Ranked · Agent platforms
Best Agent platforms — Model choice
24 of 33 agent platforms match “Model choice”. Compare their prices and features side by side.
The ranking
24 agents, ranked. Compare fit and price, then open a review. How we rank
All picks at a glance
| # | Agent | Best for | Starts at |
|---|---|---|---|
| 1 | TaleVerified | The buyer picks the provider credential and pins a model per agent; the vendor ships no model of its own and admins restrict access per person or team. | Free, then CHF 12/month |
| 2 | LuMay | Provider choice is an explicit design property: agents, flows and connectors are meant to survive a swap between providers or any compatible API. | From $249/month |
| 3 | Dust | The buyer picks the model per agent and nothing is gated behind a higher plan, though admins may cap which model tiers members can select and costlier models burn more credits. | Free, then €30/seat/month |
| 4 | Pickaxe | You choose the model per agent and can swap it at any time without rebuilding the agent, and the vendor makes not being locked to one provider an explicit selling point. | Free, then $37/month |
| 5 | Gumloop | The buyer picks the model per agent from 35+ options on both plans, can swap freely, and Enterprise admins can restrict the allowed set. | From $37/month |
| 6 | StackAI | The buyer picks provider and model per agent node and can switch later from a dropdown; admins may narrow that list but the vendor does not fix one model. | Free |
| 7 | Aisera Agent Composer (Agent Studio) | The buyer picks the foundation model, Aisera's own or a third party's, and the LLM Gateway can also route automatically between open and closed models for cost and latency. | On quote |
| 8 | UiPath Agent Builder | You pick the model per agent from the Properties panel, models are provisioned through the AI Trust Layer, and the vendor states a model can be swapped later without rebuilding the agent. | Free, then $25/month |
| 9 | Vellum | You pick the model per workspace, per conversation and per action type through inference profiles and action overrides, with custom profiles for providers not built in. | Free, then $30/month |
| 10 | SimVerified | Dev teams wanting an open-source, API-first workspace to build and deploy AI agents | Free, then $25/seat/month |
| 11 | MindStudio | You choose the model per block from a large multi-publisher catalogue, can compare models side by side, and can plug in your own keys or endpoints instead. | Free, then $20/month |
| 12 | OpenClaw | Developers and self-hosters who already run their own infrastructure and want one personal AI agent that reaches WhatsApp, Telegram, Slack, Discord, Signal and iMessage instead of a separate app. | Free |
| 13 | Agno | Python developers who want an Apache 2.0 SDK with memory, knowledge, learning, guardrails and a Control Plane they run inside their own cloud account, and who are comfortable running Docker or a cloud deploy template themselves. | Free, then $150/month |
| 14 | Botpress | Engineering-led teams building a multi-channel AI support agent who want an open-source, self-hostable core with an optional managed cloud layer. | Free, then $189/month |
| 15 | Glean | Large and mid-market enterprises whose biggest AI-agent blocker is fragmented, permission-sensitive knowledge scattered across 100+ internal tools, and who want employees building department-specific agents on that indexed knowledge without writing code. | Price not established |
| 16 | Salesforce Agentforce | Salesforce service, sales, field-service and employee-support teams that need agents to act on CRM records and have Salesforce admin or developer capacity. | Free, then $5/user per month |
| 17 | Letta | Developers and researchers who specifically need an agent whose memory, skills and identity genuinely persist and evolve across long-running sessions, rather than reset on every call. | Free, then $20/month |
| 18 | VecbaseVerified | Small teams or solo operators who want pre-built AI agent roles, shared files, and OAuth-driven workflows under one credit-based subscription. | From $19.90/year |
| 19 | ElevenLabs Agents | Developers and product teams who want ElevenLabs' voice quality and cloning as the foundation of their agent, and are comfortable assembling the rest of the stack themselves. | Free, then $6/month |
| 20 | Dify | Developers and teams who want an open-source, self-hostable platform to build RAG apps and agents with full data control. | Free, then $59/month |
| 21 | Lindy | Teams that want an AI teammate embedded in Slack and a no-code app builder under the same plan, with usage that pauses at the credit cap rather than overage-billing. | From $29.99/month |
| 22 | Relevance AI | Revenue, ops, and customer success teams running 5+ agents in production, who want multi-agent orchestration with evals, tracing, and SSO-grade governance on one bill. | From $29/month |
| 23 | LangChain | Engineering teams building a bespoke, production-grade agent who want the largest integration ecosystem plus real stateful control. | Free, then $39/seat/month |
| 24 | n8n | Ops and automation teams who want to build agentic workflows visually while keeping data on self-hosted infrastructure. | Free, then €24/month |
About this list
24 of 33 agent platforms match “Model choice”. Of the rest: 6 on some plans only, 3 no, 0 unknown.
How the agent platforms matching “Model choice” differ: 23 of 24 also match “Claude”, against 3 of 9 in the rest of the category.
The ranking
Editor’s pick
#1
TaleVerified
Open-source project workspace where teams assign tasks to AI coding agents running in sandboxes.
Best forThe buyer picks the provider credential and pins a model per agent; the vendor ships no model of its own and admins restrict access per person or team.
Model choice: Yes — The buyer picks the provider credential and pins a model per agent; the vendor ships no model of its own and admins restrict access per person or team.“Search **Model** by name or API ID. The same model can appear once per provider; read the provider on the entry before selecting it. Selecting an entry pins that pair for future runs.”Configure the agent, step 'Choose the model and provider' · checked 2026-10-03
- #2
LuMay
Enterprise agentic AI platform with packaged voice, legal, compliance and workflow agents; SaaS, on-prem or air-gapped.
Best forProvider choice is an explicit design property: agents, flows and connectors are meant to survive a swap between providers or any compatible API.
Model choice: Yes — Provider choice is an explicit design property: agents, flows and connectors are meant to survive a swap between providers or any compatible API.“The engine is provider-agnostic: you can swap between OpenAI, Anthropic, or any compatible API without changing the agent configuration, the conversation flow, or any downstream connector.”Overview section, second paragraph · checked 2026-09-09
Best forThe buyer picks the model per agent and nothing is gated behind a higher plan, though admins may cap which model tiers members can select and costlier models burn more credits.
Model choice: Yes — The buyer picks the model per agent and nothing is gated behind a higher plan, though admins may cap which model tiers members can select and costlier models burn more credits.“All plans include access to 20+ models from OpenAI, Anthropic, Google, Mistral, and DeepSeek. You choose the model per agent. No model is locked behind a higher plan, though higher-capability models may consume more credits per message.”FAQ, "Which AI models are included?" · checked 2026-10-01
Advertisement
Your agent here. Go Featured to sit above the free listings in this ranking, or buy the slot beside it.
Get featured · top of your category →- #4
Pickaxe
No-code platform for building AI agents and selling them through branded portals with billing built in.
Best forYou choose the model per agent and can swap it at any time without rebuilding the agent, and the vendor makes not being locked to one provider an explicit selling point.
Model choice: Yes — You choose the model per agent and can swap it at any time without rebuilding the agent, and the vendor makes not being locked to one provider an explicit selling point.“Building on Pickaxe means you're never locked in — when a better or cheaper model comes along, you can switch to it in seconds without changing anything else about your agent.”Models docs page, 'Why model flexibility matters' section · checked 2026-09-09
- #5
Gumloop
Multiplayer AI agent builder: teams build agents over their apps while IT keeps governance and spend control.
Best forThe buyer picks the model per agent from 35+ options on both plans, can swap freely, and Enterprise admins can restrict the allowed set.
Model choice: Yes — The buyer picks the model per agent from 35+ options on both plans, can swap freely, and Enterprise admins can restrict the allowed set.“You choose which models and providers your agents use, and you can bring your own keys (BYOK) so calls run through your own provider accounts.”'Privacy and how your data is used' section · checked 2026-09-30
- #6
StackAI
No-code enterprise platform for building, deploying and governing AI agents across business systems.
Best forThe buyer picks provider and model per agent node and can switch later from a dropdown; admins may narrow that list but the vendor does not fix one model.
Model choice: Yes — The buyer picks provider and model per agent node and can switch later from a dropdown; admins may narrow that list but the vendor does not fix one model.“StackAI is provider-agnostic, just choose your favorite provider and select the model you'd like to use in your project.”AI Agent Node page, opening paragraph · checked 2026-09-09
- #7
Aisera Agent Composer (Agent Studio)
Conversational, no-code builder for enterprise AI agents on the Aisera platform.
Best forThe buyer picks the foundation model, Aisera's own or a third party's, and the LLM Gateway can also route automatically between open and closed models for cost and latency.
Model choice: Yes — The buyer picks the foundation model, Aisera's own or a third party's, and the LLM Gateway can also route automatically between open and closed models for cost and latency.“select third-party FMs (like Azure AI, Open AI, Google Vertex AI, Llama 3, AWS Bedrock, and more) to build a robust AI stack that is suited to your enterprise needs.”'Select Your Foundational Model (FM) of Choice' heading and body · checked 2026-09-24
- #8
UiPath Agent Builder
Low-code canvas in UiPath Studio Web for building AI agents that run on the UiPath automation platform.
Best forYou pick the model per agent from the Properties panel, models are provisioned through the AI Trust Layer, and the vendor states a model can be swapped later without rebuilding the agent.
Model choice: Yes — You pick the model per agent from the Properties panel, models are provisioned through the AI Trust Layer, and the vendor states a model can be swapped later without rebuilding the agent.“Model-agnostic by design. Connect any third-party LLM or use UiPath-curated models. Switch models without rebuilding the agent. AI Trust Layer applies regardless of which model the agent talks to.”FAQ 'Evaluating Agent Builder: common questions', question 'Can I bring my own LLM, or am I locked into UiPath models?' · checked 2026-09-03
- #9
Vellum
Open-source personal AI assistant with long-term memory that acts across your tools, in the cloud or self-hosted.
Best forYou pick the model per workspace, per conversation and per action type through inference profiles and action overrides, with custom profiles for providers not built in.
Model choice: Yes — You pick the model per workspace, per conversation and per action type through inference profiles and action overrides, with custom profiles for providers not built in.“Open **Settings → Inference Profiles** and select a different active profile from the dropdown. The change applies workspace-wide immediately — no restart needed.”Model Profiles page, 'Switching profiles' section · checked 2026-09-27
- #10
SimVerified
Open-source AI workspace for building, deploying and running agents across 1,000+ integrations.
Best forDev teams wanting an open-source, API-first workspace to build and deploy AI agents
Model choice: Yes — You pick the model per Agent block across 15+ providers; the default is only a default.“The Agent block supports models from OpenAI, Anthropic, Google, Groq, Cerebras, DeepSeek, xAI, and more, plus local models through Ollama if you self-host.”Getting Started FAQ, 'Can I use a different model?' · checked 2026-09-03
- #11
MindStudio
No-code platform for building, running and deploying AI agents as drag-and-drop workflows.
Best forYou choose the model per block from a large multi-publisher catalogue, can compare models side by side, and can plug in your own keys or endpoints instead.
Model choice: Yes — You choose the model per block from a large multi-publisher catalogue, can compare models side by side, and can plug in your own keys or endpoints instead.“Instantly connect to 200+ AI models via the MindStudio Service Router (no API keys required)”Free plan card, Platform features bullet (repeated on Individual) · checked 2026-09-20
Best forDevelopers and self-hosters who already run their own infrastructure and want one personal AI agent that reaches WhatsApp, Telegram, Slack, Discord, Signal and iMessage instead of a separate app.
Model choice: Yes — You pick the model: provider, authentication and execution runtime are separate layers, and per-agent or per-model runtime policy decides which harness executes a turn.“OpenClaw separates model choice, authentication, and execution runtime.”Models and media providers section, intro paragraph · checked 2026-09-21
- #13
Agno
Python SDK plus self-hosted AgentOS runtime and hosted control plane for building and operating agents.
Best forPython developers who want an Apache 2.0 SDK with memory, knowledge, learning, guardrails and a Control Plane they run inside their own cloud account, and who are comfortable running Docker or a cloud deploy template themselves.
Model choice: Yes — You choose the provider and model and can reassign `agent.model` between turns; the vendor sells the control plane, not inference.“Agno is model-agnostic: bring OpenAI, Anthropic, Google or any supported provider and switch without rewriting your agents.”Home page overview, final sentence · checked 2026-10-11
- #14
Botpress
AI agent platform with a visual studio, a code-first TypeScript ADK and a helpdesk, priced per conversation.
Best forEngineering-led teams building a multi-channel AI support agent who want an open-source, self-hostable core with an optional managed cloud layer.
Model choice: Yes — You choose the models and can mix them across one workflow, per bot or per Autonomous Node; Botpress then routes between your own fast, best and fallback slots, and picks for you only if you set nothing.“Choose and configure the models powering your agent. Mix and match LLMs across different parts of your workflow — optimize for cost, speed, or capability depending on the task.”Page body, 'Everything your support team needs.' feature grid, 'Multi-LLM strategy' tile · checked 2026-09-02
- #15
Glean
Enterprise AI platform for building, governing and running agents on permission-aware company context.
Best forLarge and mid-market enterprises whose biggest AI-agent blocker is fragmented, permission-sensitive knowledge scattered across 100+ internal tools, and who want employees building department-specific agents on that indexed knowledge without writing code.
Model choice: Yes — Admins choose which of 40+ models are available and to whom; auto routing can pick per task instead.“AI usage controls let admins turn models on or off, control model access by user or department, and set usage limits to manage spend by user, agent, or department.”Governance - Model choice on your terms section · checked 2026-09-02
- #16
Salesforce Agentforce
Salesforce's platform for building, deploying and monitoring AI agents on top of CRM data.
Best forSalesforce service, sales, field-service and employee-support teams that need agents to act on CRM records and have Salesforce admin or developer capacity.
Model choice: Yes — The customer selects the model option in Setup and can override it per agent or subagent in Agent Script; leaving the default hands the choice to Salesforce's managed mix.“To change the default model option for Agentforce, go to the Agentforce Agents page in Setup.”Prose above the standard configuration models table, first sentence · checked 2026-09-03
Best forDevelopers and researchers who specifically need an agent whose memory, skills and identity genuinely persist and evolve across long-running sessions, rather than reset on every call.
Model choice: Yes — You pick the model and can switch mid-conversation; memory travels with the agent across providers.“Users can change an agent's underlying model at any time, even mid-conversation.”Opening paragraph · checked 2026-09-02
- #18
VecbaseVerified
Annual membership for member-rate access to a multi-vendor model catalog, plus hosted AI agents.
Best forSmall teams or solo operators who want pre-built AI agent roles, shared files, and OAuth-driven workflows under one credit-based subscription.
Model choice: Yes — The buyer picks the model: each Agent carries its own chosen AI model as a setting, drawn from a catalog spanning Anthropic, OpenAI, Google, DeepSeek, Qwen and Mistral.“An Agent is an AI teammate you set up for a responsibility. It has a name, instructions, a chosen model, a work environment, and access you control.”Section 'Agents and tasks', first paragraph · checked 2026-09-27
- #19
ElevenLabs Agents
Hosted platform for building voice and chat agents, with telephony, SDKs and a choice of LLM.
Best forDevelopers and product teams who want ElevenLabs' voice quality and cloning as the foundation of their agent, and are comfortable assembling the rest of the stack themselves.
Model choice: Yes — You pick the model per agent, plus a backup cascade; LLM usage is billed on top of the plan and varies by model.“ElevenAgents provides a unified interface to connect your agent to multiple models and providers, offering flexibility, reliability, and cost optimization.”Models, opening paragraph · checked 2026-09-02
Best forDevelopers and teams who want an open-source, self-hostable platform to build RAG apps and agents with full data control.
Model choice: Yes — You pick the model per app and per node, from bundled providers or any provider you install and key yourself; workspace defaults are configurable.“Add your own API key to a supported provider when you want higher rate limits or billing through your own provider account.”'Use Your Own Account with a Supported Provider' section · checked 2026-09-02
- #21
Lindy
Slack-native AI teammate that connects to company tools and does delegated work, billed per seat with pooled credits.
Best forTeams that want an AI teammate embedded in Slack and a no-code app builder under the same plan, with usage that pauses at the credit cap rather than overage-billing.
Model choice: Yes — The buyer picks the model per task from a dropdown and can set a default, and Lindy also picks one itself to control credit spend; no tier restricts which models are reachable.“Every plan, trial seats included, gets all models. There's no upsell wall on model choice.”'What every plan gets' section, opening line · checked 2026-09-19
- #22
Relevance AI
Platform for building and running specialist business agents and multi-agent workforces.
Best forRevenue, ops, and customer success teams running 5+ agents in production, who want multi-agent orchestration with evals, tracing, and SSO-grade governance on one bill.
Model choice: Yes — You pick the model per agent, set a fallback model from another provider, and the feature table marks "Bring your own LLM" available on every published tier.“| **Bring your own LLM** | ✓ | ✓ | ✓ |”Complete feature comparison, AI management table, "Bring your own LLM" row · checked 2026-09-22
- #23
LangChain
Open source agent frameworks plus LangSmith, a hosted platform to trace, evaluate, deploy and govern agents.
Best forEngineering teams building a bespoke, production-grade agent who want the largest integration ecosystem plus real stateful control.
Model choice: Yes — You choose the provider everywhere except Fleet's Fast, Pro and Max tiers, where LangChain selects and maintains the underlying model for you; custom configurations can override even those.“All features support custom workspace configurations, so you can use any provider or model—even for features that show a curated list by default.”Feature Access section, note under the table · checked 2026-09-18
- #24
n8n
Workflow automation platform for building and running AI agents on a visual canvas, with code where needed.
Best forOps and automation teams who want to build agentic workflows visually while keeping data on self-hosted infrastructure.
Model choice: Yes — You pick the provider and model per node or per agent, and swap it without rebuilding the workflow; a fallback model can be attached to an agent.“Swap cloud or offline models without rebuilding your workflows.”Build AI agents you can actually follow, 'Build complex AI without getting boxed in' · checked 2026-09-02
Side by side
Scroll sideways to see them all.
| Feature | TaleVerified | LuMay | Dust | Pickaxe | Gumloop | StackAI | Aisera Agent Composer (Agent Studio) | UiPath Agent Builder | Vellum | SimVerified | MindStudio | OpenClaw | Agno | Botpress | Glean | Salesforce Agentforce | Letta | VecbaseVerified | ElevenLabs Agents | Dify | Lindy | Relevance AI | LangChain | n8n |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Description | Open-source project workspace where teams assign tasks to AI coding agents running in sandboxes. | Enterprise agentic AI platform with packaged voice, legal, compliance and workflow agents; SaaS, on-prem or air-gapped. | Platform for building and running company agents on connected tools, data and 20+ models. | No-code platform for building AI agents and selling them through branded portals with billing built in. | Multiplayer AI agent builder: teams build agents over their apps while IT keeps governance and spend control. | No-code enterprise platform for building, deploying and governing AI agents across business systems. | Conversational, no-code builder for enterprise AI agents on the Aisera platform. | Low-code canvas in UiPath Studio Web for building AI agents that run on the UiPath automation platform. | Open-source personal AI assistant with long-term memory that acts across your tools, in the cloud or self-hosted. | Open-source AI workspace for building, deploying and running agents across 1,000+ integrations. | No-code platform for building, running and deploying AI agents as drag-and-drop workflows. | Open-source personal agent runtime you host yourself and message from any chat app. | Python SDK plus self-hosted AgentOS runtime and hosted control plane for building and operating agents. | AI agent platform with a visual studio, a code-first TypeScript ADK and a helpdesk, priced per conversation. | Enterprise AI platform for building, governing and running agents on permission-aware company context. | Salesforce's platform for building, deploying and monitoring AI agents on top of CRM data. | Stateful agent harness, cloud and SDK for agents with persistent, git-versioned memory. | Annual membership for member-rate access to a multi-vendor model catalog, plus hosted AI agents. | Hosted platform for building voice and chat agents, with telephony, SDKs and a choice of LLM. | Open-source platform for building agentic workflows, AI agents and RAG knowledge pipelines. | Slack-native AI teammate that connects to company tools and does delegated work, billed per seat with pooled credits. | Platform for building and running specialist business agents and multi-agent workforces. | Open source agent frameworks plus LangSmith, a hosted platform to trace, evaluate, deploy and govern agents. | Workflow automation platform for building and running AI agents on a visual canvas, with code where needed. |
| Category | Agent platforms | Agent platforms | Agent platforms | Agent platforms | Agent platforms | Agent platforms | Agent platforms | Agent platforms | Agent platforms | Agent platforms | Agent platforms | Agent platforms | Agent platforms, Agent frameworks | Agent platforms | Agent platforms | Agent platforms | Agent platforms, Coding agents, Agent frameworks | Agent platforms | Agent platforms, Voice agents | Agent platforms | Agent platforms | Agent platforms | Agent platforms, Agent frameworks | Agent platforms |
| Pricing | From Free | From $249/month | From Free | From Free | From $37/month | From Free | - | From Free | From Free | From Free | From Free | From Free | From Free | From Free | - | From Free | From Free | From $19.90/year | From Free | From Free | From $29.99/month | From $29/month | From Free | From Free |
| Tags |
Get quotes from the top agents
Describe what you need. We route it to the best-matched providers.
The digestFree
Which agents actually ship.
New agents and articles, by email, at most once a week.
One-click unsubscribe
This ranking
- 24 agents ranked
- paid plans $2-$150
- 17 free or freemium
- verified October 11, 2026