# xAI models

Canonical HTML page: [xAI models](<https://impossibl.com/xai>)
Markdown alternative: [xAI models as Markdown](<https://impossibl.com/xai.md>)

Access 8 models from xAI through the Impossibl API, including Grok 4.20 (non-reasoning), Grok 4.20 (reasoning), and Grok 4.20 (multi-agent). Compare API pricing, context windows, and capabilities.

Select two or three models to [compare specifications and API costs](<https://impossibl.com/compare.md>). Model types and billing units are not interchangeable.

## Models

### [Grok 4.20 (non-reasoning)](<https://impossibl.com/xai/grok-4.20-0309-non-reasoning>)

Grok 4.20 (non-reasoning) is a text generation model from xAI, available through the Impossibl API. Its published context window is 1,000,000 tokens. The advertised input rate is $1.25 per million input tokens. The advertised output rate is $2.50 per million output tokens. Additional pricing brackets apply when the input exceeds a published context threshold.

- API identifier: `xai/grok-4.20-0309-non-reasoning`
- Creator: xAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $2.50 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.20-0309-non-reasoning.md>)

### [Grok 4.20 (reasoning)](<https://impossibl.com/xai/grok-4.20-0309-reasoning>)

Grok 4.20 (reasoning) is a text generation model from xAI, available through the Impossibl API. Its published context window is 1,000,000 tokens. The advertised input rate is $1.25 per million input tokens. The advertised output rate is $2.50 per million output tokens. Additional pricing brackets apply when the input exceeds a published context threshold.

- API identifier: `xai/grok-4.20-0309-reasoning`
- Creator: xAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $2.50 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.20-0309-reasoning.md>)

### [Grok 4.20 (multi-agent)](<https://impossibl.com/xai/grok-4.20-multi-agent-0309>)

Grok 4.20 (multi-agent) is a text generation model from xAI, available through the Impossibl API. Its published context window is 1,000,000 tokens. The advertised input rate is $1.25 per million input tokens. The advertised output rate is $2.50 per million output tokens. Additional pricing brackets apply when the input exceeds a published context threshold.

- API identifier: `xai/grok-4.20-multi-agent-0309`
- Creator: xAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $2.50 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.20-multi-agent-0309.md>)

### [Grok 4.3](<https://impossibl.com/xai/grok-4.3>)

Grok 4.3 is a text generation model from xAI, available through the Impossibl API. Its published context window is 1,000,000 tokens. The advertised input rate is $1.25 per million input tokens. The advertised output rate is $2.50 per million output tokens. Additional pricing brackets apply when the input exceeds a published context threshold.

- API identifier: `xai/grok-4.3`
- Creator: xAI; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $2.50 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.3.md>)

### [Grok 4.5](<https://impossibl.com/xai/grok-4.5>)

Grok 4.5 is a text generation model from xAI, available through the Impossibl API. Its published context window is 500,000 tokens. The advertised input rate is $2.00 per million input tokens. The advertised output rate is $6.00 per million output tokens. Additional pricing brackets apply when the input exceeds a published context threshold.

- API identifier: `xai/grok-4.5`
- Creator: xAI; model type: Text generation.
- Context window: 500,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $6.00 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.5.md>)

### [Grok 4.6](<https://impossibl.com/xai/grok-4.6>)

Grok 4.6 is a text generation model from xAI, available through the Impossibl API. Its published context window is 500,000 tokens. The advertised input rate is $2.00 per million input tokens. The advertised output rate is $6.00 per million output tokens. Additional pricing brackets apply when the input exceeds a published context threshold.

- API identifier: `xai/grok-4.6`
- Creator: xAI; model type: Text generation.
- Context window: 500,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $2.00 per million input tokens; $6.00 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-4.6.md>)

### [Grok Build 0.1](<https://impossibl.com/xai/grok-build-0.1>)

Grok Build 0.1 is a text generation model from xAI, available through the Impossibl API. Its published context window is 256,000 tokens. The advertised input rate is $1.00 per million input tokens. The advertised output rate is $2.00 per million output tokens. Additional pricing brackets apply when the input exceeds a published context threshold.

- API identifier: `xai/grok-build-0.1`
- Creator: xAI; model type: Text generation.
- Context window: 256,000 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.00 per million input tokens; $2.00 per million output tokens. Above 200,000 input tokens per request, context-tier rates apply to the whole request.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-build-0.1.md>)

### [Grok Voice TTS 1.0](<https://impossibl.com/xai/grok-voice-tts-1.0>)

Grok Voice TTS 1.0 is a text-to-speech model from xAI, available through the Impossibl API. The advertised input rate is $15.00 per million input characters.

- API identifier: `xai/grok-voice-tts-1.0`
- Creator: xAI; model type: Text to speech.
- Context window: Not published; tool calling: Not published.
- Inputs: text; outputs: audio.
- Base API pricing (USD): $15.00 per million input characters.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/xai/grok-voice-tts-1.0.md>)

## Compare xAI models

- [Grok 4.20 (non-reasoning) vs Grok 4.20 (reasoning)](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-4.20-0309-reasoning>); [Markdown comparison](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-4.20-0309-reasoning.md>)
- [Grok 4.20 (non-reasoning) vs Grok 4.20 (multi-agent)](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-4.20-multi-agent-0309>); [Markdown comparison](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-4.20-multi-agent-0309.md>)
- [Grok 4.20 (non-reasoning) vs Grok 4.3](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-4.3>); [Markdown comparison](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-4.3.md>)
- [Grok 4.20 (non-reasoning) vs Grok 4.5](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-4.5>); [Markdown comparison](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-4.5.md>)
- [Grok 4.20 (non-reasoning) vs Grok 4.6](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-4.6>); [Markdown comparison](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-4.6.md>)
- [Grok 4.20 (non-reasoning) vs Grok Build 0.1](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-build-0.1>); [Markdown comparison](<https://impossibl.com/compare/xai/grok-4.20-0309-non-reasoning/xai/grok-build-0.1.md>)

## Frequently asked questions

### Which xAI models are available through Impossibl?

The directory lists 8 models from xAI available through the Impossibl API, including Grok 4.20 (non-reasoning), Grok 4.20 (reasoning), and Grok 4.20 (multi-agent). Open each model page for its API identifier, capabilities, and current pricing.

### How much do xAI models cost?

xAI model prices vary by model and usage. All rates below are published base API rates in USD. For token-priced models, published input rates start at $1.00 per million input tokens. Published output rates start at $2.00 per million output tokens. Input and output minima may refer to different models. For character-priced models, published input rates start at $15.00 per million input characters. Long-context tiers can change prices for the whole request; check each model's thresholds and rates. Individual model pages include published cache prices and billing units. Applicable fees and workspace-specific pricing can affect the amount paid.

### What context windows do xAI models support?

Among xAI models with a published limit on Impossibl, the largest context window is 1,000,000 tokens, listed for Grok 4.20 (non-reasoning), Grok 4.20 (reasoning), and Grok 4.20 (multi-agent). Context limits vary by model and are separate from maximum output limits. Context windows are unpublished for 1 model.

### What inputs and capabilities do xAI models support?

Available model types include text generation and text to speech. Published input support includes image and text; support varies by model. Tool-calling support is unspecified for 8 models.

### How do I use xAI models through an API?

Use the exact model identifier from the model page with the Impossibl API. For example, select xai/grok-4.20-0309-non-reasoning with /v1/chat/completions. Endpoint compatibility depends on the selected model. The API quickstart explains how to create an API key and send a request.

## Sources and related links

Prices, capabilities, limits, and availability describe the public Impossibl API offering. An unpublished fact is unknown; a published zero price is zero. Compare matching billing units and check context tiers before estimating costs.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Model directory as Markdown](<https://impossibl.com/models.md>)
- [API quickstart](<https://impossibl.com/docs/agent-quickstart>)
- [Model documentation](<https://impossibl.com/docs/models>)