Text model
grok-4.20-multi-agent-experimental-beta-0304 pricing
xAI charges $1.25 per million input tokens and $2.50 per million output tokens for grok-4.20-multi-agent-experimental-beta-0304, and $0.20 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $1.25/ 1M
- Output
- $2.50/ 1M
- Cached input
- $0.20/ 1M
- Context
- 1Mtokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $1.25 | $2.50 | $0.20 | — |
| Standard, prompts over 200K tokens | $2.50 | $5.00 | $0.40 | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.00287 | 100,000 | $287.50 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00455 | 100,000 | $455.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.0086 | 250,000 | $2,150.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with grok-4.20-multi-agent-experimental-beta-0304, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| xai/grok-build-0.1 | $0.0023 | 20% |
| xai/grok-code-fast | $0.0023 | 20% |
| databricks/databricks-gemini-3-flash | $0.00244 | 15% |
| deepinfra/moonshotai/Kimi-K2.7-Code | $0.00238 | 17% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: xAI pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.