GPT, Claude, Gemini, GLM, and beyond. A single place for the intelligence you need, the balance you use, and the tools you already love.
More time building. Less time switching accounts, checking balances, and changing the way you work.
Stream output as it arrives. Keep your flow from the first token to the last, without waiting for a whole response.
Bring your model usage into a single API balance, with a clear view of what you use and where it goes.
Clear provider names. Explicit model IDs. Explore each family’s strengths and choose the right intelligence for the job.
Explore model familiesKeep the tools you know. Configure an endpoint and key, then get back to the work in front of you.
Balance, model usage, and API access in one considered workspace. The details you need, without the noise.
The workspace is designed around three simple steps. Your model can change. Your workflow does not have to.
An account or API key is the starting point. One workspace for your model choices and the tools you build with.
A shared balance, clear usage, and a single place to understand where your tokens go. Less account juggling.
Choose a model, configure your endpoint, and bring it into a compatible SDK or CLI. Keep working where you already do.
Explore Gemini, Claude, GPT, and Grok. Compare reasoning, coding, and image generation for your next project.
claude-opus-5-5Sustained agentic coding and complex knowledge work.
Provider list prices · USD / 1M tokens
Standard API prices. Cache writes use the 5-minute rate; 1-hour writes cost more. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
claude-opus-5Coding, analysis, and multi-step agent workflows with the Opus family.
Provider list prices · USD / 1M tokens
Standard API prices. Cache writes use the 5-minute rate; 1-hour writes cost more. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
gpt-6.1-solStrong intelligence for complex tasks with a focus on efficiency.
Provider list prices · USD / 1M tokens
Standard API prices for short-context requests. Cache writes use the 30-minute rate; 12-hour writes and long-context requests cost more. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
gpt-6-solComplex coding and agentic workflows, from planning to execution.
Provider list prices · USD / 1M tokens
Standard API prices for short-context requests. Cache writes use the 30-minute rate; 12-hour writes and long-context requests cost more. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
claude-opus-4-8Use Opus 4.8 through Palatial. Your dashboard shows its live availability, exact model ID, and credit rates.
Provider list prices · USD / 1M tokens
Standard API prices. Cache writes use the 5-minute rate; 1-hour writes cost more. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
gpt-6-lunaFocused intelligence for everyday tasks and high-volume workloads.
Provider list prices · USD / 1M tokens
Standard API prices for short-context requests. Cache writes use the 30-minute rate; 12-hour writes and long-context requests cost more. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
grok-4.7Configurable reasoning, coding, image understanding, and client tool workflows.
Provider list prices · USD / 1M tokens
xAI Standard API prices, checked November 15, 2026. All token rates double at 200,000 prompt tokens. Cache writes have no separately published rate. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
grok-build-0.1A coding model with text and image input, client tools, and structured output.
Provider list prices · USD / 1M tokens
xAI Standard API prices, checked November 15, 2026. All token rates double at 200,000 prompt tokens. Cache writes have no separately published rate. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
grok-imagine-image-2.0Generate images with low or medium quality at 1K, 1.5K, or 2K resolution.
Provider list prices · USD / image
| Tier | USD / image |
|---|---|
| 1K · low | $0.04 |
| 1.5K · low | $0.05 |
| 2K · low | $0.06 |
| 1K · medium | $0.06 |
| 1.5K · medium | $0.07 |
| 2K · medium | $0.08 |
xAI output-image list prices, checked November 15, 2026. Select quality and resolution per request. Palatial currently supports text-to-image generation; image editing is not enabled. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
gemini-4-argonComplex engineering, mathematical problem solving, and multi-step agents.
See provider source for API pricing.
Palatial usage is billed separately in credits. See your dashboard for billing rates.
gemini-3.8-flashLong-running software engineering and complex agent workflows.
See provider source for API pricing.
Palatial usage is billed separately in credits. See your dashboard for billing rates.
gemini-3.6-flashA fast, multimodal option for coding, iteration, and everyday tasks.
See provider source for API pricing.
Palatial usage is billed separately in credits. See your dashboard for billing rates.
gemini-3.5-flash-liteLightweight execution for extraction, document parsing, and subagent tasks.
See provider source for API pricing.
Palatial usage is billed separately in credits. See your dashboard for billing rates.
claude-sonnet-5-5Responsive reasoning for coding, writing, and everyday problem solving.
See provider source for API pricing.
Palatial usage is billed separately in credits. See your dashboard for billing rates.
claude-haiku-5-5High-volume classification, extraction, and routing tasks.
See provider source for API pricing.
Palatial usage is billed separately in credits. See your dashboard for billing rates.
gpt-6.1-terraVisual understanding, precise computer use, and natural writing.
See provider source for API pricing.
Palatial usage is billed separately in credits. See your dashboard for billing rates.
grok-4.6Text and image understanding with configurable reasoning and tool calling.
Provider list prices · USD / 1M tokens
xAI Standard API prices, checked November 15, 2026. All token rates double at 200,000 prompt tokens. Cache writes have no separately published rate. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
grok-4.5Reasoning and tool-connected work across text and images.
Provider list prices · USD / 1M tokens
xAI Standard API prices, checked November 15, 2026. All token rates double at 200,000 prompt tokens. Cache writes have no separately published rate. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
grok-4.3Text, code, and image understanding with configurable reasoning.
Provider list prices · USD / 1M tokens
xAI Standard API prices, checked November 15, 2026. All token rates double at 200,000 prompt tokens. Cache writes have no separately published rate. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
grok-4.20-0309-reasoningThe reasoning variant of Grok 4.20 for text and image tasks.
Provider list prices · USD / 1M tokens
xAI Standard API prices, checked November 15, 2026. All token rates double at 200,000 prompt tokens. Cache writes have no separately published rate. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
grok-4.20-0309-non-reasoningThe non-reasoning Grok 4.20 variant for text, images, and client tools.
Provider list prices · USD / 1M tokens
xAI Standard API prices, checked November 15, 2026. All token rates double at 200,000 prompt tokens. Cache writes have no separately published rate. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
grok-4.20-multi-agent-0309Provider-managed agent collaboration through Responses. Client function tools and a client-specified output cap are not supported.
Provider list prices · USD / 1M tokens
xAI Standard API prices, checked November 15, 2026. All token rates double at 200,000 prompt tokens. Cache writes have no separately published rate. Responses API only; client function tools are not supported. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
grok-imagine-imageGenerate images from a text prompt at 1K or 2K resolution.
Provider list prices · USD / image
| Tier | USD / image |
|---|---|
| 1K · standard | $0.02 |
| 2K · standard | $0.02 |
xAI output-image list prices, checked November 15, 2026. Palatial currently supports text-to-image generation; image editing is not enabled. Provider source
Palatial usage is billed separately in credits. See your dashboard for billing rates.
Publisher USD prices are references. Palatial bills separately in credits, with the applicable token or image units. Your dashboard shows live availability, billing details, and exact API model IDs.
A little clarity before your first request. Models, balances, and the tools you want to connect.
The workspace brings GPT, Claude, Gemini, GLM, DeepSeek, Qwen, Mistral, and Grok into one model-selection experience. The model lineup highlights Gemini, Claude, and GPT models and their different strengths. Exact model IDs and availability belong in the account workspace when access is connected.
A wider choice of intelligence. One place to manage it. Find your model, bring your tools, and make room for what comes next.