How Baseten’s scores are calculated

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

• [probe] https://docs.baseten.co/llms.txt“PROBE llms.txt: HTTP 200 at https://docs.baseten.co/llms.txt # Baseten - [Baseten overview](https://docs.baseten.co/overview.md): Run hosted models, deploy custom models, and train”
• [probe] https://docs.baseten.co/overview.md“PROBE docs-md: HTTP 200 at https://docs.baseten.co/overview.md > ## Documentation Index > Fetch the complete documentation index at: https://docs.baseten.co/llms.txt > Use this file t”
• [claimed-docs] https://docs.baseten.co/agent-setup.md“Install the Baseten skill and MCP servers so your coding agent can manage your Baseten workspace and search these docs.”
• [probe] https://docs.baseten.co/agent-setup“official MCP server documented at https://docs.baseten.co/agent-setup”
• [probe] https://docs.baseten.co/mcp“PROBE mcp-endpoint (2026-09-04): POST initialize to https://docs.baseten.co/mcp answered HTTP 200 with a JSON-RPC/MCP response (event: message data: {"result":{"protocolVersion":"2025-06-18","capabilities":{"tools":{"listChanged":true},"resources":{"listChanged":true}) — a live, publicly reachable MCP server.”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

• [github] https://github.com/basetenlabs/truss“You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it. No Python code, no Dockerfile, no container management.”
• [github] https://github.com/basetenlabs/truss“Deploying a model to Baseten via Truss turns a Hugging Face model into a production-ready API endpoint. You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it.”
• [claimed-docs] https://docs.baseten.co/inference/overview.md“Async inference returns a request ID quickly and completes later through webhook or polling, which suits batch work, long documents”
• [claimed-docs] https://docs.baseten.co/inference/overview.md“Async inference returns a request ID quickly and completes later through webhook or polling, which suits batch work, long documents, or any case where the caller should not hold a connection open for minutes.”
• [claimed-docs] https://docs.baseten.co/overview“Call hosted models through an OpenAI-compatible API, deploy your own models on dedicated infrastructure”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/pricing-and-limits.md“x-ratelimit-remaining-requests: Reports how many requests remain before you reach the request rate limit.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/pricing-and-limits.md“You can also set a workspace budget and query usage by API key or model.”
• [claimed-docs] https://docs.baseten.co/overview“a `config.yaml` can define the model, hardware, and inference engine without custom serving code”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

• [claimed-docs] https://docs.baseten.co/agent-setup.md“Install the Baseten skill and MCP servers so your coding agent can manage your Baseten workspace and search these docs.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/coding-agents.md“Connect Claude Code, Codex CLI, or Pi with Baseten Switch.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/coding-agents.md“Use [Baseten Switch](/reference/cli/baseten-switch) to route requests from Claude Code or Codex CLI to Model APIs.”
• [probe] https://docs.baseten.co/mcp“PROBE mcp-endpoint (2026-09-04): POST initialize to https://docs.baseten.co/mcp answered HTTP 200 with a JSON-RPC/MCP response (event: message data: {"result":{"protocolVersion":"2025-06-18","capabilities":{"tools":{"listChanged":true},"resources":{"listChanged":true}) — a live, publicly reachable MCP server.”
• [probe] https://docs.baseten.co/agent-setup“official MCP server documented at https://docs.baseten.co/agent-setup”

Connect an agent via an official MCP serverweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

• [claimed-docs] https://docs.baseten.co/agent-setup.md“Install the Baseten skill and MCP servers so your coding agent can manage your Baseten workspace and search these docs.”
• [probe] https://docs.baseten.co/agent-setup“official MCP server documented at https://docs.baseten.co/agent-setup”
• [probe] https://docs.baseten.co/mcp“PROBE mcp-endpoint (2026-09-04): POST initialize to https://docs.baseten.co/mcp answered HTTP 200 with a JSON-RPC/MCP response (event: message data: {"result":{"protocolVersion":"2025-06-18","capabilities":{"tools":{"listChanged":true},"resources":{"listChanged":true}) — a live, publicly reachable MCP server.”

Use an official CLIweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

• [github] https://github.com/basetenlabs/truss“You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it. No Python code, no Dockerfile, no container management.”
• [github] https://github.com/basetenlabs/truss“Deploying a model to Baseten via Truss turns a Hugging Face model into a production-ready API endpoint. You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it.”
• [claimed-docs] https://docs.baseten.co/training/index.md“Deploy any synced checkpoint with one CLI command”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/coding-agents.md“Use [Baseten Switch](/reference/cli/baseten-switch) to route requests from Claude Code or Codex CLI to Model APIs.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/coding-agents.md“Connect Claude Code, Codex CLI, or Pi with Baseten Switch.”

Drive the product through a documented public APIweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

• [claimed-docs] https://docs.baseten.co/overview“They support the OpenAI Chat Completions API and the Anthropic Messages API in beta, so you can use familiar client SDKs.”
• [claimed-docs] https://docs.baseten.co/overview“Call hosted models through an OpenAI-compatible API, deploy your own models on dedicated infrastructure”
• [claimed-docs] https://docs.baseten.co/inference/overview.md“Async inference returns a request ID quickly and completes later through webhook or polling, which suits batch work, long documents”
• [claimed-docs] https://docs.baseten.co/training/index.md“Fine-tuning or running RL on a supported base model: Loops provisions a dedicated trainer and paired sampler, and each training step is an API call from a Python loop you write.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/pricing-and-limits.md“Model APIs bill by token and enforce request and token rate limits. You can also set a workspace budget and query usage by API key or model.”
• [probe] https://inference.baseten.co/v1/models“PROBE models-endpoint (2026-09-04): GET https://inference.baseten.co/v1/models without a key returned HTTP 401 (No Authorization header provided) — the OpenAI-style models endpoint is live and speaks JSON, but enumerating the catalog requires an API key.”
• [probe] https://docs.baseten.co/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.baseten.co/openapi.json, https://docs.baseten.co/swagger.json, https://docs.baseten.co/api/openapi.json, https://docs.baseten.co/.well-known/openapi.json)”
• [github] https://github.com/basetenlabs/truss“You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it. No Python code, no Dockerfile, no container management.”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

• [claimed-docs] https://docs.baseten.co/inference/model-apis/pricing-and-limits.md“Model APIs bill by token and enforce request and token rate limits. You can also set a workspace budget and query usage by API key or model.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/pricing-and-limits.md“To monitor token and request consumption by API key or model, see Usage.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/pricing-and-limits.md“You can also set a workspace budget and query usage by API key or model.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/pricing-and-limits.md“To raise a Basic account's limits, request email verification. You can also use that form to move to Pro or Enterprise.”

Build against official SDKsweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

• [github] https://github.com/basetenlabs/truss“Write once, run anywhere: Package model code, weights, and dependencies with a model server that behaves the same in development and production.”
• [github] https://github.com/basetenlabs/truss“You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it. No Python code, no Dockerfile, no container management.”
• [github] https://github.com/basetenlabs/truss“Truss lets you serve models with the Baseten Inference Stack as well as deploy models from any open-source framework: vLLM, SGLang, TensorRT-LLM, `transformers`, `diffusers`, PyTorch, TensorFlow, and more.”
• [github] https://github.com/basetenlabs/truss“Deploying a model to Baseten via Truss turns a Hugging Face model into a production-ready API endpoint. You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it.”
• [claimed-docs] https://docs.baseten.co/overview“They support the OpenAI Chat Completions API and the Anthropic Messages API in beta, so you can use familiar client SDKs.”
• [claimed-docs] https://docs.baseten.co/inference/structured-outputs.md“Because Baseten exposes an OpenAI-compatible endpoint, you can use LangChain's `ChatOpenAI` with `with_structured_output` by pointing `base_url` at Baseten”
• [claimed-docs] https://docs.baseten.co/overview“Call hosted models through an OpenAI-compatible API, deploy your own models on dedicated infrastructure”

Subscribe to events via webhooksweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

• [claimed-docs] https://docs.baseten.co/inference/overview.md“Async inference returns a request ID quickly and completes later through webhook or polling, which suits batch work, long documents”
• [claimed-docs] https://docs.baseten.co/inference/overview.md“Async inference returns a request ID quickly and completes later through webhook or polling, which suits batch work, long documents, or any case where the caller should not hold a connection open for minutes.”
• [claimed-docs] https://docs.baseten.co/inference/overview.md“Async inference returns a request ID quickly and completes later through webhook or polling”

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

• [probe] https://docs.baseten.co/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.baseten.co/openapi.json, https://docs.baseten.co/swagger.json, https://docs.baseten.co/api/openapi.json, https://docs.baseten.co/.well-known/openapi.json)”
• [claimed-docs] https://docs.baseten.co/inference/structured-outputs.md“Structured outputs let you generate text that conforms to specific JSON schemas, providing reliable data extraction and controlled text generation.”
• [claimed-docs] https://docs.baseten.co/inference/function-calling.md“Function calling* (also called *tool calling*) lets a model choose a tool and produce its arguments from a user request.”
• [claimed-docs] https://docs.baseten.co/inference/streaming.md“Return model output token by token as it is generated.”

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

• [probe] https://docs.baseten.co/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.baseten.co/openapi.json, https://docs.baseten.co/swagger.json, https://docs.baseten.co/api/openapi.json, https://docs.baseten.co/.well-known/openapi.json)”
• [claimed-docs] https://docs.baseten.co/overview“They support the OpenAI Chat Completions API and the Anthropic Messages API in beta, so you can use familiar client SDKs.”
• [claimed-docs] https://docs.baseten.co/overview“Call hosted models through an OpenAI-compatible API, deploy your own models on dedicated infrastructure”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 4 (quality) × 0.6 (partial) = 2.4 of 10 max

• [claimed-docs] https://docs.baseten.co/overview“They also support stable environments for development, staging, and production.”
• [github] https://github.com/basetenlabs/truss“Write once, run anywhere: Package model code, weights, and dependencies with a model server that behaves the same in development and production.”

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

• [claimed-docs] https://docs.baseten.co/inference/model-apis/deprecation.md“Migrate to a dedicated deployment with the deprecated model weights. Contact us for assistance.”
• [probe] https://docs.baseten.co/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.baseten.co/openapi.json, https://docs.baseten.co/swagger.json, https://docs.baseten.co/api/openapi.json, https://docs.baseten.co/.well-known/openapi.json)”

Do everything through the API that I can do in the UIweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

• [github] https://github.com/basetenlabs/truss“You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it. No Python code, no Dockerfile, no container management.”
• [claimed-docs] https://docs.baseten.co/training/index.md“Your Axolotl config, TRL script, or custom loop runs unchanged in a container. Baseten provisions the GPUs, syncs checkpoints as your job saves them, and deploys any checkpoint as a production endpoint.”
• [claimed-docs] https://docs.baseten.co/training/index.md“Deploy any synced checkpoint with one CLI command”
• [claimed-docs] https://docs.baseten.co/training/index.md“Loops provisions a dedicated trainer and paired sampler, and each training step is an API call from a Python loop you write.”
• [claimed-docs] https://docs.baseten.co/inference/overview.md“Async inference returns a request ID quickly and completes later through webhook or polling, which suits batch work, long documents”
• [claimed-docs] https://docs.baseten.co/inference/structured-outputs.md“Structured outputs let you generate text that conforms to specific JSON schemas, providing reliable data extraction and controlled text generation.”
• [claimed-docs] https://docs.baseten.co/inference/function-calling.md“Function calling* (also called *tool calling*) lets a model choose a tool and produce its arguments from a user request.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/pricing-and-limits.md“You can also set a workspace budget and query usage by API key or model.”
• [probe] https://docs.baseten.co/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.baseten.co/openapi.json, https://docs.baseten.co/swagger.json, https://docs.baseten.co/api/openapi.json, https://docs.baseten.co/.well-known/openapi.json)”

Export all of my data in open formats and leaveweight 3

3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

• [github] https://github.com/basetenlabs/truss“Write once, run anywhere: Package model code, weights, and dependencies with a model server that behaves the same in development and production.”
• [github] https://github.com/basetenlabs/truss“You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it. No Python code, no Dockerfile, no container management.”
• [claimed-docs] https://docs.baseten.co/training/index.md“Your Axolotl config, TRL script, or custom loop runs unchanged in a container. Baseten provisions the GPUs, syncs checkpoints as your job saves them, and deploys any checkpoint as a production endpoint.”
• [claimed-docs] https://docs.baseten.co/training/index.md“Deploy any synced checkpoint with one CLI command”
• [claimed-docs] https://docs.baseten.co/concepts/howbasetenworks.md“Baseten provisions GPUs through MCM, runs your training container, and syncs checkpoints to storage as the job progresses.”

Read the product's source under an open licenseweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

• [github] https://github.com/basetenlabs/truss“Write once, run anywhere: Package model code, weights, and dependencies with a model server that behaves the same in development and production.”
• [github] https://github.com/basetenlabs/truss“You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it. No Python code, no Dockerfile, no container management.”
• [github] https://github.com/basetenlabs/truss“Fast developer loop: Iterate with live reload, skip Docker and Kubernetes configuration, and use a batteries-included serving environment.”
• [github] https://github.com/basetenlabs/truss“Support for all Python frameworks: From `transformers` and `diffusers` to PyTorch and TensorFlow to vLLM, SGLang, and TensorRT-LLM, Truss supports models created and served with any framework.”
• [github] https://github.com/basetenlabs/truss“Truss lets you serve models with the Baseten Inference Stack as well as deploy models from any open-source framework: vLLM, SGLang, TensorRT-LLM, `transformers`, `diffusers`, PyTorch, TensorFlow, and more.”
• [github] https://github.com/basetenlabs/truss“Deploying a model to Baseten via Truss turns a Hugging Face model into a production-ready API endpoint. You write a `config.yaml` that specifies the model, the hardware, and the engine, then `uvx truss push` builds a TensorRT-optimized container and deploys it.”

Self-host the core productweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Get AI-generated insights and suggestions from my data inside the productweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

• [claimed-docs] https://docs.baseten.co/agent-setup.md“Install the Baseten skill and MCP servers so your coding agent can manage your Baseten workspace and search these docs.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/coding-agents.md“Connect Claude Code, Codex CLI, or Pi with Baseten Switch.”
• [claimed-docs] https://docs.baseten.co/inference/model-apis/coding-agents.md“Use [Baseten Switch](/reference/cli/baseten-switch) to route requests from Claude Code or Codex CLI to Model APIs.”
• [probe] https://docs.baseten.co/agent-setup“official MCP server documented at https://docs.baseten.co/agent-setup”
• [probe] https://docs.baseten.co/mcp“PROBE mcp-endpoint (2026-09-04): POST initialize to https://docs.baseten.co/mcp answered HTTP 200 with a JSON-RPC/MCP response (event: message data: {"result":{"protocolVersion":"2025-06-18","capabilities":{"tools":{"listChanged":true},"resources":{"listChanged":true}) — a live, publicly reachable MCP server.”

Operate the product with natural-language commandsweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

• [claimed-docs] https://docs.baseten.co/agent-setup.md“Install the Baseten skill and MCP servers so your coding agent can manage your Baseten workspace and search these docs.”
• [probe] https://docs.baseten.co/agent-setup“official MCP server documented at https://docs.baseten.co/agent-setup”
• [probe] https://docs.baseten.co/mcp“PROBE mcp-endpoint (2026-09-04): POST initialize to https://docs.baseten.co/mcp answered HTTP 200 with a JSON-RPC/MCP response (event: message data: {"result":{"protocolVersion":"2025-06-18","capabilities":{"tools":{"listChanged":true},"resources":{"listChanged":true}) — a live, publicly reachable MCP server.”

Perform bulk operations across many items at onceweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

• [claimed-docs] https://docs.baseten.co/inference/overview.md“Async inference returns a request ID quickly and completes later through webhook or polling, which suits batch work, long documents”
• [claimed-docs] https://docs.baseten.co/inference/overview.md“Async inference returns a request ID quickly and completes later through webhook or polling, which suits batch work, long documents, or any case where the caller should not hold a connection open for minutes.”
• [claimed-docs] https://docs.baseten.co/inference/overview.md“Async inference returns a request ID quickly and completes later through webhook or polling”

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh