MagicTools
LLM API Pricing Calculator (all models)

Grok 4.6 API Pricing and Cost Estimates

xAI Grok 4.6 API pricing is $2 per 1M input tokens and $6 per 1M output tokens. Cached input is billed at $0.5 per 1M tokens. The context window is 500K tokens. No batch tier is offered. Prices verified 2026-08-16 against the official pricing page.

Input / 1M tokens

$2

Output / 1M tokens

$6

Cached input / 1M

$0.5

Context window

500K

Monthly cost at three workloads

WorkloadTokens / monthStandard50% cache hit
Light (prototype / side project)5M in + 1M out$16.00$12.25
Medium (small production app)50M in + 10M out$160$123
Heavy (production at scale)500M in + 100M out$1600$1225

Note: Requests over 200K tokens bill at 2×.

Closest-priced alternatives

ModelInput / 1MOutput / 1MMedium workload / mo
xAI Grok 4.6$2$6$160
xAI Grok 4.5$2$6$160
Anthropic Claude Sonnet 5$2$10$200
Zhipu (z.ai) GLM-5.2$1.4$4.4$114
DeepSeek DeepSeek V4 Pro$1.3$3.91$104

Medium workload = 50M input + 10M output tokens per month at standard price, no caching. Prices verified 2026-08-16.

Calculate with your own volume

Back

LLM API Pricing Calculator

Compare current API prices for Claude, GPT, Gemini, DeepSeek, Kimi, Grok and other LLMs, and estimate your monthly bill from token volume. Includes prompt-caching prices and batch discounts that most comparison tables miss. Prices last verified 2026-08-16. Runs entirely in your browser — no upload, no signup.

M tokens
M tokens

Share of input tokens served from prompt cache

ModelInput $/MOutput $/MCached $/MContextEst. monthly

GPT-5.6 luna

OpenAI

$0.2$1.2$0.021.05M$22.00

Gemini 3.1 Flash-Lite

Google

$0.25$1.5$0.0251M$27.50

DeepSeek V4 Flash

DeepSeek · open-weight

$0.435$1.3$0.01451M$34.75

Gemini 3.6 Flash

Google

$0.75$3.75$0.0751M$75.00

GLM-5

Zhipu (z.ai) · open-weight

$1$3.2$0.2200K$82.00

Grok 4.20

xAI

$1.25$2.5$0.21M$87.50

Kimi K2.7 Code

Moonshot · open-weight

$0.95$4$0.19262K$87.50

Claude Haiku 4.5

Anthropic

$1$5$0.1200K$100

DeepSeek V4 Pro

DeepSeek · open-weight

$1.3$3.91$0.0431M$104

GLM-5.2

Zhipu (z.ai) · open-weight

$1.4$4.4$0.26200K$114

Grok 4.6

xAI

$2$6$0.5500K$160

Grok 4.5

xAI

$2$6$0.3500K$160

Claude Sonnet 5

Anthropic

$2$10$0.21M$200

GPT-5.6 terra

OpenAI

$2$12$0.21.05M$220

Gemini 3.1 Pro Preview

Google

$2$12$0.21M$220

Kimi K3

Moonshot · open-weight

$3$15$0.31.048576M$300

Claude Opus 5

Anthropic

$5$25$0.51M$500

GPT-5.6 sol

OpenAI

$5$30$0.51.05M$550

Claude Fable 5

Anthropic

$10$50$11M$1000

Prices are per 1 million tokens in USD, standard (non-batch) tier, verified 2026-08-16 against official pricing pages. Claude Sonnet 5: The $2 / $10 launch price is now permanent; the planned Sep 2026 increase to $3 / $15 was cancelled. GPT-5.6 sol: Requests beyond the long-context threshold bill at 2× input / 1.5× output. GPT-5.6 terra: Requests beyond the long-context threshold bill at 2× input / 1.5× output. GPT-5.6 luna: Requests beyond the long-context threshold bill at 2× input / 1.5× output. Gemini 3.1 Pro Preview: Prompts over 200K tokens bill at $4 / $18. Gemini 3.6 Flash: Intro price through Dec 31, 2026; $1.50 / $7.50 from Jan 1, 2027. Grok 4.6: Requests over 200K tokens bill at 2×. Grok 4.5: Requests over 200K tokens bill at 2×. Kimi K3: Always-on reasoning; output includes thinking tokens. DeepSeek V4 Pro: Peak-hour price (Beijing 09:00–12:00, 14:00–18:00) effective Aug 17, 2026; all other hours bill at 50% of peak. DeepSeek V4 Flash: Peak-hour price (Beijing 09:00–12:00, 14:00–18:00) effective Aug 17, 2026; all other hours bill at 50% of peak.

Batch discount is applied only to models whose provider offers an async batch tier. Cached-input pricing models the read price; cache-write surcharges (Anthropic) are not included. Long-context surcharges apply above provider thresholds and are noted per model.

FAQ

How much does the Grok 4.6 API cost?

$2 per 1M input tokens and $6 per 1M output tokens, with cached input at $0.5 per 1M. Note: Requests over 200K tokens bill at 2×. (Verified 2026-08-16.)

What does a month of Grok 4.6 cost in practice?

A medium workload of 50M input + 10M output tokens per month runs about $160/mo, or about $123/mo if half the input hits the prompt cache.

How does prompt caching change Grok 4.6 pricing?

Input tokens served from the prompt cache bill at $0.5 per 1M — about 25% of the standard input price. Repeated prefixes like system prompts and few-shot examples benefit most.

Is Grok 4.6 cheaper than Grok 4.5?

At the same medium workload, Grok 4.6 costs about $160/mo versus about $160/mo for xAI Grok 4.5. Also weigh quality, latency, and context window (500K vs 500K tokens).

API pricing for other models