Grok 4.20 Non-Reasoning API via TokenMix

Use Grok 4.20 Non-Reasoning from xAI as a chat model through the TokenMix AI API relay and multi-model gateway.

High-performance model with industry-leading speed and agentic tool calling capabilities, offering the lowest hallucination rate with strict prompt adherence. Currently in beta.

API access

  • Base URL: https://api.tokenmix.ai/v1
  • Model ID: grok-4-20-non-reasoning
  • OpenAI SDK compatible. Change the base URL and use your TokenMix API key.

Pricing

Input $2/M tokens, output $6/M tokens

Capabilities

Vision, Function calling, JSON mode, Streaming

Model specs

  • Context: 2000K tokens
  • Max output: 30K tokens

Availability

2/2 available API endpoints are healthy right now.

Recent performance

TTFT 1022ms, latency 5712ms, throughput 196.0 tok/s.

Start using this model

Create an API key, top up from $1 when needed, and call this model through the TokenMix OpenAI-compatible endpoint.

Create API key · View pricing · Quickstart