TeXRA

Appearance

AI Models ​

TeXRA supports models from multiple providers. Select models from the dropdown in the TeXRA UI. Hover over options to see context window and cost estimates.

Model ID suffixes:

  • T = Thinking/reasoning mode enabled (shows chain-of-thought)
  • - = Lighter/faster variant
  • Numbers indicate version (e.g., 45 = 4.5, 25 = 2.5)

Anthropic Models ​

Model IDUse CaseCostSpeed
opus46TComplex tasks with reasoning$$$$Slow
opus46High quality, complex tasks$$$$Slow
opus45TComplex tasks with reasoning$$$$Slow
opus45High quality, complex tasks$$$$Slow
sonnet45TAll-rounder with reasoning$$$Medium
sonnet45Strong all-rounder$$$Medium
haiku45TFast with reasoning$$Fast
haiku45Fast responses$$Fast
haiku35Budget option$Fast

For 1M-token context on Opus 4.6 and Sonnet 4/4.5, enable texra.model.useAnthropic1MBeta in settings.

OpenAI Models ​

Model IDUse CaseCostSpeed
gpt52proPremium reasoning$$$$Slow
gpt52Flagship reasoning$$$Medium
gpt51Flagship, 400k context$$$Medium
gpt5Flagship reasoning$$$Medium
gpt5-Fast flagship$$Fast
gpt41Long context (1M), vision$$$Medium
gpt4oStrong all-rounder, vision$$$Medium
o3proHeavy compute reasoning$$$$Slow
o3Coding, tool calling$$$Medium
o1Advanced reasoning$$$$Slow

GPT-5 reasoning summaries require account verification. Enable with texra.model.gpt5ReasoningSummary.

Google Models ​

Model IDUse CaseCostSpeed
gemini3pPro with reasoning, 1M context$$$Medium
gemini3fFlash with reasoning, 1M context$$Fast
gemini25pStrong reasoning, vision, 1M context$$$Medium
gemini25fFast reasoning, 1M context$$Fast
gemini25f-Budget flash, 64k context$Fast

DeepSeek Models ​

Model IDUse CaseCostSpeed
deepseekV3.2 chat mode$Fast
deepseekTV3.2 with reasoning$Medium
dsr1Advanced reasoning$$Medium

Moonshot Kimi Models ​

Model IDUse CaseCostSpeed
kimi25TK2.5 with thinking mode$$$Medium
kimi25K2.5, agent tasks$$$Medium

DashScope Qwen Models ​

Model IDUse CaseCostSpeed
qwen3maxFlagship coding, 262k context$$$Medium
qwenplusHybrid thinking, 1M context$$Medium
qwenturboFast with optional thinking$Fast

Grok / xAI Models ​

Model IDUse CaseCostSpeed
grok4Large context (256k), reasoning$$$Medium
grok3Large context (131k)$$$Medium
grok2vVision-enabled$$Medium

Choosing a Model ​

  • Simple tasks: Fast, cheap models (gemini25f-, gpt5-, haiku35)
  • Complex tasks: Powerful models (opus46, gpt52pro, o1)
  • Reasoning-heavy: Thinking models (sonnet45T, deepseekT, o3)
  • Large documents: High-context models (gemini*, gpt41, gpt5)

Configuration ​

Customize available models in VS Code Settings under texra.models:

json
"texra.models": [
  "gemini3p",
  "sonnet45T",
  "opus46T",
  "gpt52",
  "deepseekT"
]

Using OpenRouter ​

To access additional models or alternative pricing:

  1. Get an OpenRouter API key
  2. Add via TeXRA: Set API Key command
  3. Enable texra.model.useOpenRouter in settings

Streaming ​

Enable streaming for long responses in settings:

json
"texra.model.useStreaming": true

Next Steps ​