NEWVectors or files. Pick a path.Start →
    Provider APIGenerationVerified 2026-11-05

    Claude Sonnet 4.5

    claude-sonnet-4-5-20250929

    Claude Sonnet 4.5 is a text and image language model (Anthropic commercial terms of service). Called on Mixpeek through the provider API.

    Mixpeek calls the provider's API by name. Provider terms apply.

    Use in a new namespaceAdd to an existing namespace Record as JSON

    New opens the Designer in Studio. For an existing namespace, open it in Studio and use its Designer tab.

    No demo for Claude Sonnet 4.5 yet

    A video, image, slideshow or playground goes here once we record one on our own data.

    What it is good and bad at

    Best at
    Multi-step tool use and reasoning; the default model of agent sessions (DEFAULT_AGENT_MODEL) and of agentic_enrich when no provider or model is given.
    Worst at
    Per-document cost: agentic_enrich makes 3 to 15 calls per document, so it needs a when filter; no video or audio input.
    Task
    Generation
    Input
    Text, Image
    Output
    Text, Structured data
    Use cases
    Tagging, Captioning

    Templates that use it

    No template uses this model yet. Browse templates.

    Input and output

    Input

    text
    messages and tool results
    image
    image URLs

    Output

    text
    messages, tool calls, structured fields

    How Mixpeek wires it

    Extractors
    None today
    Feature URIs
    None today
    Vector indexes
    None
    Retriever stages
    agentic_enrich
    Combines with
    • feature_search -> agentic_enrich (Claude Sonnet 4.5 by default, gemini-2.5-pro as escalation model)
    • agent sessions (api.agents) call Anthropic only

    How it runs

    Status
    Provider API Provider API. Agent sessions and agentic_enrich call Anthropic directly; universal__api routes claude-* models for POST /v1/inference.
    Serve apps
    universal__api
    Runtime
    Anthropic Messages API (shared.models.llm Anthropic provider, api.agents.services)
    Weights
    Provider API, no remote code
    Parameters
    Not recorded
    Size on disk
    Not recorded
    Preprocessing
    Agent or stage prompt with tool definitions.
    Postprocessing
    Tool calls executed by the runtime; final text parsed into fields.
    Serving
    realtime
    Hardware
    Provider API

    Scale to zero

    Minimum replicas
    0
    Maximum replicas
    6
    Idle timeout
    600 s
    Memory
    Not recorded
    CPUs
    0.1
    GPUs
    0
    Cold start, node warm
    Not recorded
    Cold start, new node
    Not recorded

    Measured cost

    Unmeasured

    Billed per token by Anthropic; no committed measurement.

    Our evaluations

    Unmeasured

    We have not evaluated this model on our own data yet. Publisher results are in the sources below.

    Questions

    What is Claude Sonnet 4.5 best at?
    Multi-step tool use and reasoning; the default model of agent sessions (DEFAULT_AGENT_MODEL) and of agentic_enrich when no provider or model is given.
    What are the limits of Claude Sonnet 4.5?
    Per-document cost: agentic_enrich makes 3 to 15 calls per document, so it needs a when filter; no video or audio input.
    Can Claude Sonnet 4.5 be used commercially?
    Yes. Paid Anthropic API under Anthropic's commercial terms; agent sessions bill on the platform key.
    How does Claude Sonnet 4.5 run on Mixpeek?
    Provider API. Agent sessions and agentic_enrich call Anthropic directly; universal__api routes claude-* models for POST /v1/inference.