0.quote Video costs **$0.01625** per second at **480p** → Video costs $0.01625 per second at 480p pricing.examples.1.quote Video costs **$0.026** per second at **768p** → Video costs $0.026 per second at 768p pricing.examples.2.quote Video costs **$0.052** per second at **1080p** → Video costs $0.052 per second at 1080p | fal |
| 25d ago | model.updated | pricing.examples.0.params.duration 10 → 1 pricing.examples.0.params.num_samples 2 → 1 pricing.examples.0.quote two 10-second samples cost $0.20 during the promotion → $0.010 per second through December 13, 2026 (33% off the standard $0.015 per second), then $0.015 per second. Billed per second of generated audio, per sample. pricing.examples.0.usd 0.2 → 0.01 +3 more | fal |
| 25d ago | model.updated | pricing.examples.0.params.duration 10 → 1 pricing.examples.0.params.num_samples 2 → 1 pricing.examples.0.quote two 10-second samples cost $0.20 during the promotion → $0.010 per second through December 13, 2026 (33% off the standard $0.015 per second), then $0.015 per second. Billed per second of generated audio, per sample. pricing.examples.0.usd 0.2 → 0.01 +3 more | fal |
| 25d ago | model.updated | pricing null → card | fal |
older →webhook push: POST /v1/subscriptions