Meta: Muse Ember 1.0
Muse Ember is the efficient execution model in the Muse family, built for high-volume, repeated work. It runs the sub-agent tasks, tool calls, and routing inside larger agent workflows, and processes…
meta/muse-ember-1.0
Muse Ember is the efficient execution model in the Muse family, built for high-volume, repeated work. It runs the sub-agent tasks, tool calls, and routing inside larger agent workflows, and processes large collections of images, files, and records. Pair it with Muse Spark or Muse Wonder: the larger model plans, and Muse Ember handles the volume.
Specifications & capabilities
- Input
- text, image, video, audio, file
- Output
- text
- Context window · tokens
- 1048576
- Max output · tokens
- 524288
- Published model ID
- muse-ember-1.0
- Capabilities
- audioInput, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch
Published prices
1–10 / 10
$0.0040
- Inference provider
- cloudflareWorkersAI
- Platform
- meta
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing label
- Cached input tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$0.10
- Inference provider
- cloudflareWorkersAI
- Platform
- meta
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- Input tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$0.50
- Inference provider
- cloudflareWorkersAI
- Platform
- meta
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- Output tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$0.0040
- Inference provider
- meta
- Platform
- Meta Model API
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- Standard
- input_tokens_lte
- 200000
- training_data_use
- false
- cached_tokens_included
- true
- Billing label
- Standard · Cached input / 1M tokens · Up to 200K input tokens
$0.01
- Inference provider
- meta
- Platform
- Meta Model API
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- Standard
- applies_to
- entire_request
- input_tokens_gt
- 200000
- training_data_use
- false
- cached_tokens_included
- true
- Billing label
- Standard · Cached input / 1M tokens · Over 200K input tokens
$0.10
- Inference provider
- meta
- Platform
- Meta Model API
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- Standard
- input_tokens_lte
- 200000
- training_data_use
- false
- cached_tokens_included
- true
- Billing label
- Standard · Input / 1M tokens · Up to 200K input tokens
$0.30
- Inference provider
- meta
- Platform
- Meta Model API
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- Standard
- applies_to
- entire_request
- input_tokens_gt
- 200000
- training_data_use
- false
- cached_tokens_included
- true
- Billing label
- Standard · Input / 1M tokens · Over 200K input tokens
$0.50
- Inference provider
- meta
- Platform
- Meta Model API
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- Standard
- input_tokens_lte
- 200000
- training_data_use
- false
- cached_tokens_included
- true
- Billing label
- Standard · Output / 1M tokens · Up to 200K input tokens
$1.50
- Inference provider
- meta
- Platform
- Meta Model API
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- Standard
- applies_to
- entire_request
- input_tokens_gt
- 200000
- training_data_use
- false
- cached_tokens_included
- true
- Billing label
- Standard · Output / 1M tokens · Over 200K input tokens
$0.0025
- Inference provider
- meta
- Platform
- Meta Model API
- Unit
- request
- Currency
- USD
- Billing conditions
- kind
- add-on
- tier
- Standard
- tool
- web_search
- training_data_use
- false
- Billing label
- Web search / query (plus tokens)
Provider specifications & access
1–2 / 2
- source model id
- meta/muse-ember-1.0
- hosting
- third-party
- source model id
- muse-ember-1.0
- hosting
- meta-hosted
- context length
- 1048576
- max output tokens
- 524288
- capabilities
- visionInput
- videoInput
- audioInput
- fileInput
- toolCalling
- structuredOutputs
- reasoning
- webSearch
- promptCaching
Source specification observations
1–2 / 2
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- meta
- confidence
- 1
- field
- max_output_tokens
- value
- 524288
- normalized value
- 524288
- scope
- source-model
- source id
- meta
- confidence
- 1
Explore more models