Grok 4.7
Intelligence
46.45
#28 of 520 models
Output speed
72.7 tok/s
Measured generation rate
Cost / index task
$3.738
Measured evaluation workload
End-to-end latency
62ms
First answer 55ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
21 distinct evaluations grouped by topic. Explore cross-model charts or switch to the full results list.
Domain capability
03 / Operation
Speed, tokens & price
Prices are per million tokens; latency and task costs describe the captured evaluation rather than a universal provider guarantee.
Token pricing
- Input / 1M
- $2.00
- Output / 1M
- $6.00
- Cache read / 1M
- $0.500
- Cache write / 1M
- —
- Cache-hit discount
- 75%
Response & usage
- Output speed
- 72.7 tok/s
- First chunk
- 55ms
- First answer
- 55ms
- Output / task
- 80.6k
- Reasoning / task
- 58.5k
Evaluation workload
- Canonical input
- 4.19B
- Canonical output
- 240.41M
- Answer / task
- 22k
- Index time / task
- 18.6m
- Run cost
- $4,967.354
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 82.6 tok/s | 20ms | 20ms | 26ms |
| Long | 72.7 tok/s | 55ms | 55ms | 62ms |
| Hundred K | 56.1 tok/s | 6ms | 6ms | 15ms |
| Medium Parallel | 100.6 tok/s | 44ms | 44ms | 49ms |
04 / Access
License & availability
Recorded license
No license recorded
No direct license document is available in the captured record. Weight availability alone does not establish usage rights.
- Weight access
- Closed / unavailable
- Classification
- Proprietary
- Reasoning
- Yes
Routing and providers
- OpenRouter ID
- x-ai/grok-4.7
- Tokenizer
- Grok
- Instruct type
- —
- Captured endpoints
- 5
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| xAI | unknown | 500k | — |
| xAI | unknown | 500k | — |
| xAI | unknown | 500k | — |
| xAI | unknown | 500k | — |
| xAI | unknown | 500k | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.