Model detail
Grok 4.20 Reasoning
A reasoning member of the Grok 4.20 family supporting text and image inputs, tool calling, and structured responses.
Model specs
- Model ID
-
grok-4-20-reasoning
- Context length
- 1M
- Max output
- –
- I/O modalities
- Released
- 2026-03
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
OpenAI-compatible
/v1/chat/completionsPOST
03
Tiered pricing
Unit: /1M Tokens
| Tier | Input /1M Tokens | Output /1M Tokens | Cache read /1M Tokens |
|---|---|---|---|
| standard Length ≤ 200K | $1.2500 | $2.5000 | $0.2000 |
| long_context Length > 200K | $2.5000 | $5.0000 | $0.4000 |
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
A reasoning member of the Grok 4.20 family supporting text and image inputs
A reasoning member of the Grok 4.20 family supporting text and image inputs, tool calling, and structured responses.
What should you check before using it?
1,000,000 context tokens
xAI model that supports reasoning, tool calling and structured output. Knowledge cutoff: 2025-09. Released 2026-03-10.
Why use it through MixRoute?
Grok 4.20 takes text and images on one route
Text and image inputs share the same route and the same key. MixRoute serves Grok 4.20 on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID grok-4-20-reasoning and re-run your integration tests.
07
Capabilities & compatibility
Unconfirmed capabilities stay "Unknown," no guesses
Tool calling
Grok 4.20 supports function and tool calls.
tools definition; the response returns tool_calls to execute and feed results back.
Structured output
Grok 4.20 can produce JSON-formatted output on demand.
response_format: { type: "json_schema" } forces valid JSON output.
Streaming
Grok 4.20 supports streamed responses.
stream: true streams tokens incrementally, so chat UIs render as they arrive.
Prompt caching
Grok 4.20 supports prompt caching under supported routing conditions.
Vision input
Grok 4.20 can process image inputs alongside text.
image_url content part alongside text messages.
OpenAI SDK
Call Grok 4.20 through MixRoute's OpenAI-compatible endpoint.
base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.
08
Token cost estimator
Live estimate from this page's pricing, not an actual bill
Share of the same prefix read repeatedly, up to 100%
09
FAQ
Before switching production traffic to Grok 4.20, run a pilot on a representative slice of your traffic and check output quality, latency at peak concurrency, and cost per request. Verify the error and retry behaviour, and confirm the request limits you depend on match your plan.
One endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.