Grok 4.7 vs Grok Code Fast 1
Different efforts: low · thinking
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models
Grok 4.739.2
Grok Code Fast 18
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
Grok 4.716.2
Grok Code Fast 1—
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation
Grok 4.756.7
Grok Code Fast 1—
Arena Text · creative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool
Grok 4.7 · xhigh1,424
Grok Code Fast 1—
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos
Grok 4.778.2
Grok Code Fast 1—
| Benchmark | Grok 4.7 | Grok Code Fast 1 |
|---|---|---|
| Humanity's Last Exam | 39.2 | 8 |
| Terminal-Bench 4.0 | 16.2 | — |
| AutomationBench-AA | 56.7 | — |
| Arena Text · creative writing | 1,424 · xhigh | — |
| MMMU-Pro (vision) | 78.2 | — |
Specs
| Spec | Grok 4.7 | Grok Code Fast 1 |
|---|---|---|
| Input, per 1M | $2 | $1 |
| Output, per 1M | $6 | $2 |
| Cost per task? | $1.25 | — |
| Speed, tok/s | 80 | — |
| Context | 500K | 256K |
| Weights | Closed | Closed |
| Released | Sep 2026 | Aug 2025 |
| See images | ✓ | ✓ |
| Read PDFs | Partial | — |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | ? |
| Return strict JSON | ✓ | ✓ |
| Search the web | ✓ | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
Grok 4.7 → Grok Code Fast 1
Context: 500K → 256K
Grok Code Fast 1 → Grok 4.7
Reasoning cannot be disabled›
Reasoning cannot be disabled; choose low, medium, high or xhigh effort.
Penalties and stop return error›
presencePenalty, frequencyPenalty and stop cannot be used with reasoning models; requests containing them return an error.
Set prompt_cache_key›
Set prompt_cache_key or the Chat Completions x-grok-conv-id header to keep a conversation on the same server and improve cache hits.
Pass reasoning items back unchanged · Responses›
Responses always returns encrypted reasoning even without include; pass the reasoning items back unchanged in the next request.
10% premium · US regional endpoint›
The US regional endpoint keeps inference in the United States and adds a 10% token-price premium.