Models, measured side by side
Grok 4.20 vs Grok 4.20 Multi-Agent
Compare Grok 4.20, Grok 4.20 Multi-Agent by token pricing, context length, benchmark results, speed and tool support.
Monthly workload
Monthly cost breakdown
InputOutput
Grok 4.20
$38 / mo
Grok 4.20 Multi-Agent
$38 / mo
Performance comparison
Grok 4.20
25.7
Grok 4.20 Multi-Agent
Not listed
Overview
Pricing & capacity
| Pricing & capacity | Grok 4.20 | Grok 4.20 Multi-Agent |
|---|---|---|
| Input / 1M tokens | $1.25 | $1.25 |
| Output / 1M tokens | $2.50 | $2.50 |
| Cached input / 1M | $0.20 | $0.20 |
| Monthly cost | $38 | $38 |
| Context window | 2M | 2M |
| Maximum output | 1.8M | 1.8M |
Input / 1M tokens
- Grok 4.20
- $1.25
- Grok 4.20 Multi-Agent
- $1.25
Output / 1M tokens
- Grok 4.20
- $2.50
- Grok 4.20 Multi-Agent
- $2.50
Cached input / 1M
- Grok 4.20
- $0.20
- Grok 4.20 Multi-Agent
- $0.20
Monthly cost
- Grok 4.20
- $38
- Grok 4.20 Multi-Agent
- $38
Context window
- Grok 4.20
- 2M
- Grok 4.20 Multi-Agent
- 2M
Maximum output
- Grok 4.20
- 1.8M
- Grok 4.20 Multi-Agent
- 1.8M
Benchmarks & performance
| Benchmarks & performance | Grok 4.20 | Grok 4.20 Multi-Agent |
|---|---|---|
| Arena Elo | Not listed | Not listed |
| MMLU-Pro | Not listed | Not listed |
| Intelligence Index | 25.7 | Not listed |
| GPQA | 91.1% | Not listed |
| Humanity’s Last Exam | 34.5% | Not listed |
| SciCode | Not listed | Not listed |
| Output speed | 120 tokens/s | Not listed |
| Time to first token | 19.5 s | Not listed |
| DesignArena rating | Not listed | Not listed |
| DesignArena win rate | Not listed | Not listed |
Arena Elo
- Grok 4.20
- Not listed
- Grok 4.20 Multi-Agent
- Not listed
MMLU-Pro
- Grok 4.20
- Not listed
- Grok 4.20 Multi-Agent
- Not listed
Intelligence Index
- Grok 4.20
- 25.7
- Grok 4.20 Multi-Agent
- Not listed
GPQA
- Grok 4.20
- 91.1%
- Grok 4.20 Multi-Agent
- Not listed
Humanity’s Last Exam
- Grok 4.20
- 34.5%
- Grok 4.20 Multi-Agent
- Not listed
SciCode
- Grok 4.20
- Not listed
- Grok 4.20 Multi-Agent
- Not listed
Output speed
- Grok 4.20
- 120 tokens/s
- Grok 4.20 Multi-Agent
- Not listed
Time to first token
- Grok 4.20
- 19.5 s
- Grok 4.20 Multi-Agent
- Not listed
DesignArena rating
- Grok 4.20
- Not listed
- Grok 4.20 Multi-Agent
- Not listed
DesignArena win rate
- Grok 4.20
- Not listed
- Grok 4.20 Multi-Agent
- Not listed
Tools & features
| Tools & features | Grok 4.20 | Grok 4.20 Multi-Agent |
|---|---|---|
| Function calling | Supported | Not listed |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Built-in web search | Not listed | Not listed |
| Log probabilities | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Parallel tool calls | Not listed | Not listed |
| Prompt caching | Supported | Supported |
Function calling
- Grok 4.20
- Supported
- Grok 4.20 Multi-Agent
- Not listed
Structured outputs
- Grok 4.20
- Supported
- Grok 4.20 Multi-Agent
- Supported
JSON mode
- Grok 4.20
- Supported
- Grok 4.20 Multi-Agent
- Supported
Reasoning
- Grok 4.20
- Supported
- Grok 4.20 Multi-Agent
- Supported
Built-in web search
- Grok 4.20
- Not listed
- Grok 4.20 Multi-Agent
- Not listed
Log probabilities
- Grok 4.20
- Supported
- Grok 4.20 Multi-Agent
- Supported
Deterministic seed
- Grok 4.20
- Supported
- Grok 4.20 Multi-Agent
- Supported
Parallel tool calls
- Grok 4.20
- Not listed
- Grok 4.20 Multi-Agent
- Not listed
Prompt caching
- Grok 4.20
- Supported
- Grok 4.20 Multi-Agent
- Supported
API & availability
| API & availability | Grok 4.20 | Grok 4.20 Multi-Agent |
|---|---|---|
| API identifier | grok-4.20 | grok-4.20-multi-agent |
| API providers | Not listed | Not listed |
| Knowledge cutoff | 2025-09-01 | 2025-09-01 |
| Prices checked | Oct 8, 2026 | Oct 8, 2026 |
API identifier
- Grok 4.20
grok-4.20- Grok 4.20 Multi-Agent
grok-4.20-multi-agent
API providers
- Grok 4.20
- Not listed
- Grok 4.20 Multi-Agent
- Not listed
Knowledge cutoff
- Grok 4.20
- 2025-09-01
- Grok 4.20 Multi-Agent
- 2025-09-01
Prices checked
- Grok 4.20
- Oct 8, 2026
- Grok 4.20 Multi-Agent
- Oct 8, 2026
About the models
Grok 4.20
Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
Full pricing & detailsGrok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...
Full pricing & detailsComparison FAQ
Grok 4.20: $1.25 input and $2.50 output per million tokens. Grok 4.20 Multi-Agent: $1.25 input and $2.50 output per million tokens. The cheaper choice depends on your input-to-output ratio; a model can have a lower input rate but a higher output rate.