Skip to main content
Arize+26 Positive

Where It Fits

Where does Arize belong in the stack?

Arize's primary role: LLM & Agent Observability and Evaluation. It is Core across Evaluate and Operate and touches Model, Build, and Data.

  1. Model

    1. Model APIs: Touches
    2. Model gateway: Touches

  2. Build

    1. Orchestration: Touches
    2. Tool use: Touches

  3. Data

    1. Retrieval: Touches

  4. Evaluate

    1. Evaluation: Core

  5. Operate

    1. Observability: Core
    2. Cloud deployment: Touches
    3. Guardrails: Supports
Layer by layer

Arize beside the rest of its stack

Every product we cover on AI Application Platform, on the layers it owns, placed by what its practitioners report. Pick any of them to compare.

Read as a table

Signals from

Show products that

Activating a product opens its read here. Activating the selected product opens its hub.

Arize+26Positive

Each product sits on the layers it owns, placed left to right by how far its positive sources lead its negative ones. A disc's area is its sources in this view and its tone is its band. Products with fewer than 20 sources from 15 authors have no net and sit at the right, under Unscored. The teal line joins Arize across its layers.

Read the field as a table
AI Application Platform, Teams and leaders: every product with its layers, its Overall Signal and the sentiment split behind it
ProductCore onSupportsOverall SignalNetSourcesPositiveMixedNegative
Claude Agent SDKOrchestrationTool use, Cloud deployment, GuardrailsStrong positive+52221381
BraintrustEvaluation, ObservabilityModel gateway, Tool useStrong positive+503420113
LangfuseEvaluation, ObservabilityNonePositive+462612140
JevSupporting onlyModel APIs, Model gateway, Tool use, Retrieval, Evaluation, GuardrailsPositive+402512112
Datadog Agent ObservabilityEvaluation, ObservabilityGuardrailsPositive+32269161
ArizeEvaluation, ObservabilityGuardrailsPositive+262711124
Claude APIModel APIs, Tool useOrchestration, Retrieval, Cloud deploymentPositive+255222219
Amazon BedrockModel APIs, Cloud deploymentModel gateway, Orchestration, Tool use, Retrieval, Evaluation, Observability, GuardrailsMixed+957251220
LiteLLMModel gatewayTool use, Observability, GuardrailsMixed+83710216
OpenAI APIModel APIs, Tool useOrchestration, Retrieval, Observability, Cloud deployment, GuardrailsMixed+365222320
Gemini APIModel APIs, Tool useOrchestration, Retrieval, Cloud deployment, GuardrailsMixed074242525
pgvectorRetrievalCloud deploymentNegative−29245811
MastraOrchestrationModel gateway, Tool use, Retrieval, Evaluation, Observability, Cloud deployment, GuardrailsNegative−36254813
QdrantRetrievalCloud deploymentNegative−404181023
PineconeRetrievalTool use, Cloud deploymentStrong negative−63333624
LangSmithEvaluation, ObservabilityModel gateway, Orchestration, Tool use, Cloud deploymentBelow minimumnone19973
AI SDKOrchestration, Tool useModel gateway, Retrieval, ObservabilityBelow minimumnone18891
LangGraphOrchestrationTool use, Cloud deploymentBelow minimumnone181053
PortkeyModel gatewayObservability, GuardrailsBelow minimumnone181143
Fireworks AICloud deploymentModel APIs, Model gateway, RetrievalBelow minimumnone16655
Agent PlatformModel APIs, Cloud deploymentModel gateway, Orchestration, Tool use, Retrieval, Evaluation, Observability, GuardrailsBelow minimumnone13715
OpenRouterModel gatewayModel APIs, Observability, GuardrailsBelow minimumnone11443
Microsoft FoundryModel APIs, Cloud deploymentModel gateway, Orchestration, Tool use, Retrieval, Evaluation, Observability, GuardrailsBelow minimumnone8125
OpenAI Agents SDKOrchestrationTool use, Observability, GuardrailsBelow minimumnone7322
CrewAIOrchestrationTool use, Retrieval, Observability, Cloud deployment, GuardrailsBelow minimumnone4130
Together AICloud deploymentModel APIsBelow minimumnone1001
DeepSeek APIModel APIsTool use, RetrievalBelow minimumnone0000

Each author counts once.

Stack Footprint

What is Arize used for, and by whom?

See where it fits

AI Observability, also listed under AI engineering, observability, and developer tools.

Arize across the AI Application Platform stack. Bar height is its role on each layer.

  1. Model

    1. Model APIs: Touches

      Model APIs, touches. Arize records application calls to OpenAI, Anthropic, Google, Bedrock, and other providers. Its playground and LLM judges use your configured provider keys. It supplies no models.

    2. Model gateway: Touches

      Model gateway, touches. AX connects to gateways such as LiteLLM, OpenRouter, and TrueFoundry for playground and judge calls. Arize traces those calls. The gateway controls routing and spend limits.

  2. Build

    1. Orchestration: Touches

      Orchestration, touches. OpenInference auto-instruments LangGraph, LangChain, LlamaIndex, CrewAI, DSPy, the Vercel AI SDK, and other frameworks. The framework builds and runs the agent.

    2. Tool use: Touches

      Tool use, touches. Arize records tool arguments and outputs. Phoenix evaluates tool selection and invocation. The application executes the tools.

  3. Data

    1. Retrieval: Touches

      Retrieval, touches. Retriever spans show returned documents and evaluators score relevance. The vector store handles search and indexing, including embeddings.

  4. Evaluate

    1. Evaluation: Core

      Evaluation, core. Phoenix and AX evaluate prompt and model changes using datasets and experiments. They support LLM judges and code evaluators, plus human annotations. AX adds agent-as-a-judge and labeling queues, with online production evals and CI templates.

  5. Operate

    1. Observability: Core

      Observability, core. Arize traces LLM apps and agents over OpenTelemetry. AX combines sessions and token-cost tracking with dashboards, online evals, monitors, and alerts. Phoenix self-hosts the same tracing.

    2. Cloud deployment: Touches

      Cloud deployment, touches. AX runs as SaaS in US, EU, or Canada regions, or on Kubernetes under Enterprise. Phoenix runs on Docker or Kubernetes. Neither hosts your application or models.

    3. Guardrails: Supports

      Guardrails, supports. Arize Guards screen user inputs and LLM outputs at runtime. Failed messages trigger corrective actions such as a default response, a retry, or blocking the output.

Used for AI feature development, agent development, testing, and debugging, by AI engineers, platform teams, and data teams.

Business Area
Product & Engineering
Function
Software Development
Operating Stack
AI Application Platform
Primary Role
LLM & Agent Observability and Evaluation

How to read this map. Each layer lists the products that structurally own it, so a product that only touches a layer isn't listed among its owners. Arize is underlined in teal where it is Core, and its rows sit a shade lighter; where it supports or touches a layer, that row names it first.

    Model

    Arize: touches on 2 of 2 layers

    1. Model APIs

      Hosted models an application calls for generation, reasoning, and vision, under the provider's rate limits, pricing, and data terms.

      • Arize touchesAdjacentArize records application calls to OpenAI, Anthropic, Google, Bedrock, and other providers. Its playground and LLM judges use your configured provider keys. It supplies no models.
      • Amazon BedrockAI Model APIAmazon BedrockAmazon Web Services+9 MixedAWS service for building on models from Amazon, Anthropic, OpenAI, DeepSeek, and others. AgentCore, Knowledge Bases, and Guardrails add agents, retrieval, and filters. Usage bills per token on AWS.Owns this layerModel APIsOpen product page
      • Claude APIAI Model APIClaude APIAnthropic+25 PositiveAnthropic's developer platform for building AI features and agents on Claude models: the Messages API, tool use, prompt caching, batch processing, and the Agent SDK.Owns this layerModel APIsOpen product page
      • DeepSeek APIAI Model APIDeepSeek APIDeepSeek+57 Strong positiveDeepSeek's first-party API serves deepseek-flash (DeepSeek-V4.1-Flash-1017) and deepseek-v4-pro with a 1M-token context, in OpenAI- and Anthropic-compatible formats. It bills per million tokens from a prepaid balance, with cheap cache hits and half-price off-peak hours, and stores data in the People's Republic of China.Owns this layerModel APIsOpen product page
      • Gemini APIAI Model APIGemini APIGoogle0 MixedGoogle's API for Gemini features and agents, reached with an AI Studio key or the Gemini Enterprise Agent Platform. It supports function calling, built-in tools, context caching, batch, Flex, and Priority inference.Owns this layerModel APIsOpen product page
      • Gemini Enterprise Agent PlatformAI Model APIGemini Enterprise Agent PlatformGoogle−27 NegativeGoogle Cloud platform, formerly Vertex AI, for building on Gemini, Claude and open models from Model Garden. The Agent Development Kit, Agent Runtime and RAG Engine add agents and retrieval. Usage bills per token through Google Cloud.Owns this layerModel APIsOpen product page
      • Microsoft FoundryAI Model APIMicrosoft FoundryMicrosoft−26 NegativeAzure platform, formerly Azure AI Foundry, for building on OpenAI, Anthropic, Meta, DeepSeek and Microsoft models. Foundry Agent Service, evaluations and model router add agents and routing. Usage bills per token or per provisioned unit on Azure.Owns this layerModel APIsOpen product page
      • OpenAI APIAI Model APIOpenAI APIOpenAI+3 MixedOpenAI's platform for teams building AI features and agents on GPT models. The Responses API supports function calling and remote MCP servers. Prompt caching, Batch, and Flex reduce usage costs, and the Agents SDK runs agents.Owns this layerModel APIsOpen product page

    2. Model gateways & routing

      One interface in front of several models or providers that routes requests, fails over, and enforces spend and rate limits.

      • Arize touchesAdjacentAX connects to gateways such as LiteLLM, OpenRouter, and TrueFoundry for playground and judge calls. Arize traces those calls. The gateway controls routing and spend limits.
      • LiteLLMAI GatewayLiteLLMBerriAI+8 MixedBerriAI's self-hosted gateway and Python SDK expose 100+ model providers through one OpenAI-format API. The MIT-licensed core includes virtual keys, budgets, rate limits, fallbacks, and spend tracking. Enterprise adds SSO and audit logs, plus support.Owns this layerModel gateways & routingOpen product page
      • OpenRouterAI GatewayOpenRouterOpenRouter+10 MixedOpenRouter's hosted gateway routes one OpenAI-compatible API to 500+ models from 80+ providers, with provider fallback, per-key credit limits, workspaces, guardrails, and data-policy routing. Tokens bill at provider list price from prepaid credits, with a fee on credit purchases. Stripe agreed to acquire OpenRouter on August 19, 2026.Owns this layerModel gateways & routingOpen product page
      • PortkeyAI GatewayPortkeyPalo Alto Networks0 MixedPortkey's gateway puts one OpenAI-compatible API, fallbacks, load balancing, request logs, and guardrails in front of a team's own model API keys, as a hosted service, a hybrid data plane in your VPC, or an MIT-licensed open-source gateway. Palo Alto Networks completed its purchase on May 29, 2026 and sells it as Prisma AIRS AI Gateway.Owns this layerModel gateways & routingOpen product page
      • Vercel AI Gateway

    Build

    Arize: touches on 2 of 2 layers

    1. Orchestration & agent frameworks

      Code that composes model calls, tools, memory, and control flow into multi-step workflows and agents.

      • Arize touchesAdjacentOpenInference auto-instruments LangGraph, LangChain, LlamaIndex, CrewAI, DSPy, the Vercel AI SDK, and other frameworks. The framework builds and runs the agent.
      • Claude Agent SDKAgent FrameworkClaude Agent SDKAnthropic+52 Strong positiveAnthropic's SDK, formerly the Claude Code SDK, runs the Claude Code binary inside your own service, with built-in tools, subagents, hooks, MCP, permissions, and sessions. It calls Claude models only and is billed at Claude API token prices or against Max and Team plan credits.Owns this layerOrchestration & agent frameworksOpen product page
      • CrewAIAgent FrameworkCrewAICrewAI−7 MixedCrewAI's MIT-licensed Python framework builds crews of role-based agents inside event-driven flows, on models from any vendor. CrewAI AMP deploys, traces, and governs them, free for 50 executions a month and custom-priced on Enterprise.Owns this layerOrchestration & agent frameworksOpen product page
      • LangGraphAgent FrameworkLangGraphLangChain+25 PositiveLangChain's MIT-licensed runtime builds agents as graphs with shared state in Python and JavaScript, with or without LangChain. It adds checkpoints, human interrupts, and streaming. LangSmith Deployment offers paid hosting.Owns this layerOrchestration & agent frameworksOpen product page
      • MastraAgent FrameworkMastraMastra−36 NegativeMastra is a TypeScript framework for agents, typed workflows, memory, and evals, Apache 2.0 outside its ee/ directories. Mastra Platform hosts and traces them: Starter is free with monthly allowances, Teams is US$250 a month, and Enterprise is custom.Owns this layerOrchestration & agent frameworksOpen product page
      • OpenAI Agents SDKAgent FrameworkOpenAI Agents SDKOpenAI−17 MixedOpenAI's MIT-licensed SDK runs agents with tools, handoffs, guardrails, sessions, approvals, MCP tools, and tracing inside your own service. It calls OpenAI models through the Responses API by default, reaches other models through beta adapters, and bills at OpenAI API token prices.Owns this layerOrchestration & agent frameworksOpen product page
      • AI SDKAgent FrameworkAI SDKVercel+36 PositiveVercel's Apache 2.0 TypeScript toolkit ships on npm as ai. One API covers text, structured output, tools, and agents across 46 first-party model integrations. React, Vue, Svelte, and Angular hooks stream chat. Vercel AI Gateway is the default model route.Owns this layerOrchestration & agent frameworksOpen product page

    2. Tool use & integrations

      Letting a model call functions, APIs, and MCP servers, and act on what they return.

      • Arize touchesAdjacentArize records tool arguments and outputs. Phoenix evaluates tool selection and invocation. The application executes the tools.
      • Claude APIAI Model APIClaude APIAnthropic+25 PositiveAnthropic's developer platform for building AI features and agents on Claude models: the Messages API, tool use, prompt caching, batch processing, and the Agent SDK.Owns this layerTool use & integrationsOpen product page
      • Gemini APIAI Model APIGemini APIGoogle0 MixedGoogle's API for Gemini features and agents, reached with an AI Studio key or the Gemini Enterprise Agent Platform. It supports function calling, built-in tools, context caching, batch, Flex, and Priority inference.Owns this layerTool use & integrationsOpen product page
      • OpenAI APIAI Model APIOpenAI APIOpenAI+3 MixedOpenAI's platform for teams building AI features and agents on GPT models. The Responses API supports function calling and remote MCP servers. Prompt caching, Batch, and Flex reduce usage costs, and the Agents SDK runs agents.Owns this layerTool use & integrationsOpen product page
      • AI SDKAgent FrameworkAI SDKVercel+36 PositiveVercel's Apache 2.0 TypeScript toolkit ships on npm as ai. One API covers text, structured output, tools, and agents across 46 first-party model integrations. React, Vue, Svelte, and Angular hooks stream chat. Vercel AI Gateway is the default model route.Owns this layerTool use & integrationsOpen product page

    Data

    Arize: touches on 1 of 1 layer

    1. Retrieval & grounding

      Embedding, indexing, and retrieving the documents and records an application grounds its answers in.

      • Arize touchesAdjacentRetriever spans show returned documents and evaluators score relevance. The vector store handles search and indexing, including embeddings.
      • pgvectorVector DatabasepgvectorThe pgvector project−29 NegativePostgres extension that stores vectors with the rest of your data and searches them exactly or with HNSW and IVFFlat indexes. Free under the PostgreSQL License, self-installed or on managed hosts such as Neon, Supabase, Cloud SQL, Amazon RDS and Azure.Owns this layerRetrieval & groundingOpen product page
      • PineconeVector DatabasePineconePinecone Systems−63 Strong negativeManaged vector database serving full-text, semantic, sparse and hybrid search from one index, with hosted embedding and reranking and namespaces per tenant. Runs on AWS, GCP and Azure, or in your own cloud with Bring Your Own Cloud on Enterprise.Owns this layerRetrieval & groundingOpen product page
      • QdrantVector DatabaseQdrantQdrant Solutions GmbH−40 NegativeVector database for dense, sparse and multivector search with JSON payload filters, hybrid search and built-in quantization. Self-hosted under the Apache License 2.0, or Qdrant Cloud on AWS, GCP and Azure with a free tier and usage-based Standard billing.Owns this layerRetrieval & groundingOpen product page
      • Voyage AI

    Evaluate

    Arize: core on 1 of 1 layer

    1. Evaluation & testing

      Scoring model and agent output against datasets and graders, so a prompt or model change is measured before it ships.

      • Arize
      • BraintrustAI ObservabilityBraintrustBraintrust+50 Strong positiveBraintrust evaluates and traces AI apps and agents. Dataset experiments and scorers test prompt and model changes, plus code, before release. Production tracing and online scoring, plus Topics, track results afterward. It runs in Braintrust's US or EU cloud, or, on Enterprise, with a data plane in your own cloud.Owns this layerEvaluation & testingOpen product page
      • Datadog Agent ObservabilityAI ObservabilityDatadog Agent ObservabilityDatadog+32 PositiveDatadog Agent Observability, sold as LLM Observability until 2026, traces LLM apps and agents and evaluates their output. It shares one trace ID with Datadog APM, infrastructure, and user monitoring. It bills only LLM spans, one per model call, and can be bought without other Datadog products.Owns this layerEvaluation & testingOpen product page
      • LangfuseAI ObservabilityLangfuseClickHouse+46 PositiveLangfuse traces and evaluates LLM apps and agents. It versions prompts on Langfuse Cloud or self-hosted under the MIT license. ClickHouse acquired it in January 2026.Owns this layerEvaluation & testingOpen product page
      • LangSmithAI ObservabilityLangSmithLangChain+17 MixedLangChain's platform for teams tracing and evaluating LLM applications and agents. It also deploys agents on LangChain's cloud or your infrastructure, with or without the LangChain frameworks.Owns this layerEvaluation & testingOpen product page

    Operate

    Arize: core on 1 of 3 layers; supports on 1 of 3 layers; touches on 1 of 3 layers

    1. Observability & tracing

      Tracing production requests across model calls and agent steps, with the cost, latency, and errors of each.

      • Arize
      • BraintrustAI ObservabilityBraintrustBraintrust+50 Strong positiveBraintrust evaluates and traces AI apps and agents. Dataset experiments and scorers test prompt and model changes, plus code, before release. Production tracing and online scoring, plus Topics, track results afterward. It runs in Braintrust's US or EU cloud, or, on Enterprise, with a data plane in your own cloud.Owns this layerObservability & tracingOpen product page
      • Datadog Agent ObservabilityAI ObservabilityDatadog Agent ObservabilityDatadog+32 PositiveDatadog Agent Observability, sold as LLM Observability until 2026, traces LLM apps and agents and evaluates their output. It shares one trace ID with Datadog APM, infrastructure, and user monitoring. It bills only LLM spans, one per model call, and can be bought without other Datadog products.Owns this layerObservability & tracingOpen product page
      • LangfuseAI ObservabilityLangfuseClickHouse+46 PositiveLangfuse traces and evaluates LLM apps and agents. It versions prompts on Langfuse Cloud or self-hosted under the MIT license. ClickHouse acquired it in January 2026.Owns this layerObservability & tracingOpen product page
      • LangSmithAI ObservabilityLangSmithLangChain+17 MixedLangChain's platform for teams tracing and evaluating LLM applications and agents. It also deploys agents on LangChain's cloud or your infrastructure, with or without the LangChain frameworks.Owns this layerObservability & tracingOpen product page

    2. Cloud deployment & capacity

      Running model workloads inside a cloud account or region with the throughput, data residency, and billing the business requires.

      • Arize touchesAdjacentAX runs as SaaS in US, EU, or Canada regions, or on Kubernetes under Enterprise. Phoenix runs on Docker or Kubernetes. Neither hosts your application or models.
      • Amazon BedrockAI Model APIAmazon BedrockAmazon Web Services+9 MixedAWS service for building on models from Amazon, Anthropic, OpenAI, DeepSeek, and others. AgentCore, Knowledge Bases, and Guardrails add agents, retrieval, and filters. Usage bills per token on AWS.Owns this layerCloud deployment & capacityOpen product page
      • Fireworks AIInference HostingFireworks AIFireworks AI−17 MixedFireworks AI serves open models through Serverless Inference, multi-tenant inference on Fireworks-managed infrastructure billed per token, and through on-demand deployments on dedicated GPUs billed per GPU second. It offers supervised and reinforcement fine-tuning and serves fine-tuned models for the same price as base models.Owns this layerCloud deployment & capacityOpen product page
      • Gemini Enterprise Agent PlatformAI Model APIGemini Enterprise Agent PlatformGoogle−27 NegativeGoogle Cloud platform, formerly Vertex AI, for building on Gemini, Claude and open models from Model Garden. The Agent Development Kit, Agent Runtime and RAG Engine add agents and retrieval. Usage bills per token through Google Cloud.Owns this layerCloud deployment & capacityOpen product page
      • Microsoft FoundryAI Model APIMicrosoft FoundryMicrosoft−26 NegativeAzure platform, formerly Azure AI Foundry, for building on OpenAI, Anthropic, Meta, DeepSeek and Microsoft models. Foundry Agent Service, evaluations and model router add agents and routing. Usage bills per token or per provisioned unit on Azure.Owns this layerCloud deployment & capacityOpen product page
      • Together AIInference HostingTogether AITogether AI−49 NegativeTogether AI serves open models through a serverless per-token API compatible with the OpenAI SDKs, provisioned throughput with a monthly success commitment, dedicated endpoints billed by the minute, fine-tuning and multi-node GPU clusters. Accounts are fully prepaid, with a minimum US$15 credit purchase.Owns this layerCloud deployment & capacityOpen product page
      • Microsoft Foundry
      • Groq

    3. Guardrails & AI security

      Screening prompts, responses, and agent actions for prompt injection, sensitive data, and policy violations, and blocking or logging what fails.

      • Arize supportsSupportingArize Guards screen user inputs and LLM outputs at runtime. Failed messages trigger corrective actions such as a default response, a retry, or blocking the output.
      • Prisma AIRS
      • NeMo Guardrails

    Core, Supports, and Touches describe how much of a layer a product covers. They say nothing about quality.