Second-generation multimodal frontier model from xAI; superseded by Grok 4.6 Need a token count first? Use the Grok token counter.
grok-2| Scenario | Input Tokens | Output Tokens | Uncached Cost | With Prompt Caching |
|---|---|---|---|---|
| Short Chat Query | 1,000 | 500 | $0.00700 | N/A |
| Document Summarization | 10,000 | 2,000 | $0.0400 | N/A |
| Codebase & Context Analysis | 100,000 | 20,000 | $0.4000 | N/A |
| Batch Corpus Processing | 1,000,000 | 100,000 | $3.00 | N/A |
Tier 1 (free tier) reference limits — your account's actual quota may be higher.
Ideal for production workloads demanding legacy capabilities, deep context depth (128k tokens), and reliability from xAI. Excellent when predictable tokenomics and prompt caching support are paramount.
If your use-case requires sub-second streaming latency or ultra-high frequency classification at micro-cent pricing, consider lighter budget options such as Gemini Flash-Lite or Claude Haiku. For deep formal logic, consider dedicated reasoning models like o3.
For Grok 2, 1 million input tokens costs $2.00, while 1 million output tokens costs $10.00. If using prompt caching, repetitive input prefixes are discounted to $2.00 per million.
Grok 2 features a maximum context window of 131,072 tokens (~98,304 words), with a maximum output limit of 8,192 tokens per completion.
Grok 2 utilizes the xAI Byte-level BPE (~131k vocabulary). Token counting on TokenMath runs client-side to ensure maximum privacy.
No, Grok 2 does not currently advertise prompt caching discounts on its standard API tier.