Cheaper Inference

A little less waiting. A lot more saving.

Getting your workspace ready…

grok-4.20-non-reasoning-beta API pricing, specs and examples · CheaperInference

Provider: spacexai
Model ID: grok-4.20-non-reasoning-beta
Type: Text generation
Endpoints: /v1/chat/completions, /v1/responses, /v1/messages
Input: text (verified request)
Output: text (verified text endpoint)
Vision input: Supported
Image editing: Not supported
Video input: Not supported
Reasoning: Not supported
Streaming: Supported
Context window: 2,000,000 tokens
Maximum output: 2,000,000 tokens

POST /v1/chat/completions

curl https://api.cheaperinference.com/v1/chat/completions \  -H "Authorization: Bearer ci_live_YOUR_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "grok-4.20-non-reasoning-beta",    "messages": [      {        "role": "user",        "content": "Reply with the single word OK."      }    ]  }'

POST /v1/responses

curl https://api.cheaperinference.com/v1/responses \  -H "Authorization: Bearer ci_live_YOUR_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "input": [      {        "role": "user",        "content": "Reply with the single word OK."      }    ],    "model": "grok-4.20-non-reasoning-beta",    "store": false  }'

POST /v1/messages

curl https://api.cheaperinference.com/v1/messages \  -H "Authorization: Bearer ci_live_YOUR_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "grok-4.20-non-reasoning-beta",    "messages": [      {        "role": "user",        "content": "Reply with the single word OK."      }    ],    "max_tokens": 1024  }'

Workloads to evaluate

Evaluate summarization, drafting, and question answering with examples from your own application.
Include image-based questions when your request uses a supported image input format.
Test tool calls against your application's actual function schemas before connecting actions.

Limits and tradeoffs

Requests above 200,000 input tokens may use a different price tier; the pricing section lists that tier separately.
Reported capabilities and production speed measurements describe access and observed traffic; task quality still needs an evaluation with your own examples.

$1.59375 estimated at displayed rates

1,000,000 ÷ 1,000,000 × $1.0625 + 250,000 ÷ 1,000,000 × $2.125

The same billed quantities at the listed reference rates: $1.875.

Uses uncached input at the displayed standard rates, with no extra modalities or tools. Billed output includes any charged reasoning tokens. Actual token counts, price tiers, and marketplace prices can change the total.

Price quote effective Oct 31, 2026, 7:37 PM UTC.

Python: pip install openai · Node.js: npm install openai. Set CHEAPER_INFERENCE_API_KEY on your server.

import osfrom openai import OpenAIclient = OpenAI(    api_key=os.environ["CHEAPER_INFERENCE_API_KEY"],    base_url="https://api.cheaperinference.com/v1",)request = {    "input": [        {            "role": "user",            "content": "Reply with the single word OK.",        },    ],    "model": "grok-4.20-non-reasoning-beta",    "store": False,}response = client.responses.create(**request)print(response.output_text)

import OpenAI from "openai";const client = new OpenAI({  apiKey: process.env.CHEAPER_INFERENCE_API_KEY,  baseURL: "https://api.cheaperinference.com/v1",});const response = await client.responses.create({  "input": [    {      "role": "user",      "content": "Reply with the single word OK."    }  ],  "model": "grok-4.20-non-reasoning-beta",  "store": false});console.log(response.output_text);

For other supported endpoints and their exact parameters, use the request samples and parameter reference on this page. Read the API integration guide.

Current model pricing and context compared with related models
Model	Current pricing	Context limit	Image input listed
grok-4.20-non-reasoning-beta (this model)spacexai	$1.0625 input / $2.125 output per 1M tokens	2,000,000 tokens	Yes
grok-4.20-reasoning-betaspacexai	$0.8125 input / $1.625 output per 1M tokens	2,000,000 tokens	Yes
grok-4.20-non-reasoning-batchspacexai	$0.85 input / $1.70 output per 1M tokens	2,000,000 tokens	Yes

grok-4.20-non-reasoning-beta

What you pay

Reliability and speed

Stop paying list price for tokens.

At a glance

Send a request

About grok-4.20-non-reasoning-beta

Workloads to evaluate

Limits and tradeoffs

Example: 1,000 text requests

grok-4.20-non-reasoning-beta API examples

Compare grok-4.20-non-reasoning-beta with related models

Parameters by endpoint

Pricing history

grok-4.20-non-reasoning-beta

When this model is cheapest

Popularity ranking

Product

Developers

Company

Legal