How much does the Grok 4.6 API cost?

Grok 4.6 costs $2 per 1M input tokens and $6 per 1M output tokens on Inferray, and cached input is $0.5 per 1M. That is the list price, with no gateway fee on top.

Is there a free tier for Grok 4.6?

No. You add credit and pay Grok 4.6's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is Grok 4.6 included in Token Plans?

No. Grok 4.6 is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use Grok 4.6 in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to grok-4-6. The same key works in Codex, opencode, Cline, and other agents.

Does Grok 4.6 support tool calling and vision?

Grok 4.6 supports tool calling, image input, reasoning, JSON output and streaming on Inferray.

Is it the real Grok 4.6?

Yes. A request for grok-4-6 is answered by Grok 4.6 from xAI, billed at its published list price. Inferray never substitutes a different or smaller model.

xAIChatgrok-4-6

Grok 4.6 API

Input: $2per 1M tokens
Output: $6per 1M tokens
Cached input: $0.5per 1M tokens
Context: 500K

No gateway feesPay-as-you-go only

Grok 4.6 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Explore Grok 4.6 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses through the unified API. Supported interfaces and current availability are shown below.

OpenAI-style Chat Completions
Anthropic-style Messages
OpenAI-style Responses

Get your API key Try in playground Compare models

Model details

Context window: 500K tokens
Max output: —
Input: Text, images
Output: Text
Capabilities: Reasoning, Vision, Tool calling, Streaming, JSON output
Interfaces: OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Grok 4.6 API pricing

Prices use the units shown below. No gateway fees. Usage, size and model options may affect the total.

Grok 4.6 pricing.
Metric	Price
/ 1M input tokens	$2
/ 1M output tokens	$6
/ 1M cached input tokens	$0.5
/ content review	$0.05
/ 1M input tokens · Up to 200K input tokens	$2
/ 1M output tokens · Up to 200K input tokens	$6
/ 1M cached input tokens · Up to 200K input tokens	$0.5
/ 1M input tokens · Above 200K input tokens	$4
/ 1M output tokens · Above 200K input tokens	$12
/ 1M cached input tokens · Above 200K input tokens	$1

What Grok 4.6 costs for real work

Typical workloads at list price, worked out from the rates above. Nothing is added on top.

Workload	Tokens	Cost
1,000 chat replies	1,500 tokens in, 400 out, each	$5.40
Summarise a 100-page document	60K tokens in, 2K out	$0.132
10M tokens of coding-agent work	10M tokens: 85% cached input, 12% fresh input, 3% output	$8.45
1M output tokens	Generated text only	$6.00

Grok 4.6 is pay-as-you-go only

Grok 4.6 is not included in Token Plans. Call it from a pay-as-you-go balance at the list price above, with no gateway fee.

Why teams pick it

Grok 4.6 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call Grok 4.6

Grok 4.6 answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

/v1/chat/completionsOpenAI-style Chat Completions · openai SDK or plain HTTP

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok-4-6",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

/v1/messagesAnthropic-style Messages · @anthropic-ai/sdk SDK or plain HTTP

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok-4-6",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

/v1/responsesOpenAI-style Responses · openai SDK or plain HTTP

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok-4-6",
  "input": "Hello"
}'

Conversation compaction is also available at POST /v1/responses/compact.

Use Grok 4.6 in your tools

Every coding agent below has a setup guide. Set the model to grok-4-6.

Run Grok 4.6 in Claude Code

Alternatives to Grok 4.6

Questions about this model

How much does the Grok 4.6 API cost?: Grok 4.6 costs $2 per 1M input tokens and $6 per 1M output tokens on Inferray, and cached input is $0.5 per 1M. That is the list price, with no gateway fee on top.
Is there a free tier for Grok 4.6?: No. You add credit and pay Grok 4.6's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.
Am I charged for failed requests?: No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.
Is Grok 4.6 included in Token Plans?: No. Grok 4.6 is pay-as-you-go only; Token Plans cover the other text models in the catalog.
Can I use Grok 4.6 in Claude Code?: Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to grok-4-6. The same key works in Codex, opencode, Cline, and other agents.
Does Grok 4.6 support tool calling and vision?: Grok 4.6 supports tool calling, image input, reasoning, JSON output and streaming on Inferray.
Is it the real Grok 4.6?: Yes. A request for grok-4-6 is answered by Grok 4.6 from xAI, billed at its published list price. Inferray never substitutes a different or smaller model.

Prices from the catalog as of November 12, 2026.