X Ai model

Grok 4.20 NON Reasoning API

x-ai/grok-4.20-non-reasoning costs $1.25 per 1M input tokens. Skip it if you need a published context window, because the catalog does not publish one. It is the Model id for Grok 4.20 NON Reasoning from X Ai.

Read quickstartEstimate cost
X AiPlatform curatedCatalog
Function CallingVision
Input price$1.25 / 1M tokens
Output price$2.50 / 1M tokens
Context length256k tokens
Max output8.2k tokens

What is Grok 4.20 NON Reasoning API in NextModel?

x-ai/grok-4.20-non-reasoning costs $1.25 per 1M input tokens. Skip it if you need a published context window, because the catalog does not publish one. It is the Model id for Grok 4.20 NON Reasoning from X Ai.

grok-4-20-non-reasoning via NextModel: 256k-token context; $1.25 / 1M tokens in / $2.50 / 1M tokens out per 1M tokens. Capabilities: streaming.

Best use cases

  • Call it when the catalog's quality use case matches your task and streaming is sufficient.
  • It has a published input price of $1.25 per 1M tokens and a published output price of $2.50 per 1M tokens.
  • You need the listed capabilities on this catalog entry.

When not to use

  • Do not call it if you need a published context window.
  • Do not call it if you need first-party CacheSafety data; the bench table has no first-party CacheSafety row for this exact model.
  • A required number is unpublished in the catalog snapshot.

OpenAI-compatible code example

request.sh
curl https://api.nextmodel.app/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NEXTMODEL_API_KEY" \
  -d '{"model":"x-ai/grok-4.20-non-reasoning","messages":[{"role":"user","content":"Reply with OK."}]}'

Switching models only changes the model field.

Try it in the playground

Similar alternatives

X AiCatalog

grok-4-1-fast-non-reasoning

grok-4-1-fast-non-reasoning via NextModel: 2M-token context; $0.2 / 1M tokens in / $0.5 / 1M tokens out per 1M tokens. Capabilities: streaming.

$0.2 / 1M tokensInput$0.5 / 1M tokensOutput2MContext
Best forGeneral chat via X Ai, API workloads
Streaming
Platform curatedCurated and maintained in the NextModel catalog
View details
X AiCatalog

grok-4-1-fast-reasoning

grok-4-1-fast-reasoning via NextModel: 2M-token context; $0.2 / 1M tokens in / $0.5 / 1M tokens out per 1M tokens. Capabilities: streaming.

$0.2 / 1M tokensInput$0.5 / 1M tokensOutput2MContext
Best forGeneral chat via X Ai, API workloads
Streaming
Platform curatedCurated and maintained in the NextModel catalog
View details
X AiCatalog

grok-4-20-reasoning

grok-4-20-reasoning via NextModel: 256k-token context; $1.25 / 1M tokens in / $2.50 / 1M tokens out per 1M tokens. Capabilities: streaming.

$1.25 / 1M tokensInput$2.50 / 1M tokensOutput256kContext
Best forGeneral chat via X Ai, API workloads
Streaming
Platform curatedCurated and maintained in the NextModel catalog
View details

Compare grok-4-20-non-reasoning

grok-4-20-non-reasoning vs grok-4-1-fast-non-reasoninggrok-4-20-non-reasoning vs grok-4-1-fast-reasoninggrok-4-20-non-reasoning vs grok-4-20-reasoninggrok-4-20-non-reasoning vs Kimi K3 GLBgrok-4-20-non-reasoning vs GPT-5 Codex

Reading

Articles that explain grok-4-20-non-reasoning

FAQ

grok-4-20-non-reasoning API questions

What model id do I send for Grok 4.20 NON Reasoning?

Send x-ai/grok-4.20-non-reasoning to https://api.nextmodel.app/v1 with your OpenAI SDK. If that id is missing from /v1/models, the page is stale.

What does the catalog list for price and context?

Grok 4.20 NON Reasoning is listed at $1.25 / 1M tokens input and $2.50 / 1M tokens output. Context window: not published in catalog.

What should I treat as unverified?

Do not call it if you need a published context window. Do not call it if you need first-party CacheSafety data; the bench table has no first-party CacheSafety row for this exact model.

Start now

Ready to start building?

Passwordless signup, pay-as-you-go billing, and one OpenAI-compatible endpoint for every model. Create your key and send your first request in minutes.

Get your API keyRead the quickstart