Context
1M
Max output
1M
Serving providers
3
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: Artificial AnalysisSpeed & latency
Output speed
100 t/s
tokens / second
Time to first token
21.68s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| CritPt | 7% | default | — | |
| GPQA Diamond | 91% | default | — | |
| Humanity's Last Exam | 35% | default | — | |
| IFBench | 81% | default | — | |
| Long-Context Reasoning | 69% | default | — | |
| MMMU-Pro | 75% | default | — | |
| Omniscience | 14.8 | default | — | |
| Omniscience Accuracy | 0.3 | default | — | |
| Omniscience Non Hallucination | 0.8 | default | — | |
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 46% | — | — | |
| TerminalBench Hard | 38% | default | — | |
| τ²-bench | 93% | default | — |
Pricing detail
cost beyond the standard rate · source: models.devLong context (>200K)
$2.83 / $5.67
input / output · per 1M
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 3 providers, so the dearest route costs 140% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | $1.25 | $2.50 | 1 | |||||||||||||||||
Standardx-ai/grok-4.20
| ||||||||||||||||||||
| xAICheapest | $1.25 | $2.50 | 1 | |||||||||||||||||
Standardxai/grok-4.20
| ||||||||||||||||||||
| OCI | $3.00 | $15.00 | 1 | |||||||||||||||||
Standardoci/xai.grok-4.20
| ||||||||||||||||||||
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 platformx-ai/grok-4.20xai/grok-4.20oci/xai.grok-4.20
Frequently asked questions
Grok 4.20 pricing, context and availabilityHow much does Grok 4.20 cost?
Grok 4.20 costs $1.25 per 1M input tokens from xAI, and $2.50 per 1M output tokens from xAI. Across 3 serving providers, input prices range from $1.25 to $3.00 per 1M tokens.
What is the context window of Grok 4.20?
Grok 4.20 accepts up to 1M tokens of context and can return up to 1M output tokens.
Which providers serve Grok 4.20?
Grok 4.20 is available from 3 serving providers, each with its own pricing and model ID. xAI is currently the cheapest.
What can Grok 4.20 do?
Grok 4.20 supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.
Other xAI models
compare pricing across the xAI lineup Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI