Skip to content

Model detail

Grok 4.6

Provided by xAI
Pay-as-you-go Dynamic pricing 2 tiers

Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

Model specs

Model ID
grok-4.6
Context length
500K
Max output
–
I/O modalities
Released
2026-08

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • OpenAI-compatible /v1/chat/completions POST

03

Tiered pricing

Unit: /1M Tokens

Tier Input /1M Tokens Output /1M Tokens Cache read /1M Tokens
standard Length ≤ 200K $2.0000 $6.0000 $0.5000
long_context Length > 200K $4.0000 $12.0000 $1.0000

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Flash model for fast, efficient inference

Grok 4.6: SpaceXAI's frontier model for coding, agentic tasks, and knowledge work.. 500,000-token context.

What should you check before using it?

500,000 context, 0 output

Grok 4.6 by Xai. Knowledge cutoff: 2026-02-01.

Why use it through MixRoute?

Available through MixRoute's OpenAI-compatible endpoint

Set the model parameter to "grok-4.6" and use your MixRoute API key.

07

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Available:

Tool calling

Grok 4.6 supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.
Available:

Structured output

Grok 4.6 can produce JSON-formatted output on demand.

EX response_format: { type: "json_schema" } forces valid JSON output.
Available:

Streaming

Grok 4.6 supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.
Available:

Prompt caching

Grok 4.6 supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.
Available:

Vision input

Grok 4.6 can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.
Available:

OpenAI SDK

Call Grok 4.6 through MixRoute's OpenAI-compatible endpoint.

EX Change 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

Grok 4.6 supports prompt caching where available. Stable prefixes such as system prompts and tool definitions benefit most.

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.

Create an API key View integration docs