Skip to main content
CTOR supports multiple AI model providers. Configure API keys in settings to enable a provider.
The Image input column shows native image support. A model marked — can still work with images if you set a fallback vision model — CTOR describes each image as text so the model can use it.

​
Anthropic

ModelContext windowReasoningExtended thinkingImage input
claude-fable-51MYesMaxYes
claude-sonnet-51MYesMaxYes
claude-sonnet-4.6200KYes—Yes
claude-opus-4.8200KYesMaxYes
claude-opus-4.7200KYesMaxYes
claude-opus-4.6200KYesMaxYes
claude-haiku-4-5-20251001200KYes—Yes
Anthropic supports two authentication modes: an API key (pay-per-token billing) or Login with Claude OAuth (credit-based usage against a Claude Pro or Max subscription). Configure either in Settings > Providers > Anthropic. See settings for details.

​
OpenAI

ModelContext windowReasoningExtended thinkingImage input
gpt-5.5272KYesMaxYes
gpt-5.4272KYesMaxYes
gpt-5.3-codex400KYesMaxYes
gpt-5.2-codex400KYesMaxYes
gpt-5.2400KYesMaxYes
gpt-5.1-codex-mini400KYes—Yes
gpt-5.4-nano400KYesMaxYes

​
OpenAI Codex

ModelContext windowReasoningExtended thinkingImage input
gpt-5.5272KYesMaxYes
gpt-5.4272KYesMaxYes
gpt-5.4-mini272KYesMaxYes
gpt-5.3-codex-spark128KYesMax—
gpt-5.3-codex-spark requires a ChatGPT Pro plan. It appears in the model selector only when the signed-in OpenAI Codex account is on the Pro plan. gpt-5.5 and gpt-5.4 support speed mode — a Normal/Fast toggle appears in the input bar when either model is selected.

​
Google

ModelContext windowReasoningExtended thinkingImage input
gemini-3.5-flash1MYes—Yes
gemini-3.1-pro-preview1MYes—Yes
gemini-3-pro-preview1MYes—Yes
gemini-3-flash-preview1MYes—Yes
gemma-4-26b-a4b-it256KYes—Yes
gemma-4-31b-it256KYes—Yes

​
Google Agent Platform (Vertex AI)

ModelContext windowReasoningExtended thinkingImage input
gemini-3.5-flash1MYes—Yes
gemini-3.1-pro-preview1MYes—Yes
gemini-3-flash-preview1MYes—Yes
claude-opus-4.7200KYesMaxYes
claude-opus-4.6200KYesMaxYes
claude-sonnet-4.6200KYes—Yes
claude-haiku-4.5200KYes—Yes
Google rebranded Vertex AI to Agent Platform; CTOR shows both names so the provider is findable by either label. Gemini models go through the Generative AI API on Vertex; Claude models use Anthropic’s Vertex partner endpoint. Authentication uses Application Default Credentials (ADC), a service account key file, or an API key (Gemini only — Claude partner models reject API keys). See settings for setup details.

​
GitHub Copilot

ModelContext windowReasoningExtended thinkingImage input
claude-sonnet-51MYesMaxYes
claude-sonnet-4.6200KYes—Yes
claude-haiku-4.5144KYes—Yes
gpt-5.4400KYesMaxYes
gpt-5.4-mini400KYesMaxYes
gpt-5.3-codex400KYesMaxYes
gpt-5.2264KYesMaxYes
gpt-5.2-codex400KYesMaxYes
gemini-3.5-flash128KYes—Yes
gemini-3.1-pro-preview128KYes—Yes
gemini-3-flash-preview128KYes—Yes
kimi-k2.7-code256KYes—Yes
GitHub Copilot uses OAuth for authentication. Configure it in Settings > Providers > GitHub Copilot. OpenAI Codex uses OAuth for authentication (Login with OpenAI). Configure it in Settings > Providers > OpenAI Codex.

​
OpenCode Zen

ModelContext windowReasoningExtended thinkingImage input
claude-fable-51MYesMaxYes
claude-sonnet-51MYesMaxYes
claude-sonnet-4.6200KYes—Yes
claude-opus-4.7200KYesMaxYes
claude-opus-4.6200KYesMaxYes
claude-haiku-4.5200KYes—Yes
gpt-5.4272KYesMaxYes
gpt-5.4-mini400KYesMaxYes
gpt-5.3-codex400KYesMaxYes
gpt-5.2-codex400KYesMaxYes
gpt-5.2400KYesMaxYes
gemini-3.1-pro1MYes—Yes
gemini-3-flash1MYes—Yes
kimi-k2.7-code256KYes—Yes
kimi-k2.6256KYes—Yes
kimi-k2.5256KYes—Yes
glm-5.21MYesMax—
glm-5.1200KYes——
glm-5200KYes——
minimax-m3512KYes—Yes
minimax-m2.5200KYes——

​
OpenCode Go

ModelContext windowReasoningExtended thinkingImage input
kimi-k2.7-code256KYes—Yes
kimi-k2.6256KYes—Yes
kimi-k2.5256KYes—Yes
glm-5.21MYesMax—
glm-5.1200KYes——
minimax-m3512KYes—Yes
minimax-m2.7200KYes——
qwen3.7-max1MYes——
qwen3.7-plus256KYes—Yes
qwen3.6-plus256KYes—Yes
mimo-v2.5-pro1MYes——
mimo-v2.51MYes—Yes
deepseek-v4-pro1MYesMax—
deepseek-v4-flash1MYesMax—

​
OpenAI Compatible endpoints

Add any number of OpenAI-compatible API endpoints, each with its own name, base URL, API key, and model list. Manage endpoints in Settings > OpenAI Compatible Endpoints. Each endpoint is configured with:
FieldDescription
Endpoint NameA display name (e.g., “Ollama”, “vLLM”, “LM Studio”)
Base URLThe API endpoint (e.g., http://localhost:11434/v1)
API ModeChat Completions (default) or Responses — selects which OpenAI API the endpoint uses. Choose Responses for reasoning-capable models.
API KeyOptional, depending on the provider
ModelsOne or more model identifiers available at this endpoint
Models from configured endpoints appear in the model selector grouped under the endpoint name. This allows you to use local models (Ollama, LM Studio) or any third-party provider that implements the OpenAI API format.
If you previously configured a single OpenAI Compatible provider, it is automatically migrated to the new multi-endpoint format on first launch.

​
Per-model options

Each model you add to an endpoint carries its own options:
OptionDescription
VisionTreat the model as supporting image input. CTOR does not verify endpoint support.
ReasoningTreat the model as a reasoning-capable Responses model. CTOR sends reasoning.effort and preserves encrypted reasoning across turns. Available only when the endpoint’s API Mode is Responses.
XHighAllow the xhigh thinking level for this model. Available only when Reasoning is enabled.
ContextOverride the context window in tokens (minimum 32K). Leave blank for the 128K default.
The reasoning options unlock in sequence: set the endpoint API Mode to Responses to enable Reasoning, then enable Reasoning to unlock XHigh.

​
Thinking levels

Models with reasoning support can use different thinking levels to control the depth of analysis:
LevelToken budgetBest for
Off—Fast responses, simple tasks
High~16k tokensMost tasks
Max~32k tokensComplex reasoning, architecture decisions
The Max level is only available on models marked with “Max” in the extended thinking column above.

​
Speed mode

When using OpenAI Codex with gpt-5.5 or gpt-5.4, a speed mode selector (gauge icon) appears to the right of the thinking level selector in the input bar.
ModeBehavior
NormalStandard processing — default latency and cost
FastPriority tier — lower latency, higher cost
Fast maps to the Codex Responses API service_tier: 'priority'. The setting is persisted per session. The selector is only visible when a model that supports speed mode is active. Switching to a model without speed mode support hides the control; any previously set “Fast” preference is not applied.

​
Environment variable fallback

If no API key is configured in the app settings, the agent checks these environment variables:
  • ANTHROPIC_API_KEY — used for Anthropic models
  • OPENAI_API_KEY — used for OpenAI models