This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
SpaceXAI has launched a newer release, Grok 4. We suggest considering it instead.
Grok 3 Intelligence, Performance & Price Analysis
Model summary
Verbosity
Grok 3 is below average in intelligence and particularly expensive when comparing to other non-reasoning models of similar price. The model supports text input, outputs text and image, and has a 1M tokens context window.
Grok 3 scores 12 on the Artificial Analysis Intelligence Index, placing it below average among comparable models (median: 15).
Pricing for Grok 3 is $3.00 per 1M input tokens (somewhat expensive, median: $2.00) and $15.00 per 1M output tokens (somewhat expensive, median: $10.00).
At 106 tokens per second, Grok 3 is faster than average (83).
| Reasoning | No This page shows the non-reasoning version of this model. A reasoning variant may also exist. |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text and image |
| Context window | 1M ~1500 A4 pages of size 12 Arial font |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Intelligence Index Task
Intelligence Evaluations
Agentic knowledge work, (Elo-500)/2000
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic real-world work tasks, (Elo-500)/2000
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Long context reasoning
Coding
Physics reasoning
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
AA-Omniscience
AA-Omniscience Index
Intelligence Index Comparisons
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Speed
Measured by Output Speed (tokens per second)
Output Speed
Time per Intelligence Index Task
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Frequently Asked Questions
Common questions about Grok 3
Grok 3 was released on February 19, 2025.
Grok 3 was created by SpaceXAI.
Grok 3 scores 12 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other non-reasoning models in a similar price tier (median: 15).
Grok 3 generates output at 106.5 tokens per second (based on SpaceXAI's API), which is above average compared to other non-reasoning models in a similar price tier (median: 83.2 t/s).
Grok 3 has a time to first token (TTFT) of 1.77s (based on SpaceXAI's API), which is somewhat higher than average compared to other non-reasoning models in a similar price tier (median: 1.10s).
Grok 3 costs $3.00 per 1M input tokens (somewhat higher than average, median: $2.00) and $15.00 per 1M output tokens (somewhat higher than average, median: $10.00), based on SpaceXAI's API.
Grok 3 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens (based on SpaceXAI's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $2.63 per 1M tokens. Pricing may vary by provider. Compare provider pricing
No, Grok 3 is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Grok 3 supports text input.
Grok 3 supports text and image output.
No, Grok 3 does not support image input. It can only process text.
No, Grok 3 is not multimodal. It only supports text input.
Grok 3 has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
No, Grok 3 is proprietary. The model weights are not publicly available.
Grok 3 is a proprietary model and SpaceXAI has not disclosed the model size or parameter count.
Grok 3 achieves a score of 12 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Grok 3 is available via API through 3 providers. Compare API providers
Grok 3 is available through 3 API providers. Compare providers