# Grok API pricing, every xAI model per million tokens

On 25 September 2026, xAI models on this list cost from $1.00 per million input tokens (Grok Build 0.1) to $2.00 (Grok 4.6), and from $2.00 per million output tokens (Grok Build 0.1) to $6.00 (Grok 4.6).

Prices checked 25 September 2026 at 06.00 UTC . Source OpenRouter public model list . US dollars per million tokens

Input tokens per call

Output tokens per call

Calls a day

Search models

| Model | Input | Output | Cached input | Batch in / out | Context | Your month | Listed |
|---|---|---|---|---|---|---|---|
| Grok 4.7 | $1.60 | $4.80 | $0.40 |  | 500K | $168.00 | 2026-09-21 |
| Grok 4.6 | $2.00 | $6.00 | $0.50 |  | 500K | $210.00 | 2026-08-12 |
| Grok 4.5 | $2.00 | $6.00 | $0.30 |  | 500K | $210.00 | 2026-07-08 |
| Grok Build 0.1 | $1.00 | $2.00 | $0.20 |  | 256K | $90.00 | 2026-05-20 |
| Grok 4.3 | $1.25 | $2.50 | $0.20 | $1.00 / $2.00 | 1M | $112.50 | 2026-04-30 |
| Grok 4.20 Multi-Agent | $1.25 | $2.50 | $0.20 |  | 2M | $112.50 | 2026-03-31 |
| Grok 4.20 | $1.25 | $2.50 | $0.20 |  | 2M | $112.50 | 2026-03-31 |

[Compare xAI with every other provider](https://shurco.ai/tools/llm-api-pricing/)

## Common questions

### How much does the Grok API cost?

On 25 September 2026, xAI models on this list cost from $1.00 per million input tokens (Grok Build 0.1) to $2.00 (Grok 4.6), and from $2.00 per million output tokens (Grok Build 0.1) to $6.00 (Grok 4.6).

### What is the cheapest Grok model?

For a typical mix of three input tokens to every output token, the cheapest is Grok Build 0.1 at $1.00 per million input tokens and $2.00 per million output tokens.

### What is the newest Grok model on the list?

Grok 4.7, listed on 21 September 2026, at $1.60 per million input tokens and $4.80 per million output tokens.

### Which Grok model has the largest context window?

Grok 4.20 Multi-Agent, with 2M tokens of context.

### Does xAI offer batch pricing?

Yes, 1 of its models on this list show a batch price, with batch input at a median of 80 percent of the standard price. Batch suits work that can wait for its answer.

## Other providers

[GPT](https://shurco.ai/tools/llm-api-pricing/openai/)[Claude](https://shurco.ai/tools/llm-api-pricing/anthropic/)[Gemini](https://shurco.ai/tools/llm-api-pricing/google/)[DeepSeek](https://shurco.ai/tools/llm-api-pricing/deepseek/)[Mistral](https://shurco.ai/tools/llm-api-pricing/mistral/)[Llama](https://shurco.ai/tools/llm-api-pricing/meta/)[Qwen](https://shurco.ai/tools/llm-api-pricing/qwen/)[Kimi](https://shurco.ai/tools/llm-api-pricing/moonshot/)[GLM](https://shurco.ai/tools/llm-api-pricing/zai/)[Command](https://shurco.ai/tools/llm-api-pricing/cohere/)[Nova](https://shurco.ai/tools/llm-api-pricing/amazon/)[MiniMax](https://shurco.ai/tools/llm-api-pricing/minimax/)

## Choosing a model for a production agent

Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. [Tell me what you are building.](https://shurco.ai/#contact)

Web version https://shurco.ai/tools/llm-api-pricing/xai/