AI model gateway

Read Docs Open Console

xAI

xAI models, pricing, and protocols

25 currently available models with pricing synced from the MoleAPI console.

25 models

X

grok-4.6 is a xAI model available through MoleAPI with openai, openai-response, openai-response-compact, anthropic, gemini, openai-alpha-search access. It fits OpenAI compatible, Responses API, Anthropic compatible, Gemini compatible workflows, with pricing synced from the MoleAPI console.

Success: 100.0%
Avg latency: 15.6s

defaultx1

Input$2 / 1M tokens

Output$6 / 1M tokens

Cache read$0.5 / 1M tokens

discountx0.8

Input$1.6 / 1M tokens

Output$4.8 / 1M tokens

Cache read$0.4 / 1M tokens

relayx0.3

Input$0.6 / 1M tokens

Output$1.8 / 1M tokens

Cache read$0.15 / 1M tokens

tempx0.1

Input$0.2 / 1M tokens

Output$0.6 / 1M tokens

Cache read$0.05 / 1M tokens

openaiopenai-responseopenai-response-compactanthropicgeminiopenai-alpha-searchOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare

X

grok-4.5-90%Official profile verified

Grok 4.5 is xAI's flagship model for code and general tasks, with agentic tool calling and configurable reasoning.

defaultx1

Input$2 / 1M tokens

Output$6 / 1M tokens

Cache read$0.5 / 1M tokens

discountx0.8

Input$1.6 / 1M tokens

Output$4.8 / 1M tokens

Cache read$0.4 / 1M tokens

relayx0.3

Input$0.6 / 1M tokens

Output$1.8 / 1M tokens

Cache read$0.15 / 1M tokens

tempx0.1

Input$0.2 / 1M tokens

Output$0.6 / 1M tokens

Cache read$0.05 / 1M tokens

AA index 54openaiopenai-responseopenai-response-compactanthropicgeminiopenai-alpha-searchOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare

X

grok-composer-2.5-fast-70%

Grok model by xAI for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1

Input$3 / 1M tokens

Output$15 / 1M tokens

Cache read$0.5 / 1M tokens

discountx0.8

Input$2.4 / 1M tokens

Output$12 / 1M tokens

Cache read$0.4 / 1M tokens

relayx0.3

Input$0.9 / 1M tokens

Output$4.5 / 1M tokens

Cache read$0.15 / 1M tokens

openaiopenai-responseopenai-response-compactanthropicgeminiopenai-alpha-searchOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare

X

grok-4.5-latest-70%Official profile verified

Grok 4.5 is xAI's flagship model for code and general tasks, with agentic tool calling and configurable reasoning.

defaultx1

Input$2 / 1M tokens

Output$6 / 1M tokens

Cache read$0.5 / 1M tokens

discountx0.8

Input$1.6 / 1M tokens

Output$4.8 / 1M tokens

Cache read$0.4 / 1M tokens

relayx0.3

Input$0.6 / 1M tokens

Output$1.8 / 1M tokens

Cache read$0.15 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

X

Grok model by xAI for general chat, writing, coding assistance, and tool-assisted workflows.

Success: 0.0%
Avg latency: 1.6s

defaultx1

Input$1.25 / 1M tokens

Output$2.5 / 1M tokens

Cache read$0.2 / 1M tokens

discountx0.8

Input$1 / 1M tokens

Output$2 / 1M tokens

Cache read$0.16 / 1M tokens

relayx0.3

Input$0.375 / 1M tokens

Output$0.75 / 1M tokens

Cache read$0.06 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

X

grok-4.20-0309-non-reasoning-70%

Grok reasoning model by xAI for complex problem solving, analysis, coding, and agent workflows.

defaultx1

Input$2 / 1M tokens

Output$6 / 1M tokens

Cache read$0.2 / 1M tokens

discountx0.8

Input$1.6 / 1M tokens

Output$4.8 / 1M tokens

Cache read$0.16 / 1M tokens

relayx0.3

Input$0.6 / 1M tokens

Output$1.8 / 1M tokens

Cache read$0.06 / 1M tokens

openaiOpenAI compatibleReasoningPrompt cacheCompare

X

grok-4.20-0309-reasoning-70%

Grok reasoning model by xAI for complex problem solving, analysis, coding, and agent workflows.

defaultx1

Input$2 / 1M tokens

Output$6 / 1M tokens

Cache read$0.2 / 1M tokens

discountx0.8

Input$1.6 / 1M tokens

Output$4.8 / 1M tokens

Cache read$0.16 / 1M tokens

relayx0.3

Input$0.6 / 1M tokens

Output$1.8 / 1M tokens

Cache read$0.06 / 1M tokens

openaiOpenAI compatibleReasoningPrompt cacheCompare

X

grok-4.20-beta-0309-non-reasoning

Grok reasoning model by xAI for complex problem solving, analysis, coding, and agent workflows.

defaultx1

Input$2 / 1M tokens

Output$6 / 1M tokens

Cache read$0.2 / 1M tokens

openaiOpenAI compatibleReasoningPrompt cacheCompare

X

grok-4.20-beta-0309-reasoning

Grok reasoning model by xAI for complex problem solving, analysis, coding, and agent workflows.

defaultx1

Input$2 / 1M tokens

Output$6 / 1M tokens

Cache read$0.2 / 1M tokens

openaiOpenAI compatibleReasoningPrompt cacheCompare

X

grok-4.20-non-reasoning-70%

Grok reasoning model by xAI for complex problem solving, analysis, coding, and agent workflows.

Success: 100.0%
Avg latency: 1.7s

defaultx1

Input$2 / 1M tokens

Output$6 / 1M tokens

Cache read$0.5 / 1M tokens

discountx0.8

Input$1.6 / 1M tokens

Output$4.8 / 1M tokens

Cache read$0.4 / 1M tokens

relayx0.3

Input$0.6 / 1M tokens

Output$1.8 / 1M tokens

Cache read$0.15 / 1M tokens

openaiOpenAI compatibleReasoningPrompt cacheCompare

X

grok-4.20-reasoning-70%

Grok reasoning model by xAI for complex problem solving, analysis, coding, and agent workflows.

defaultx1

Input$1.25 / 1M tokens

Output$2.5 / 1M tokens

Cache read$0.2 / 1M tokens

discountx0.8

Input$1 / 1M tokens

Output$2 / 1M tokens

Cache read$0.16 / 1M tokens

relayx0.3

Input$0.375 / 1M tokens

Output$0.75 / 1M tokens

Cache read$0.06 / 1M tokens

openaiOpenAI compatibleReasoningPrompt cacheCompare

X

Grok model by xAI for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1

Input$3 / 1M tokens

Output$15 / 1M tokens

Cache read$0.75 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

X

grok-4-1-fast-non-reasoning

Grok reasoning model by xAI for complex problem solving, analysis, coding, and agent workflows.

Success: 100.0%
Avg latency: 3.4s

defaultx1

Input$0.2 / 1M tokens

Output$0.5 / 1M tokens

Cache read$0.05 / 1M tokens

openaiOpenAI compatibleReasoningPrompt cacheCompare

X

grok-4-1-fast-reasoning

Grok reasoning model by xAI for complex problem solving, analysis, coding, and agent workflows.

defaultx1

Input$0.2 / 1M tokens

Output$0.5 / 1M tokens

Cache read$0.05 / 1M tokens

openaiOpenAI compatibleReasoningPrompt cacheCompare

X

grok-4-fast-non-reasoning

Grok reasoning model by xAI for complex problem solving, analysis, coding, and agent workflows.

defaultx1

Input$0.2 / 1M tokens

Output$0.5 / 1M tokens

Cache read$0.05 / 1M tokens

openaiOpenAI compatibleReasoningPrompt cacheCompare

X

grok-4-fast-reasoning

Grok reasoning model by xAI for complex problem solving, analysis, coding, and agent workflows.

defaultx1

Input$0.2 / 1M tokens

Output$0.5 / 1M tokens

Cache read$0.05 / 1M tokens

openaiOpenAI compatibleReasoningPrompt cacheCompare

X

Grok model by xAI for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1

Input$3 / 1M tokens

Output$15 / 1M tokens

Cache read$0.75 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

X

Grok model by xAI for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1

Input$0.3 / 1M tokens

Output$0.5001 / 1M tokens

Cache read$0.075 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

X

grok-composer-70%

grok-composer is a xAI model available through MoleAPI with openai, openai-response, openai-response-compact, anthropic, gemini, openai-alpha-search access. It fits OpenAI compatible, Responses API, Anthropic compatible, Gemini compatible workflows, with pricing synced from the MoleAPI console.

relayx0.3

Input$22.5 / 1M tokens

Output$22.5 / 1M tokens

openaiopenai-responseopenai-response-compactanthropicgeminiopenai-alpha-searchOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleCompare

X

grok-imagine-image-2.0-70%

grok-imagine-image-2.0 is a xAI model available through MoleAPI with openai access. It fits OpenAI compatible, Vision workflows, with pricing synced from the MoleAPI console.

defaultx1

Input$75 / 1M tokens

Output$75 / 1M tokens

discountx0.8

Input$60 / 1M tokens

Output$60 / 1M tokens

relayx0.3

Input$22.5 / 1M tokens

Output$22.5 / 1M tokens

openaiOpenAI compatibleVisionCompare

X

grok-build-0.1-70%

Grok model by xAI for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1

Input$1 / 1M tokens

Output$2 / 1M tokens

Cache read$0.2 / 1M tokens

discountx0.8

Input$0.8 / 1M tokens

Output$1.6 / 1M tokens

Cache read$0.16 / 1M tokens

relayx0.3

Input$0.3 / 1M tokens

Output$0.6 / 1M tokens

Cache read$0.06 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

X

grok-code-fast-1

Grok coding model by xAI for code generation, repository understanding, debugging, and agentic development.

defaultx1

Input$0.2 / 1M tokens

Output$1.5 / 1M tokens

Cache read$0.02 / 1M tokens

openaiOpenAI compatibleCodingPrompt cacheCompare

X

Grok model by xAI for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1

Input$1 / 1M tokens

Output$2 / 1M tokens

Cache read$0.2 / 1M tokens

discountx0.8

Input$0.8 / 1M tokens

Output$1.6 / 1M tokens

Cache read$0.16 / 1M tokens

relayx0.3

Input$0.3 / 1M tokens

Output$0.6 / 1M tokens

Cache read$0.06 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

X

grok-build-latest-70%

Grok model by xAI for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1

Input$1 / 1M tokens

Output$2 / 1M tokens

Cache read$0.2 / 1M tokens

discountx0.8

Input$0.8 / 1M tokens

Output$1.6 / 1M tokens

Cache read$0.16 / 1M tokens

relayx0.3

Input$0.3 / 1M tokens

Output$0.6 / 1M tokens

Cache read$0.06 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

X

grok-latest-70%

Grok model by xAI for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1

Input$2 / 1M tokens

Output$6 / 1M tokens

Cache read$0.5 / 1M tokens

discountx0.8

Input$1.6 / 1M tokens

Output$4.8 / 1M tokens

Cache read$0.4 / 1M tokens

relayx0.3

Input$0.6 / 1M tokens

Output$1.8 / 1M tokens

Cache read$0.15 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare