Research report · data-report
Claude models: a census of 143 listings
86 of 143 listings answer yes for “Claude models”. Counted from our own datasheet, with the query that reproduces every figure.
On this page
Claude models, across 143 settled listings
Of the 143 Published listings whose datasheet settles “Claude models”, the largest group is “Yes” at 86 (60%). Measured 2026-10-03.
Explore the matching agents
Claude models · Datasheet criterion claude · Report counted .
Current listings as of ; this set may differ from the report's original sample. Includes “Yes” and “Qualified” answers only. Read the conditions on qualified answers before treating them as a match. “No”, “Not applicable” and “Not established” answers are excluded.
View 109 current matching records
- Ada Qualified
Anthropic is named in Ada's curated model portfolio and its MCP server targets Claude, but Ada selects the models and never offers Claude as a customer-chosen option.
Source retrieved 2026-10-03
- AgentBridge Yes
Claude Code is one of the two first-class sides of the bridge, wired in through a Claude Code plugin and MCP channel with a recommended Claude Code version in the prerequisites.
Source retrieved 2026-10-03
- Agentix Labs Yes
Claude is the firm's lead model platform, with a dedicated partner page describing Claude agent architecture, tool contracts and MCP-based integration work.
Source retrieved 2026-10-03
- AgentsKit.js Yes
A first-class Anthropic adapter covers the Claude family with streaming, tool calls and vision, and Claude on AWS is reachable through the separate Bedrock adapter.
Source retrieved 2026-09-09
- Agno Yes
Native Anthropic adapter with a `Claude` model class, plus Claude via Bedrock, Vertex AI and Azure AI Foundry.
Source retrieved 2026-09-02
- Aident Loadout Qualified
Claude Code and Claude Desktop are named supported clients, so Claude-based agents can use it, but Loadout supplies no model and does not bill for Claude inference.
Source retrieved 2026-10-03
- Aider Yes
Anthropic Claude is named as one of the models aider works best with, and the quick-start shows launching it with an Anthropic key.
Source retrieved 2026-09-30
- Amplemarket Qualified
Claude is supported as a client that drives Amplemarket over its MCP server, on Claude's own paid tiers; the vendor never discloses which model powers Duo internally, so this is access from Claude rather than a model choice.
Source retrieved 2026-09-10
- Antigravity CLI Qualified
Claude Sonnet 4.6 and Opus 4.6 are selectable reasoning models on the free and consumer paid plans, but the model matrix marks both unavailable on Enterprise deployments.
Source retrieved 2026-09-10
- API.market Qualified
Claude is supported as a client that calls the marketplace over MCP, with a Claude Desktop config published; no Claude model API appeared among the hosted LLM products I read.
Source retrieved 2026-10-03
- Argorant Yes
Claude is a first-class client with its own setup guide and a native remote MCP connector covering Desktop, Cowork and Code.
Source retrieved 2026-09-26
- Arsum Qualified
Anthropic models appear in the published implementation stack of one delivered client build, which shows Arsum works with Claude but is not a product-wide support statement.
Source retrieved 2026-10-03
- Artisan Qualified
Artisan ships an official Claude connector on all plans, so Claude can drive your Artisan account from a chat. That is Claude acting as a client, not disclosure that Claude powers Ava. The vendor names no model behind Ava, and the connector is flagged as early.
Source retrieved 2026-09-02
- AudioCodes Live Hub Qualified
Claude models are supported only as bring-your-own custom models configured with your own Anthropic API key; the pre-deployed model list carries OpenAI and Google models only.
Source retrieved 2026-09-24
- Augment Code Yes
Claude Opus, Sonnet, Haiku and Fable families are all selectable.
Source retrieved 2026-09-02
- AutoGen Qualified
A first-party Anthropic client exists in the extensions package, but Microsoft labels the section experimental rather than a supported integration.
Source retrieved 2026-09-19
- Bitsclan IT Solutions Yes
Anthropic models are named as one of the two providers behind their chatbots, and a generative AI section is headed From GPT to Claude; the AI agent page itself names no model vendor.
Source retrieved 2026-09-11
- Botpress Yes
First-party Anthropic integration maintained by Botpress; you pick Claude models per node, workflow or skill, billed at cost to your workspace AI Spend.
Source retrieved 2026-09-02
- Browserbase Yes
Anthropic models are reachable through Model Gateway with only a Browserbase API key.
Source retrieved 2026-09-02
- Cartesia Yes
Anthropic Claude models are named in the SDK's supported-models table and used in its examples.
- Claude Agent SDK Yes
Claude is the only model family; you can pin a specific Claude model per session.
Source retrieved 2026-09-02
- Claude Code Yes
Claude is the only model family: Fable, Opus, Sonnet and Haiku aliases, resolved per provider.
Source retrieved 2026-09-02
- Cline Yes
Claude is supported and is the vendor's recommended coding model, reachable through Cline's own billing, through Anthropic directly, or via Bedrock and Vertex.
Source retrieved 2026-09-12
- CodeRabbit Yes
Anthropic is named as a model provider that receives code for reviewing, though CodeRabbit selects the models and buyers cannot pick a specific Claude version on hosted plans.
Source retrieved 2026-09-15
- Cresta Qualified
Anthropic is named as a sub-processor supplying natural-language APIs, which is the closest Cresta comes to confirming Claude in its stack; buyers are never offered a named model to select.
Source retrieved 2026-09-13
- CrewAI Yes
Anthropic is one of the natively integrated providers, configured with your own key, and Claude models are also reachable through Bedrock and Snowflake Cortex.
Source retrieved 2026-09-13
- Cursor Yes
Anthropic models are first-class, billed from the Other Models pool at Anthropic's own per-token API rates.
Source retrieved 2026-09-02
- Decagon Qualified
Anthropic is named as one of Decagon's AI providers and is listed as an LLM subprocessor, but the buyer never selects Claude — routing is Decagon's.
Source retrieved 2026-09-14
- Deepgram Voice Agent API Yes
Anthropic is a Deepgram-managed provider, so no endpoint of your own is needed; Claude Sonnet models bill at the Advanced tier and Claude Haiku at Standard.
Source retrieved 2026-09-02
- Devin Yes
Anthropic models are selectable in Devin CLI, where opus and sonnet resolve to the latest in each family.
Source retrieved 2026-09-02
- Devin Desktop Qualified
Claude is a premium model: the plan table marks premium models absent on Free and present from Pro upward; the model table lists Opus, Sonnet and Haiku variants.
Source retrieved 2026-09-03
- Dify Yes
Anthropic models are among the providers covered by bundled message credits; you can also add your own Anthropic key.
Source retrieved 2026-09-02
- Dust Yes
Claude is named in the plan feature list of frontier models, and the admin model tier tables list several Claude models across Basic through Ultra tiers.
Source retrieved 2026-10-01
- ElevenLabs Agents Yes
Anthropic models are natively selectable in agent settings; a few older Claude models drop out in EU data-residency workspaces.
Source retrieved 2026-09-02
- Elicit Yes
Anthropic is a named subprocessor whose models generate Elicit's AI responses, so Claude is in the stack, but as Elicit's own choice, with no Claude toggle exposed to the buyer.
Source retrieved 2026-09-14
- Faceless.so Qualified
Claude is supported as a caller, not as a generation model: a custom connector, remote MCP server and packaged skill let Claude drive Faceless, while the video models are the vendor's own three.
Source retrieved 2026-10-03
- Factory Yes
Anthropic models are listed natively, from Haiku 4.5 through Opus-class, with per-model usage multipliers.
Source retrieved 2026-09-02
- Fin Qualified
Anthropic is one of the providers Fin falls back to for resilience, but the answer model is Intercom's own Apex and the buyer is not offered a model picker, so Claude is under the hood rather than selectable.
Source retrieved 2026-09-18
- GC AI Yes
Anthropic's Claude family is one of four providers the platform routes to, and Teams and Enterprise admins can additionally opt in to the Claude Fable 5 model, which carries 30-day retention rather than zero data retention.
Source retrieved 2026-09-14
- Genspark Yes
Anthropic models are offered as the frontier option in AI Slides Ultra mode, and the Team plan card lists a Claude model in its zero-credit chat lineup.
Source retrieved 2026-09-15
- GitHub Copilot Yes
Claude is in the catalog from the Free plan up, with the premium Opus tier gated to Pro+ and above; Anthropic models are served from AWS, Anthropic and Google Cloud.
Source retrieved 2026-09-02
- Glean Yes
Anthropic models are offered through Google Vertex AI or Amazon Bedrock, or directly with your own Anthropic key.
Source retrieved 2026-09-02
- Google Agent Development Kit (ADK) Yes
Claude is supported in Python and Java, either through the registry wrapper on Google Cloud Agent Platform or directly against Anthropic with your own API key.
Source retrieved 2026-09-15
- goose Yes
Claude is supported through Anthropic directly and via Bedrock, Vertex, Snowflake, Databricks and Copilot, and the vendor names Claude 4 as the model goose works best with today.
Source retrieved 2026-09-16
- GPT Researcher Yes
Claude is named as a supported model and anthropic appears in the docs list of LLM providers, with your own Anthropic key.
Source retrieved 2026-09-16
- Gumloop Yes
Anthropic is a first-class provider in the model picker and the docs list nine Claude models served directly by Anthropic.
Source retrieved 2026-09-30
- HOL Guard Yes
Claude Code is a stable supported harness with native approval, browser fallback and resume, though prompt events are not surfaced.
Source retrieved 2026-09-29
- IrisAgent Yes
Anthropic models are scored inside the production IrisAgent stack on its own leaderboard, and the vendor says production routing follows that board.
Source retrieved 2026-09-24
- Juggler Yes
Anthropic's API and the Claude Code CLI are both first-class providers; with the Claude Code provider Juggler spawns the CLI with strict MCP config and serves it Juggler's own toolset.
Source retrieved 2026-09-17
- Julius AI Qualified
Anthropic models are selectable from the model dropdown but only once you pay; the Free tier is restricted to the vendor's own lightweight models, and the flagship Anthropic model needs Pro or above.
Source retrieved 2026-09-17
- Junie Yes
Anthropic models are reachable both through the JetBrains subscription and by pasting your own Anthropic key, and the CLI ships a built-in alias mapping onto Claude models.
Source retrieved 2026-09-18
- Kilo Code Yes
Claude models are in the hosted catalogue and available via an Anthropic BYOK key.
Source retrieved 2026-09-02
- LangChain Yes
A first-party langchain-anthropic package covers Claude with tool calling, structured output and streaming, and the LLM Gateway routes Anthropic model IDs with one LangSmith key.
Source retrieved 2026-09-18
- Langflow Yes
Anthropic Claude models work out of the box through the core Language Model component, with a dedicated Anthropic bundle adding provider-specific parameters such as prefill and a custom API URL.
Source retrieved 2026-09-25
- LangGraph Yes
Claude models are reached through the first-party ChatAnthropic integration, and also via ChatBedrock and Vertex for Anthropic models on those clouds.
Source retrieved 2026-09-02
- Lead Scorer Yes
Claude is a first-class client through the hosted MCP server, including Claude Code, with per-client setup guides and OAuth sign-in rather than a pasted key.
Source retrieved 2026-09-18
- Leaping AI Yes
Claude is named as one of the large language models a customer can choose to power an agent; the vendor lists model choice as a platform feature rather than a tier upgrade.
Source retrieved 2026-09-09
- Letta Yes
Anthropic API, Amazon Bedrock and GitHub Copilot connections; supported both locally and signed in with Letta.
Source retrieved 2026-09-02
- Lindy Yes
Anthropic models are named on the enterprise page as selectable per job, and Lindy's billing docs say every plan, including trial seats, gets every model with no upsell wall.
Source retrieved 2026-09-19
- LiveKit Agents Yes
Anthropic plugin for Python and Node.js, using your own Anthropic API key. Claude is not among the models served through LiveKit Inference, so it is a plugin-only path.
Source retrieved 2026-09-02
- LlamaIndex Yes
Anthropic Claude is one of three model families the platform runs, via Anthropic API or AWS Bedrock.
Source retrieved 2026-09-02
- LuMay Yes
The runtime names Anthropic as a swappable provider alongside OpenAI; the vendor names the provider, not a specific Claude model version.
Source retrieved 2026-09-09
- Manus Qualified
Claude is selectable only for LLM features inside apps Manus builds for you; you cannot choose it for the Manus agent itself, and Anthropic is not among the disclosed foundational-model subprocessors.
Source retrieved 2026-09-02
- Mastra Yes
Anthropic is a named first-class provider in the model router; models are selected as provider/model-name strings.
Source retrieved 2026-09-02
- Maven AGI Yes
The Master Services Agreement names Anthropic, alongside OpenAI, as one of exactly two LLM providers generating output today, and lists it as a contracted sub-processor rather than an optional integration.
Source retrieved 2026-09-03
- Microsoft Agent Framework Yes
Anthropic is a first-class model provider with its own client package, reachable through Anthropic directly or through Foundry, Bedrock and Vertex AI endpoints.
Source retrieved 2026-09-19
- MindStudio Yes
Anthropic is a first-class publisher in the model catalogue with fifteen Claude entries listed alongside their per-million-token input and output rates.
Source retrieved 2026-09-20
- n8n Yes
Dedicated Anthropic Chat Model node for agents and chains, usable with your own Anthropic key or, on Cloud, with n8n Gateway credits.
Source retrieved 2026-09-02
- Octacer Yes
Claude is one of the models they document integrating into client workflows, recommended for complex reasoning and analysis work.
Source retrieved 2026-09-26
- OpenAI Agents SDK (Python) Qualified
The SDK names only OpenAI models; non-OpenAI providers are reached through OpenAI-compatible endpoints or the beta Any-LLM and LiteLLM adapters, and Claude is never named in the docs.
Source retrieved 2026-09-02
- OpenClaw Yes
Anthropic is a first-class provider, reachable either through an API key or through a Claude subscription route, and Claude CLI can execute the turn as a backend.
Source retrieved 2026-09-21
- OpenCode Yes
Anthropic is a first-class provider, and the vendor's own Zen gateway serves several Claude models with published per-token prices.
Source retrieved 2026-09-21
- OpenHands Yes
Claude Sonnet, Opus and Haiku are all sold through the vendor's own LLM proxy, and can equally be reached with your own Anthropic key.
Source retrieved 2026-09-21
- Perplexity Yes
Claude is one of the models the consumer product orchestrates, and the Agent API exposes Opus, Sonnet and Haiku by model id.
Source retrieved 2026-09-02
- Pickaxe Yes
Anthropic is one of the providers in the model catalogue and Claude models appear as selectable options per agent, billed through Pickaxe credits rather than your own Anthropic account.
Source retrieved 2026-09-09
- PitchAI Agent Engine Yes
Anthropic's Claude and Claude Code both appear in the vendor's model and agent inventory, with no tier restriction attached to the list.
Source retrieved 2026-10-03
- PolyAI Yes
Claude is one of the third-party models you can run instead of Raven; the model docs list Claude options under the Amazon Bedrock provider tab, selectable per channel.
Source retrieved 2026-09-02
- Pydantic AI Yes
Anthropic is a first-class built-in provider with its own model class and install extra, selectable by a provider-prefixed model string like anthropic:claude-sonnet-4-6.
Source retrieved 2026-09-21
- Qualified Yes
Anthropic models are used via Amazon Bedrock as a named generative-AI subprocessor.
Source retrieved 2026-09-02
- Relevance AI Yes
Anthropic Claude models run through Anthropic's API with no data logging, and agent settings expose Claude-specific thinking type and effort controls.
Source retrieved 2026-09-22
- Replit Agent Yes
Anthropic models are selectable in both paid modes, with the heavier variants reserved for Max Mode rather than the cheaper Power tier.
Source retrieved 2026-09-22
- Retell AI Yes
Claude models are selectable as the agent's conversation model and priced per minute for voice and per message for chat, alongside GPT and Gemini options.
Source retrieved 2026-09-23
- Rox Qualified
Anthropic is a named AI service-provider subprocessor under zero data retention, so Claude models are in the stack; Rox publishes no model names and no model picker, so a buyer cannot select Claude.
Source retrieved 2026-09-03
- SafeNet Creations Yes
Agents built on the vendor's MCP architecture run against Claude, and the vendor presents model choice as deliberately non-locked-in across the three named providers.
Source retrieved 2026-09-28
- Salesforce Agentforce Yes
Anthropic Claude models are named rows in the supported-model table, and the non-default AWS-Hosted Agentforce model option is a Claude model on Amazon Bedrock.
Source retrieved 2026-09-03
- SalesTouch Yes
Claude is a first-class client on both plans, connected either through the vendor's plugin marketplace flow or a manual remote MCP entry.
Source retrieved 2026-09-25
- SEOmatic Yes
Anthropic Claude is used for specific jobs by default and becomes the sole writing model for workspaces flagged EU-sensitive, running on your own Anthropic key.
Source retrieved 2026-10-03
- Sierra Qualified
Anthropic is a named AI-services subprocessor, so Claude is in the mix, but Sierra routes models itself and never exposes a Claude selector.
Source retrieved 2026-09-26
- Sim Yes
Anthropic is one of 15+ supported providers; hosted Claude pricing is published per model.
Source retrieved 2026-09-03
- sipgate flow Yes
Claude is named as a model you integrate behind the voice layer; sipgate does not resell it, your own application makes the call.
Source retrieved 2026-09-26
- SkaleAgents Qualified
Claude is supported as the assistant you bring: bot pages hand off to Claude, and Claude Code and Claude Desktop connect to the MCP server, but you do not select a model inside SkaleAgents.
Source retrieved 2026-10-03
- StackAI Yes
Anthropic is one of the providers StackAI supplies hosted keys for, and the agent node's own settings document Claude-specific behaviour such as required streaming on long responses.
Source retrieved 2026-09-09
- TecAdRise Qualified
Anthropic is selectable only in their separately published Chrome extension, where the user supplies the key; the models behind client voice agents and Agent-OS builds are never named.
Source retrieved 2026-09-12
- TelEcho Qualified
Claude appears as a place you drive TelEcho from, via the vendor's MCP integration, not as a model the agent can run on; the pricing calculator's LLM selector offers OpenAI models only.
Source retrieved 2026-09-16
- Telnyx Voice AI Agents Yes
Claude is selectable as the assistant's model in the Agent tab, and the model table marks a Claude Haiku entry as requiring no API key of your own; prompts still leave Telnyx for Anthropic.
Source retrieved 2026-09-09
- UiPath Agent Builder Yes
Anthropic is one of only three model providers the Agents documentation lists as selectable for an agent, served through AWS Bedrock, and you choose it per agent in the Properties panel.
Source retrieved 2026-09-03
- Undermind Yes
Published Claude connector, one-click setup, plus documented Claude Code CLI install.
- Vapi Yes
Claude is selectable as the assistant's LLM, on Vapi's integration or your own Anthropic account.
Source retrieved 2026-09-03
- Vecbase Yes
Anthropic Claude models are first-class entries in the public model catalog, each with its own Vecbase model ID and published per-token usage rates.
Source retrieved 2026-09-27
- Vellum Yes
Anthropic's Claude is the default provider for managed cloud assistants, and Vellum supplies the API credentials on the free Base plan.
Source retrieved 2026-09-27
- VoiceAgents Yes
Anthropic is one of three selectable LLM providers, chosen per agent.
Source retrieved 2026-09-03
- Warp Yes
Anthropic models are a first-class option in the model picker, and Claude Code can also be used as the agent harness inside Warp.
Source retrieved 2026-09-03
- WTAgent Yes
Claude is a first-class provider selected with a flag; it uses whichever model your claude.ai browser profile already has chosen.
Source retrieved 2026-09-21
- Xquik Yes
Claude, Claude.ai and Claude Code are named as supported MCP clients, with OAuth 2.1 the documented authentication path for them.
Source retrieved 2026-10-03
- Zed Yes
Anthropic Claude models are served through Zed's own hosted plan with published per-million-token rates, and Claude is also reachable via your own Anthropic key.
Source retrieved 2026-09-29
- Zencoder Yes
Anthropic models are in the managed catalogue on paid plans and Claude Code can be chosen as the runtime; the Opus tiers require Pro Plus or above.
Source retrieved 2026-09-09
- Zendesk AI agents Qualified
Claude is not what powers the agent; it is reachable as an external action in action flows using your own Anthropic key.
- zot Yes
Anthropic is a first-class provider reachable either with an API key or by logging in with an existing Claude Pro or Max subscription through the OAuth flow.
Source retrieved 2026-09-28
- ZTABS Yes
Anthropic Claude is named as one of the foundation models they build agents on, alongside OpenAI and Google, and is listed in the EMRG product stack.
Source retrieved 2026-09-25
The population
143 listings in this index are Published. This is the population as of 2026-10-03. 143 of the 143 published listings in this index carry a settled answer for “Claude models”. That row asks: Does it run on Claude? Every listing in the index is settled on this row, so nothing is left out.
Findings
-
86 of the 143 settled listings answer “Yes” for “Claude models”. That is 60% of the settled set.
-
23 of the 143 settled listings answer “Qualified” for “Claude models”. That is 16% of the settled set.
-
18 of the 143 settled listings answer “No” for “Claude models”. That is 13% of the settled set.
-
16 of the 143 settled listings answer “Not established” for “Claude models”. That is 11% of the settled set.
1 of those yes answers is Agentix Labs, which still answers yes for “Claude models”. Its listing carries the stored answer and links to the source recorded for it. This is one worked example, not an independent audit of every source in the census.
What we counted, and how
Each figure above is a count over the “Claude models” row of the listing datasheet, taken from the same stored answer the listing page renders. The denominator is the 143 listings whose answer is settled, meaning one of yes, qualified, no, does not apply, not established. On this row that is the whole index, because every listing has a recognised stored answer. Every number here is stored with the read-only query that reproduces it and re-run every sixty seconds against the live corpus, so a figure that stops reproducing surfaces as drift rather than as a stale sentence nobody notices. Our full method covers how a datasheet row is settled in the first place.
Limitations
This counts stored datasheet answers, not independently tested capabilities. A sourced answer can record a vendor statement or our reading of published evidence; this census does not re-fetch those sources. “Not established” means we have not established an answer. That can reflect vendor nondisclosure, blocked evidence, or unfinished research, not a no. An absent or unrecognised answer is excluded rather than treated as a researched finding. The figures are restated when the stored corpus changes; the date above is the count used for this published version, not a new verification of the vendors.
Get the next report
New agents rankings and fresh data reports. One short email, one-click unsubscribe.