grok-4.20-reasoning

Text

Reasoning-oriented Grok variant built for multi-step problem solving and agentic tool use, with strict prompt adherence and low hallucination.

Input price

$2.12515% off

Market: $2.5

/ M

Output price

$4.2515% off

Market: $5

/ M

Cache read

$0.3415% off

Market: $0.4

/ M

Cache write

$015% off

/ M

Input

Text

Output

Text

API

Quick Start

Drop-in code to call this model with EasyAPI's OpenAI-compatible API.

Get your API key

Create an API key from your dashboard and set it as an environment variable:

Replace sk-xxxxxxxx with your API token from the console (Bearer token).

Create API token

shell

export EASYAPI_API_KEY=sk-xxxxxxxx

Make your first request

Use xai/grok-4.20-reasoning with the EasyAPI API:

cURL

curl https://token.easyapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{"model":"xai/grok-4.20-reasoning","messages":[{"role":"user","content":"Hello!"}]}'

Enable streaming

Add "stream": true to your request body to receive responses as server-sent events:

curl

curl -N https://token.easyapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{"model":"xai/grok-4.20-reasoning","messages":[{"role":"user","content":"Hello!"}],"stream":true}'

Endpoint

Sends a chat completion request. Supports streaming and non-streaming modes.

POSThttps://token.easyapi.com/v1/chat/completions

Authorization: Bearer $EASYAPI_API_KEY
Content-Type: application/json
Model: xai/grok-4.20-reasoning

发送对话补全请求，支持流式与非流式。 Docs

GEThttps://token.easyapi.com/v1/models

Authorization: Bearer $EASYAPI_API_KEY

获取当前账户可用模型列表。 Docs

Parameters

Name	Type	Default	Description
`model`	string	—	模型 ID，如 openai/gpt-4o、anthropic/claude-3-5-sonnet
`messages`	array	—	对话消息列表，每项含 role 与 content
`stream`	boolean	false	设为 true 时以 SSE 流式返回
`temperature`	float	1	采样温度，越高越随机
`max_tokens`	integer	—	单次回复最大生成 Token 数
`top_p`	float	1	核采样，限制候选词累积概率
`frequency_penalty`	float	0	频率惩罚，降低重复用词
`presence_penalty`	float	0	存在惩罚，鼓励新话题

Using third-party SDKs

Official OpenAI and other SDKs work by swapping the base URL. See integration guide

Related models

grok-4.20

xAI

Reasoning-oriented Grok variant built for multi-step problem solving and agentic tool use, with strict prompt adherence and low hallucination.

TextMultimodal

15% off

Input price

$2.125/ M

Output price

$4.25/ M

Cache read

$0.34/ M

Cache write

$0/ M

grok-4.20-multi-agent

xAI

Multi-agent variant that dispatches sub-agents in parallel for deep research, multi-step reasoning, and tool orchestration.

TextMultimodal

15% off

Input price

$3.4/ M

Output price

$10.2/ M

Cache read

$0.34/ M

Cache write

$0/ M

grok-4.3

xAI

Grok 4.3 is a reasoning model from xAI that supports text and image inputs with text output. It is suited for agentic workflows, instruction following, long-document analysis, and deep research. The model supports a 1M token context window. Requests above 200K total tokens are billed at a higher rate.

TextMultimodal

15% off

Input price

$2.125/ M

Output price

$4.25/ M

Cache read

$0.34/ M

Cache write

$0/ M

grok-4.5

xAI

Grok's flagship reasoning model, running an internal chain of thought before responding. Strong performance on coding and STEM tasks, with support for text, image, and file inputs. Suited for technical problem-solving and long-document analysis.

TextMultimodal

15% off

Input price

$1.7/ M

Output price

$5.1/ M

Cache read

$0.425/ M

Cache write

$0/ M