Deprecated on May 1, 2026. 4 providers still list it at the prices below.
Context
131K
Max output
131K
Serving providers
4
Cheapest input
$1.25 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: ARC Prize and Artificial AnalysisSpeed & latency
Output speed
100 t/s
tokens / second
Time to first token
1.65s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ARC-AGI-2 | 0% | default | $0.142 | |||||||||||||||||
| CritPt | 0% | default | — | |||||||||||||||||
| GPQA Diamond | 69% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 4% | default | — | |||||||||||||||||
| IFBench | 47% | default | — | |||||||||||||||||
| LiveCodeBench | 43% | default | — | |||||||||||||||||
| Long-Context Reasoning | 58% | default | — | |||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 80% | default | — | |||||||||||||||||
| Omniscience | -33.2 | default | — | |||||||||||||||||
| Omniscience Accuracy | 0.3 | default | — | |||||||||||||||||
| Omniscience Non Hallucination | 0.1 | default | — | |||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 37% | — | — | |||||||||||||||||
| TerminalBench Hard | 11% | default | — | |||||||||||||||||
| τ²-bench | 49% | default | — | |||||||||||||||||
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $1.25 to $3.00 per 1M tokens across 4 providers, so the dearest route costs 140% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| xAICheapest | $1.25 | $2.50 | 1 | |||||||||||||
Standardxai/grok-3
| ||||||||||||||||
| Azure | $3.00 | $15.00 | 1 | |||||||||||||
Standardazure_ai/grok-3
| ||||||||||||||||
| OCI | $3.00 | $15.00 | 1 | |||||||||||||
Standardoci/xai.grok-3
| ||||||||||||||||
| VercelVercel reseller quote | $3.00 | $15.00 | 1 | |||||||||||||
Standardvercel_ai_gateway/xai/grok-3
| ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 58% since first tracked
Cost calculator
estimate your monthly spend on this model$450
estimated / month
Model IDs
copy the exact identifier for your platformxai/grok-3azure_ai/grok-3oci/xai.grok-3vercel_ai_gateway/xai/grok-3
Frequently asked questions
Grok 3 pricing, context and availabilityIs Grok 3 still available?
Grok 3 was deprecated on 2026-05-01, but 4 serving providers still list it.
How much does Grok 3 cost?
Grok 3 costs $1.25 per 1M input tokens from xAI, and $2.50 per 1M output tokens from xAI. Across 4 serving providers, input prices range from $1.25 to $3.00 per 1M tokens.
What is the context window of Grok 3?
Grok 3 accepts up to 131K tokens of context and can return up to 131K output tokens.
Which providers serve Grok 3?
Grok 3 is available from 4 serving providers, each with its own pricing and model ID. xAI is currently the cheapest.
What can Grok 3 do?
Grok 3 supports tool use.
Other xAI models
compare pricing across the xAI lineupPopular comparisons
head-to-head pages featuring Grok 3
Grok 3 vs GPT-4o Listed prices from LiteLLM, OpenRouter and Vercel · last checked Sep 22, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI