GET

/v1/changes?type=model.updated&cursor=MTc5MjU2OTYxNzowMDNiYzAyMS1mZWI5LTQ1ZTctOGJmYy1iMTI0MDcwZTQ3M2I%3D

count 50order newest firstpage size 50
whentypesummaryprovider
30d agomodel.updated
capabilities.response_format true → —
capabilities.structured_outputs true → false
huggingface
30d agomodel.updated
deprecated true → false
huggingface
30d agomodel.updated
pricing.tables.rate.base.output_tokens $0.375/M → $0.12/M
openrouter
30d agomodel.updated
pricing.tables.rate.base.output_tokens $0.375/M → $0.12/M
openrouter
30d agomodel.updated
contextWindow 262144 → null
pricing.tables.rate.base.input_tokens $0.71/M → $0.684/M
pricing.tables.rate.base.output_tokens $4.25/M → $4.104/M
huggingface
30d agomodel.updated
capabilities.response_format — → true
capabilities.structured_outputs false → true
contextWindow 1048576 → 262144
pricing.tables.rate.base.input_tokens $0.168/M → $0.14/M
+1 more
huggingface
30d agomodel.updated
contextWindow 262144 → 65536
pricing.tables.rate.base.input_tokens $0.47/M → $0.99/M
pricing.tables.rate.base.output_tokens $3.19/M → $1.49/M
huggingface
30d agomodel.updated
pricing.tables.rate.base.cache_read_tokens $0.008/M → $0.001176/M
pricing.tables.rate.base.input_tokens $0.07/M → $0.049/M
pricing.tables.rate.base.output_tokens $0.5/M → $0.375/M
openrouter
30d agomodel.updated
pricing.examples.0.params.image_size — → 1024x1024
pricing.examples.0.params.input_text_tokens 1000 → —
pricing.examples.0.params.num_images 0 → 1
pricing.examples.0.params.quality — → low
+41 more
fal
30d agomodel.updated
pricing.examples.0.params.input_image_tokens — → 0
pricing.examples.0.params.input_text_tokens — → 0
pricing.examples.0.quote For **low** quality, you will be charged $0.011 for 1024x1024 or $0.016 for any other size *per output image*. → For low quality, you will be charged $0.011 for 1024x1024 or $0.016 for any other size per output image.
pricing.examples.1.params.input_image_tokens — → 0
+18 more
fal
30d agomodel.updated
contextWindow null → 131072
pricing null → card
huggingface
30d agomodel.updated
contextWindow null → 131072
pricing null → card
huggingface
30d agomodel.updated
capabilities.response_format — → true
capabilities.structured_outputs false → true
contextWindow 1000000 → 262144
pricing.tables.rate.base.input_tokens $0.42/M → $0.47/M
+1 more
huggingface
30d agomodel.updated
deprecated true → false
huggingface
30d agomodel.updated
deprecated true → false
huggingface
30d agomodel.updated
deprecated true → false
huggingface
30d agomodel.updated
capabilities.response_format true → —
capabilities.structured_outputs true → false
contextWindow 65536 → 1000000
pricing.tables.rate.base.input_tokens $0.99/M → $0.42/M
+1 more
huggingface
30d agomodel.updated
capabilities.response_format — → true
capabilities.structured_outputs false → true
huggingface
30d agomodel.updated
pricing.tables.rate.base.cache_read_tokens $0.0425/M → $0.05/M
pricing.tables.rate.base.input_tokens $0.0765/M → $0.09/M
pricing.tables.rate.base.output_tokens $0.255/M → $0.3/M
openrouter
30d agomodel.updated
pricing.tables.rate.base.cache_read_tokens $0.003/M → $0.006/M
pricing.tables.rate.base.input_tokens $0.15/M → $0.3/M
pricing.tables.rate.base.output_tokens $0.6/M → $1.2/M
openrouter
30d agomodel.updated
pricing.price.+.0.if.1.*.1.lookup.keys.1 prompt → input_tokens
pricing.price.+.1.if.1.*.1.lookup.keys.1 completion → output_tokens
pricing.tables.rate.base.completion $2.08/M → —
pricing.tables.rate.base.input_tokens — → $0.4/M
+2 more
openrouter
30d agomodel.updated
capabilities.response_format true → —
capabilities.structured_outputs true → false
huggingface
30d agomodel.updated
displayName Anthropic's Claude Sonnet 5.5 → Claude Sonnet 5.5
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Haiku 4.5 → Claude Haiku 4.5
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Opus 5.5 → Claude Opus 5.5
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Sonnet 4.5 → Claude Sonnet 4.5
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Opus 4.8 → Claude Opus 4.8
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Opus 5 → Claude Opus 5
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Haiku 5.5 → Claude Haiku 5.5
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Sonnet 4.6 → Claude Sonnet 4.6
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Sonnet 5 → Claude Sonnet 5
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Opus 4.5 → Claude Opus 4.5
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Opus 4.6 → Claude Opus 4.6
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Fable 5.1 → Claude Fable 5.1
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Opus 4.7 → Claude Opus 4.7
google-vertex-anthropic
30d agomodel.updated
displayName Anthropic's Claude Fable 5 → Claude Fable 5
google-vertex-anthropic
30d agomodel.updated
pricing.examples.1.quote Each additional megapixel will cost 0.03. → Each additional megapixel will cost $0.03.
pricing.inputs.megapixels.default — → 1
pricing.price.+ {…} → —
pricing.price.if — → {…}
fal
30d agomodel.updated
pricing.inputs.resolution.default standard → 1K
pricing.inputs.resolution.values.0 standard → 512x512
pricing.inputs.resolution.values.1 512x512 → 2K
pricing.inputs.resolution.values.2 2K → 4K
+3 more
fal
30d agomodel.updated
pricing.examples.0.params.input_megapixels — → 1
pricing.examples.0.params.megapixels 1 → —
pricing.examples.0.params.num_images — → 1
pricing.examples.0.params.output_megapixels — → 1
+10 more
fal
30d agomodel.updated
pricing.examples.0.params.image_size — → 1024x1024
pricing.examples.0.params.megapixels 1 → —
pricing.examples.0.params.num_images — → 1
pricing.examples.0.quote Requests cost **$0.016** per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024x1024 generation with 512*512 size image input will cost **0.032** (1 MP input + 1 MP output, each costing **0.016**). → a 1024x1024 generation with 512*512 size image input will cost **$0.032** (1 MP input + 1 MP output, each costing **$0.016**).
+8 more
fal
30d agomodel.updated
pricing.examples.0.params.num_generations — → 1
pricing.examples.0.quote Your request will cost $0.375 per generation. → Your request will cost **$0.375** per generation.
pricing.examples.1 — → {…}
pricing.examples.2 — → {…}
+6 more
fal
30d agomodel.updated
pricing.examples.0.quote Your request will be charged at **0.01** $ per second of the input video, with a minimum charge for **60** seconds. Credits are not deducted if no cuts take place. → Your request will be charged at **$0.01** per second of the input video, with a minimum charge for **60** seconds. Credits are not deducted if no cuts take place.
fal
30d agomodel.updated
pricing.examples.0.params.num_images — → 1
pricing.examples.0.quote Your request will cost **$0.1** with TURBO, **$0.15** with BALANCED, and **$0.20** with QUALITY. → Each image costs **$0.10** with TURBO
pricing.examples.1.params.num_images — → 1
pricing.examples.1.quote Your request will cost **$0.1** with TURBO, **$0.15** with BALANCED, and **$0.20** with QUALITY. → Each image costs **$0.15** with BALANCED
+7 more
fal
30d agomodel.updated
pricing.examples.0.params.num_images 0 → —
pricing.examples.0.quote You will be charged $0.002 per 1,000 input text tokens. One word is roughly 4 tokens. → You will be charged **$0.002** per 1,000 input text tokens. Token counts vary with the text; you are charged for actual token usage.
pricing.examples.0.usd 0.01 → 0.002
pricing.examples.1.params.input_tokens 0 → —
+21 more
fal
30d agomodel.updated
pricing.examples.0.params.num_reference_images 1 → 1
pricing.inputs.num_reference_images.default 1 → 1
pricing.inputs.num_reference_images.kind number → enum
pricing.inputs.num_reference_images.values — → {…}
+3 more
fal
30d agomodel.updated
pricing.examples.0.quote Your request will cost $0.75 per generation. For $1.00, you can run this model 1 time. → Your request will cost **$0.75** per generation. For **$1.00**, you can run this model 1 time.
fal
30d agomodel.updated
pricing.examples.0.params.input_megapixels — → 1
pricing.examples.0.params.lora_size_gb — → 0
pricing.examples.0.params.megapixels 1 → —
pricing.examples.0.params.output_megapixels — → 1
+11 more
fal
30d agomodel.updated
pricing.examples.0.params.image_size — → 1024x1024
pricing.examples.0.params.input_mp 1 → —
pricing.examples.0.params.output_mp 1 → —
pricing.examples.0.quote a 1024×1024 generation with a 512×512 input image will cost $0.022 (1 MP input + 1 MP output, each costing $0.011). → a 1024×1024 generation with a 512×512 input image will cost $0.022 (1 MP input + 1 MP output, each costing $0.011)
+8 more
fal
30d agomodel.updated
pricing.examples.0.params.images 1 → —
pricing.examples.0.params.num_images — → 1
pricing.examples.0.quote Your request will cost **$0.039** per image. For **$1.00**, you can run this model **25 times.** → Each image costs **$0.0398**.
pricing.examples.0.usd 0.039 → 0.0398
+4 more
fal
30d agomodel.updated
pricing.examples.0.quote $0.10 per second of generated output video. The charge is based on final output duration in seconds. → **$0.10** per second of generated output video. The charge is based on final output duration in seconds.
fal