Claude Sonnet 5

LicenceFACT

not returned by the registry

Evidence not verified

ParametersFACT

not returned by the registry

Evidence not verified

Context lengthFACT

not returned by the registry

Evidence not verified

Downloads (30 days)FACT

not returned by the registry

Evidence not verified

LikesFACT

not returned by the registry

Evidence not verified

GatedFACT

no

Fresh·Retrieved 19 Sep 2026

Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: — parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).

No parameter count has been fetched for this model, so there is nothing to compute. We will not infer a size from the model’s name.

No hardware profile was sized for this answer.

Prompt (per million tokens, USD)FACT

2

Source: openrouter

Fresh·Retrieved 19 Sep 2026

Completion (per million tokens, USD)FACT

10

Fresh·Retrieved 19 Sep 2026

• Vendor apiAgent workflow on a model vendor’s APILangGraph as the orchestration graph mixing deterministic and model-driven steps, a closed model (GPT-5, Claude or Gemini) for the reasoning, your own tools for the actions, Langfuse for tracing and evaluation, and human approval gates on the steps that change something.
• Private cloudAssistant on Amazon BedrockA model served through Amazon Bedrock, Bedrock Knowledge Bases for retrieval over your content (with OpenSearch Serverless if you manage the vector store yourself), a web application you build, IAM Identity Center for sign-in, and a VPC with PrivateLink so the call stays on your network.
• Private cloudAgent workflow on a managed cloud runtimeA managed agent runtime that handles orchestration, memory, tool invocation and observability; a model from the same cloud; your APIs exposed as tools; private networking; and human approval gates on consequential actions. Same shape as the framework-hosted agent, one tenancy instead of two.
• Vendor apiAssistant on a model vendor’s APIOpen WebUI as the interface, a LiteLLM gateway holding the vendor key and the spend log, a closed model (GPT-5, Claude Sonnet or Gemini) reached over its API, and pgvector for retrieval over your own documents. The application is identical to a self-hosted one; only the model moves to a vendor endpoint.

1. 01
   Tier 2·official vendor legal documentationVendor legal and technical documentation

   Claude Sonnet 5 - Claude Platform Docs

   https://platform.claude.com/docs/en/models/sonnet-5/overview

   Ageing·Retrieved 19 Sep 2026sha256:dfddabffd4ee

   1 record01 claude-sonnet-5

2. 02
   Tier 2·official vendor legal documentationVendor legal and technical documentation

   Foundry Models from partners and community - Microsoft Foundry

   https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners

   Ageing·Retrieved 19 Sep 2026sha256:43d6e40d0d27

   1 record02 claude-sonnet-5

3. 03
   Tier 2·official vendor legal documentationVendor legal and technical documentation

   Models at a glance - Amazon Bedrock

   https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards.html

   Ageing·Retrieved 19 Sep 2026sha256:4c3b2b576226

   1 record03 Claude Sonnet 5

4. 04–09
   Tier 4·official repository / model cardOpenRouter

   OpenRouter endpoints — anthropic/claude-sonnet-5

   https://openrouter.ai/api/v1/models/anthropic/claude-sonnet-5/endpoints

   Ageing·Retrieved 19 Sep 2026sha256:3063359c9057

   6 records04 name = Claude Platform on AWS ·05 name = Azure ·06 name = Azure ·07 name = Claude Platform on AWS ·08 name = Claude Platform on AWS ·09 name = Azure