Model prices / xAI / Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning)
xAI · released 2026-03-09
The official API price of Grok 4.20 (Non-Reasoning) is $1.25 per 1M input tokens and $2.5 per 1M output tokens (as of 2026-11-12). Context window: 1M tokens, up to 30K output tokens per request. 13 providers sell it, none below the official price.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| xAIOfficialTiered pricinggrok-4.20-0309-non-reasoning | $1.25 | $2.5 | $0.2 | OfficialTiered pricing | Official docs |
 AI/ML APIx-ai/ | $1.25 | $2.5 | $0.2 | Official docs | |
EEden AITiered pricingxai/ | $1.25 | $2.5 | $0.2 | Tiered pricing | Official docs |
 VertexTiered pricingxai/ | $1.25 | $2.5 | $0.2 | Tiered pricing | Official docs |
IImpossiblTiered pricingxai/ | $1.25 | $2.5 | $0.2 | Tiered pricing | Official docs |
 DevPass (LLM Gateway)Tiered pricinggrok-4-20-non-reasoning | $1.25 | $2.5 | $0.2 | Tiered pricing | Official docs |
LLLM GatewayTiered pricingvertex-openai/ | $1.25 | $2.5 | $0.2 | Tiered pricing | Official docs |
MMerge Gatewayxai/ | $1.25 | $2.5 | $0.2 | Official docs | |
OOCI Generative AITiered pricingxai. | $1.25 | $2.5 | $0.2 | Tiered pricing | Official docs |
TTempr GatewayTiered pricingxai/ | $1.25 | $2.5 | $0.2 | Tiered pricing | Official docs |
 Vercel AI GatewayTiered pricingspacexai/ | $1.25 | $2.5 | $0.2 | Tiered pricing | Official docs |
 Cloudflare AI Gatewayxai/ | $2 | $6 | $0.2 | Official docs |
3 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| DevPass (LLM Gateway)Tiered pricinggrok-4-20-beta-0309-non-reasoning | $2 | $6 | $0.2 | Tiered pricing | Official docs |
LLLM GatewayTiered pricingxai/ | $2 | $6 | $0.2 | Tiered pricing | Official docs |
 ZenMuxTiered pricingx-ai/ | $2 | $6 | $0.2 | Tiered pricing | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Grok model for agentic tool use, reasoning, coding, and live assistance
Description from models.dev.
Specs
- Type
- Text
- Context
- 1M
- Max output
- 30K
- Input
- Text, Image, PDF
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- —
- Open weights
- No
- Released
- 2026-03-09
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.