Compare prices for the same model
USD per 1 million uncached text tokens. Each cell lists input / output. Short-context Standard rates; cache, tools, regional fees, taxes and funding fees are excluded.
| Exact model | Official provider | OpenRouter | API429 |
|---|---|---|---|
Grok 3grok-3 | Not verified in this review | No verified exact match | $0.9 / $4.5Base rate; full conditions below |
Grok 3 Minigrok-3-mini | Not verified in this review | No verified exact match | $0.09 / $0.15Base rate; full conditions below |
Grok 4grok-4 | Not verified in this review | No verified exact match | $0.9 / $4.5Base rate; full conditions below |
Grok 4 0709grok-4-0709 | Not verified in this review | No verified exact match | $0.9 / $4.5Base rate; full conditions below |
Grok 4 1 Fastgrok-4-1-fast | Not verified in this review | No verified exact match | $0.06 / $0.15Base rate; full conditions below |
Grok 4 Fastgrok-4-fast | Not verified in this review | No verified exact match | $0.06 / $0.15Base rate; full conditions below |
Grok 4 Fast Reasoninggrok-4-fast-reasoning | Not verified in this review | No verified exact match | $0.06 / $0.15Base rate; full conditions below |
Grok 4.3grok-4.3 | $1.25 / $2.5Global Standard; input <200,000 tokensSource | $1.25 / $2.5Base tier; context overrides applySource | $0.375 / $0.75Base rate; full conditions below |
Grok 4.5grok-4.5 | $2 / $6Global Standard; input <200,000 tokensSource | $2 / $6Base tier; context overrides applySource | $0.6 / $1.8$0.6 / 1,000,000 input tokens · Context up to 199,999 tokens inclusive |
Grok 4.6grok-4.6 | $2 / $6Global Standard; input <200,000 tokensSource | $2 / $6Base tier; context overrides applySource | $0.6 / $1.8$0.6 / 1,000,000 input tokens · Context up to 199,999 tokens inclusive |
Grok 4.7grok-4.7 | $2 / $6Global Standard; input <200,000 tokensSource | $2 / $6Base tier; context overrides applySource | $0.6 / $1.8$0.6 / 1,000,000 input tokens · Context up to 199,999 tokens inclusive |
Grok Buildgrok-build | Not verified in this review | No verified exact match | $0.3 / $0.6Base rate; full conditions below |
Grok Code Fastgrok-code-fast | Not verified in this review | No verified exact match | $0.06 / $0.45Base rate; full conditions below |
Grok Code Fast 1grok-code-fast-1 | Not verified in this review | No verified exact match | $0.06 / $0.45Base rate; full conditions below |
Grok Composer 2.5 Fastgrok-composer-2.5-fast | Not verified in this review | No verified exact match | $0.3 / $0.6Base rate; full conditions below |
OpenRouter amounts are model-list rates, excluding its separately listed platform fees. A missing quote means it was not verified for this comparison; it does not establish that the provider has no such model. Unverified reference figures are not filled with older or inferred prices.
The same workload, three budgets
Example: grok-4.7, 10 million input and 2 million output tokens across many short-context requests. No cache, tools or extra operations; this is not one 10-million-token prompt.
A changed token mix or context tier changes the result. For actual budgets, add billable reasoning, cache writes and tool use from your usage records.
The inclusive 200K boundary and regional pricing
For Grok 4.7 and 4.6, 199,999 input tokens still use the short-context rate; 200,000 use the long-context rate. xAI publishes a separate US regional endpoint with a 10% premium. This comparison uses Global Standard and does not silently substitute regional pricing.
Grok API access and subscriptions
Chat subscriptions and API requests follow separate billing terms. Web search, X search and hosted tools can add fees and require route support. Listing Grok in API429’s catalog does not mean that every direct xAI API feature is exposed through the gateway.
For agents, compare the whole conversation’s billable usage, including reasoning and resent history. A short user message does not always create a short billable prompt.
All published xAI / Grok rates in API429
These rows come from the live public API429 catalog, including conditional rates. Publication is separate from access under your key. GET /v1/models confirms your permitted models.
| Model | Rate and condition |
|---|---|
Grok 3grok-3 | $0.9 / 1,000,000 cached input tokens $0.9 / 1,000,000 input tokens $4.5 / 1,000,000 output tokens |
Grok 3 Minigrok-3-mini | $0.09 / 1,000,000 cached input tokens $0.09 / 1,000,000 input tokens $0.15 / 1,000,000 output tokens |
Grok 4grok-4 | $0.9 / 1,000,000 cached input tokens $0.9 / 1,000,000 input tokens $4.5 / 1,000,000 output tokens |
Grok 4 0709grok-4-0709 | $0.9 / 1,000,000 cached input tokens $0.9 / 1,000,000 input tokens $4.5 / 1,000,000 output tokens |
Grok 4 1 Fastgrok-4-1-fast | $0.06 / 1,000,000 cached input tokens $0.06 / 1,000,000 input tokens $0.15 / 1,000,000 output tokens |
Grok 4 Fastgrok-4-fast | $0.06 / 1,000,000 cached input tokens $0.06 / 1,000,000 input tokens $0.15 / 1,000,000 output tokens |
Grok 4 Fast Reasoninggrok-4-fast-reasoning | $0.06 / 1,000,000 cached input tokens $0.06 / 1,000,000 input tokens $0.15 / 1,000,000 output tokens |
Grok 4.3grok-4.3 | $0.375 / 1,000,000 cached input tokens $0.375 / 1,000,000 input tokens $0.75 / 1,000,000 output tokens |
Grok 4.5grok-4.5 | $0.09 / 1,000,000 cached input tokens · Context up to 199,999 tokens inclusive $0.18 / 1,000,000 cached input tokens · Context over 199,999 tokens $0.6 / 1,000,000 input tokens · Context up to 199,999 tokens inclusive $1.2 / 1,000,000 input tokens · Context over 199,999 tokens $1.8 / 1,000,000 output tokens · Context up to 199,999 tokens inclusive $3.6 / 1,000,000 output tokens · Context over 199,999 tokens |
Grok 4.6grok-4.6 | $0.15 / 1,000,000 cached input tokens · Context up to 199,999 tokens inclusive $0.3 / 1,000,000 cached input tokens · Context over 199,999 tokens $0.6 / 1,000,000 input tokens · Context up to 199,999 tokens inclusive $1.2 / 1,000,000 input tokens · Context over 199,999 tokens $1.8 / 1,000,000 output tokens · Context up to 199,999 tokens inclusive $3.6 / 1,000,000 output tokens · Context over 199,999 tokens |
Grok 4.7grok-4.7 | $0.15 / 1,000,000 cached input tokens · Context up to 199,999 tokens inclusive $0.3 / 1,000,000 cached input tokens · Context over 199,999 tokens $0.6 / 1,000,000 input tokens · Context up to 199,999 tokens inclusive $1.2 / 1,000,000 input tokens · Context over 199,999 tokens $1.8 / 1,000,000 output tokens · Context up to 199,999 tokens inclusive $3.6 / 1,000,000 output tokens · Context over 199,999 tokens |
Grok Buildgrok-build | $0.3 / 1,000,000 cached input tokens $0.3 / 1,000,000 input tokens $0.6 / 1,000,000 output tokens |
Grok Code Fastgrok-code-fast | $0.06 / 1,000,000 cached input tokens $0.06 / 1,000,000 input tokens $0.45 / 1,000,000 output tokens |
Grok Code Fast 1grok-code-fast-1 | $0.06 / 1,000,000 cached input tokens $0.06 / 1,000,000 input tokens $0.45 / 1,000,000 output tokens |
Grok Composer 2.5 Fastgrok-composer-2.5-fast | $0.3 / 1,000,000 cached input tokens $0.3 / 1,000,000 input tokens $0.6 / 1,000,000 output tokens |
API429 catalog generated: . Public source.
Connect the model and check the result
Create an API429 key and check the permitted model IDs before migrating a workload. Keep the key on your server. Review the request contract and inspect actual usage and charges on a small representative job before increasing volume.
Sources and comparison method
Reference rates checked October 2, 2026. Recheck after a model release, promotion or pricing change. Reference figures are hidden after their review deadline; current API429 prices load from the public catalog. Neither individual contracts nor discounts are inferred.