Pricing
Cheap GPT API
Access GPT models through Tokely with your OpenAI SDK. Compare input, output and cached-token prices with OpenAI rates. Pay as you go.
tokely.me/cheap-gpt-api
Grok API pricing: Grok 4.3 to 4.7
Grok 4.3: $0.1875 input / $0.375 output per 1M tokens. Up to 85% off selected models vs Grok prices. Pay as you go.
By TokelyReviewed Tokely serves Grok 4.3, 4.5, 4.6 and 4.7 through its OpenAI-compatible endpoint. Grok 4.3 is the low-cost option; 4.5 to 4.7 are the newer, stronger models. The table lists each version's Tokely rate and the published reference price.
Grok API price comparison
| Model | Tokely input / output | Tokely example | model developer example | Discount vs model developer |
|---|---|---|---|---|
| Grok 4.3Grok | $0.1875 / $0.375Cache read: $0.1875 | $0.28125 | $1.875$1.25 / $2.5 per 1M | 85.0% off |
| Grok Build 0.1Grok | $0.404415 / $0.80883Cache read: $0.404415 | $0.606623 | $1.5$1 / $2 per 1M | 59.6% off |
| Grok 4.20 Non ReasoningGrok | $0.505519 / $1.011038Cache read: $0.505519 | $0.758279 | $1.875$1.25 / $2.5 per 1M | 59.6% off |
| Grok 4.20 ReasoningGrok | $0.505519 / $1.011038Cache read: $0.505519 | $0.758279 | $1.875$1.25 / $2.5 per 1M | 59.6% off |
| Grok 4.5Grok | $1.4 / $4.2Cache read: $0.21 | $2.45 | $3.5$2 / $6 per 1M | 30.0% off |
| Grok 4.6Grok | $1.4 / $4.2Cache read: $0.35 | $2.45 | $3.5$2 / $6 per 1M | 30.0% off |
| Grok 4.7Grok | $1.4 / $4.2Cache read: $0.35 | $2.45 | $3.5$2 / $6 per 1M | 30.0% off |
Pick the version
Grok 4.3 suits high-volume chat and extraction at a low per-token rate. Grok 4.5 to 4.7 target harder reasoning and coding. Keep the version fixed when you compare prices.
Verified on Tokely
Grok 4.3 was tested with streaming usage, JSON mode, sampling controls, reasoning effort, inline image input and prompt caching through api.tokely.me.
One key for every model
Every model on this page is available through one OpenAI-compatible endpoint and one balance, with routing modes, bounded fallback, spending limits and request logs.
LLM gateway: one API for every model ↗
A hosted LLM gateway with one OpenAI-compatible endpoint, account routing modes, bounded fallback, spending limits and request logs. Text, image, video and audio from one balance.
OpenAI-compatible API for Claude, Gemini, GPT and more ↗
Keep the OpenAI SDK and call Claude, Gemini, GPT, Kimi, GLM and other supported models. Change the base URL, key and model ID.
Questions before you switch
How do I call the Grok API with the OpenAI SDK?
Set base_url to https://api.tokely.me/v1, use your Tokely key and a model such as grok-4.3.
Do I need an xAI account?
No. Usage is billed from your Tokely balance.
START WITH YOUR OWN WORKLOADKnow the price.
Know the price.
Then make the call.
Check the model, compare the rate, and connect with a Tokely key.