Can My Agent Uselookup · compare · cite

Aug 28, 2026 · Catalog foundation is up

Product feature · models-context

Model selectionCommon product term

Choose the model or documented model class used for a run.

Terminology basis: Common product term. xAI — Grok Bot for teams and enterprises

Model selection: 10 supported, 0 partial, 1 unsupported, 20 unreviewed across 31 cataloged products.

Markdown · JSON

Explore this familyMore in Models and context11 capabilities

Current evidence by product

Can my agent use Model selection?

Read across for the answer. 11 of 31 current product columns have reviewed evidence; unreviewed does not mean unsupported.

Known issues (0)Report an issue
  • Supported10
  • Partial0
  • Unsupported1
  • Unknown20
  • Not applicable0

Web

9 products

Desktop

13 products

CLI

9 products

Unknown means no public evidence has been reviewed for that product and capability. It does not mean unsupported.

How statuses are assigned

Definition and scope

What this capability means

This row asks whether the operator can select a specific model or a clearly documented model class for the exact harness and task. An opaque automatic router is not explicit selection; a “fast” or “deep” mode may be partial if its underlying model can change without notice.

Evidence should record eligible plans, model aliases and revisions, per-workspace restrictions, whether tools and media inputs narrow the choices, and whether the selection persists for a conversation, agent, project, or single run.

Traceable compatibility

Assertion ledger

Documentation evidence only. No runtime conformance test is implied.

ChatGPTweb · current
Supported
Target
2026-08-28 ChatGPT Work web documentation observation · hosted-observation
Environment
hosted-default
Observed
2026-08-28
  • planavailable choices depend on account eligibility, plan, and supported model
Evidence
ChatGPTdesktop · current
Supported
Target
current ChatGPT desktop documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • planavailable choices depend on account eligibility, plan, and supported model
Evidence
Codex CLIcli · current
Supported
Target
current Codex CLI documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtime/model changes an interactive session; --model or -m selects a model for interactive and non-interactive runs
Evidence
Claudeweb · current
Supported
Target
2026-08-28 Claude web documentation observation · hosted-observation
Environment
hosted-default
Observed
2026-08-28
  • planthe selector shows models available to the account and can be restricted by an Enterprise role
Evidence
Claudedesktop · current
Supported
Target
current Claude Desktop documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • planthe selector shows models available to the account and can be restricted by an Enterprise role
Evidence
Claude CLIcli · current
Supported
Target
current Claude Code documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtimesupports /model, --model, ANTHROPIC_MODEL, and persistent model settings with documented precedence
Evidence
Gemini CLIcli · current
Supported
Target
current Gemini CLI documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtime/model and --model expose automatic model classes and manual model selection; this setting does not override models used by subagents
Evidence
Grok Botdesktop · current
Unsupported
Target
2026-08-28 Grok Bot desktop documentation observation · hosted-observation
Environment
hosted-default
Observed
2026-08-28
  • runtimemodel choice is fully managed by the product; neither members nor administrators receive a model picker
Evidence
Copilot CLIcli · current
Supported
Target
current GitHub Copilot CLI command reference · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtime/model selects for the current session or persists at repository or global scope; --model selects at startup and auto enables product routing
Evidence
Copilot Chatdesktop · current
Supported
Target
current VS Code language-model documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • planavailable models depend on provider access, Copilot plan, organization policy, configured BYOK providers, and agent-harness compatibility
Evidence
Cursordesktop · current
Supported
Target
current Cursor model-selection documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • planselectable model inventory, pricing, and Max Mode availability depend on the current Cursor plan and provider availability
Evidence
  1. 1. Evidence checked 2026-08-28: xAI's Grok Bot team documentation says the product has no model picker and does not plan to let users or administrators choose its models; requests use a product-managed fixed model set with automatic failover.
  2. 2. Evidence checked 2026-08-28: OpenAI documents model controls in ChatGPT Work on the web and ChatGPT desktop, plus /model and --model/-m selection in Codex CLI.
  3. 3. Evidence checked 2026-08-28: Anthropic documents model selectors in Claude web and desktop and /model, --model, environment, and settings-based selection in Claude Code.
  4. 4. Evidence checked 2026-08-28: Gemini CLI exposes Auto, Pro, Flash, Flash-Lite, and manual model selection through /model and --model.
  5. 5. Evidence checked 2026-08-28: GitHub Copilot CLI exposes per-session, repository, global, command-line, and automatic model selection with documented precedence.
  6. 6. Evidence checked 2026-08-28: VS Code exposes a language-model picker, automatic routing, and BYOK or local-model configuration for supported agent sessions.
  7. 7. Evidence checked 2026-08-28: Cursor documents a model picker and curated selectable models with task, cost, speed, and context tradeoffs.