Skip to content

AI Models

TeXRA supports models from multiple providers. Select models from the dropdown in the TeXRA UI. Hover over an option to see its context window and cost estimate.

Model
sonnet46T
opus48TT
opus48
sonnet46TT
sonnet46
haiku45TT
haiku45

The model picker: monospace model ids with a T badge on thinking variants, and a hover popover showing context window and per-1M token pricing.

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
fable5Most capable, always-on adaptive thinking$$$$Slow
opus48TTop-tier reasoning, long-horizon work$$$$Slow
opus48Most capable for agentic coding$$$$Slow
sonnet46TAll-rounder with reasoning$$$Medium
sonnet46Strong all-rounder$$$Medium
haiku45TFast with reasoning$$Fast
haiku45Fast responses$$Fast

Fable 5, Opus 4.8, and Sonnet 4.6 include the full 1M context window at standard pricing — no opt-in or beta header required. Other Claude models use a 200K context window.

Claude Fable 5 (fable5) is Anthropic's most capable model. Thinking is always on — adaptive, with summarized reasoning — so there is no separate T variant. It supports the full reasoning-effort range up to Extra High and the top Max tier, and is eligible for context compaction in tool-use mode.

Claude Opus 4.8 uses adaptive thinking only (extended thinking with a manual budget_tokens is no longer accepted). TeXRA's reasoning-effort selector maps to Anthropic's effort levels automatically — pick opus48T with Extra High (or the top Max tier) effort for the strongest agentic coding and long-horizon tasks. Opus 4.8 also supports high-resolution images (up to 2576px / 3.75MP) for better figure, chart, and screenshot understanding; note that TeXRA downscales images above texra.maxImageDimension (default 2000px) before sending, so raise that setting if you want to take full advantage of Opus 4.8's higher limit.

OpenAI Models

Model IDUse CaseCostSpeed
gpt55proTop-tier reasoning, 1M context$$$$$Slow
gpt55Flagship reasoning$$$$Medium
gpt54Mid-tier reasoning$$$Medium
gpt54-Lower-cost reasoning$$Fast
gpt54--Budget reasoning$Fast

GPT-5.5 is OpenAI's latest flagship and the model TeXRA pins the Codex integration to. GPT-5.5 Pro (gpt55pro) extends GPT-5.5 with a 1.05M context window and xhigh default reasoning for the hardest planning and long-horizon tasks, at premium pricing — it is hidden by default; enable it from Settings → Models when you need it. The GPT Pro variants (gpt5pro, gpt52pro, gpt55pro) charge $15-$30 per 1M input and $120-$180 per 1M output, so for one-off hard questions consider enabling the inquiry tool and pasting the answer from your own ChatGPT subscription instead of running a full agent turn against the API. gpt54 and its mini/nano variants remain the lower-cost option for most workloads. See the API reference for full capabilities.

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

Google Models

Model IDUse CaseCostSpeed
gemini31pPro with reasoning, 1M context$$$Medium
gemini35fFlash model with 1M context$$Fast

DeepSeek Models

Model IDUse CaseCostSpeed
deepseekV4 Flash chat mode$Fast
deepseekTV4 Flash with reasoning$Medium
deepseekproV4 Pro chat mode$Medium
deepseekproTV4 Pro with reasoning$Medium
dsr1Advanced reasoning$$Medium

Moonshot Kimi Models

Model IDUse CaseCostSpeed
kimi26TK2.6 with thinking mode$$$Medium
kimi26K2.6, agent tasks$$$Medium

DashScope Qwen Models

Model IDUse CaseCostSpeed
qwenplusHybrid thinking, 1M context$$Medium
qwenturboFast with optional thinking$Fast

MiniMax Models

Model IDUse CaseCostSpeed
minimaxM27Flagship with interleaved thinking$$Medium
minimaxM25Strong all-rounder$$Medium

MiniMax uses interleaved thinking (chain-of-thought woven into responses). API keys are region-specific — international keys (api.minimax.io) and China keys (api.minimaxi.com) are not interchangeable. Toggle the region in the Models tab.

  • International: Get your API key at platform.minimax.io
  • China: Get your API key at platform.minimaxi.com
  • Coding Plan: MiniMax offers monthly subscription plans ($10/$20/$50/mo) as an alternative to pay-as-you-go. Coding Plan keys are not interchangeable with standard API keys — enter your Coding Plan key via "Set API Key" as usual. Subscribe here.

GLM (Zhipu AI / Z.AI) Models

Model IDUse CaseCostSpeed
glm5Flagship open-source model$$$Medium
glm5turboFast inference, agent-optimized$$$Medium
glm47Programming and multi-step reasoning$$Medium
glm46vMultimodal vision model$$Medium
glm45Hybrid reasoning (MoE)$$Medium

GLM models support thinking mode (reasoning is shown inline). The API uses a non-standard base path (/api/paas/v4), which TeXRA handles automatically.

  • International (Z.AI): Get your API key at z.ai — endpoint: api.z.ai
  • China (BigModel): Get your API key at open.bigmodel.cn — endpoint: open.bigmodel.cn (default)
  • Coding Plan: GLM offers monthly subscription plans as an alternative to pay-as-you-go, with access to all GLM models. Coding Plan uses a separate endpoint (/api/coding/paas/v4). Enable the "Coding Plan" toggle in the Models tab. Subscribe here.

Grok / xAI Models

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

Choosing a Model

Simple tasksFast, cheap models
qwenturbodeepseekhaiku45
Complex tasksPowerful flagship models
fable5opus48gpt55gemini31p
Code-heavy / LaTeX editingStrong editing models
opus48Tsonnet46Tqwenplus
Reasoning-heavyThinking models
fable5opus48Tsonnet46TdeepseekTkimi26T
Large documentsHigh-context models
gemini31pfable5sonnet46opus48

Pick a model by intent: each use case maps to a short list of recommended model ids.

Customizing the Model List

Choose which models appear in the extension picker from the Dashboard → Models tab — toggle them on or off per provider, no JSON required (the choice is saved in the extension).

In the CLI TUI, use /model after a chat starts to switch among models that are runnable in the active API mode. Startup also asks for a model when the launcher flow needs one after the agent or team choice.

For headless CLI runs, list what's available with texra models list (or texra models show <id> for details), then pick a default for your project by setting the model key in .texra/config.json, or override per run with --model <id>.

Using OpenRouter

To access additional models or alternative pricing:

  1. Get an OpenRouter API key
  2. Add via TeXRA: Set API Key command
  3. In the Dashboard → Models tab → API Configuration, expand the OpenRouter row and enable "Use OpenRouter for All Models"

Expanding any provider's row in API Configuration reveals its key field plus the per-provider toggles described here and under Streaming:

OpenAI
Key set
sk-••••••••••••••••••••••••
Long responses arrive incrementally
Route this provider's calls through OpenRouter

Expand a provider's API Configuration row to reveal its masked key field, the per-provider Enable streaming toggle, and Use OpenRouter for All Models.

Streaming

Streaming is configured per provider rather than through a single global setting. Open the Dashboard → Models tab, expand a provider's API Configuration, and toggle streaming there (see the expanded row above). Enabling it makes long responses arrive incrementally instead of in one large reply.

Next Steps