Choose a Grok identifier by the task, supported inputs and operating conditions. This catalog keeps live model specifications close to the lifecycle and evaluation questions needed for a controlled application change.
Model families at xAI
The model catalog spans Grok language models and Imagine media generation, with Voice documented through its own service surface. Match the requested output to the correct endpoint before comparing models. Official documentation.
Image understanding and image generation are different capabilities. A model that can inspect a supplied image is not automatically the model that produces a new image. Check accepted inputs, response types and billing units for the exact operation you plan to implement.
Server-side tools can add web or X retrieval to supported workflows. Fresh retrieval should be an explicit integration choice with inspected citations, rather than a property inferred from a model’s name. Official documentation.
For a candidate shortlist, start with hard requirements: input modality, output structure, tool interface and context needs. Then evaluate task quality on examples that expose likely failures. Avoid calling the largest catalog entry the strongest without comparable evidence.
All models
| Model | Official identifier | Modalities | Context tokens | Input USD / 1M | Output USD / 1M | Status |
|---|---|---|---|---|---|---|
| grok-4.20-0309-non-reasoning | grok-4.20-0309-non-reasoning | text, image | 1,000,000 | $1.25 | $2.5 | Active |
| grok-4.20-0309-reasoning | grok-4.20-0309-reasoning | text, image | 1,000,000 | $1.25 | $2.5 | Active |
| grok-4.20-multi-agent-0309 | grok-4.20-multi-agent-0309 | text, image | 1,000,000 | $1.25 | $2.5 | Active |
| grok-4.3 | grok-4.3 | text, image | 1,000,000 | $1.25 | $2.5 | Active |
| grok-4.5 | grok-4.5 | text, image | 500,000 | $2 | $6 | Active |
| grok-4.6 | grok-4.6 | text, image | 500,000 | $2 | $6 | Active |
| grok-build-0.1 | grok-build-0.1 | text, image | 256,000 | $1 | $2 | Active |
Last verified · Source ↗
Use the catalog’s exact identifiers and capability notes. The models reference also explains aliases, while dated identifiers can provide a more specific target for reproducible deployment. Official documentation.
Keep the chosen identifier in deployment configuration. Store the evaluation results alongside it so a future operator can see why it was selected. If a field is unverified, check its official source before making it an application requirement.
Cheapest / strongest / longest-context
Only active candidates with documented values for this ranking are included. Prices retain the tier and deployment condition shown below.
| Model | Provider | Input USD / 1M | Output USD / 1M | Context tokens | Price condition | Cost |
|---|---|---|---|---|---|---|
| grok-build-0.1 | xAI | $1 | $2 | 256,000 | short context | Estimate cost |
| grok-4.20-0309-non-reasoning | xAI | $1.25 | $2.5 | 1,000,000 | short context | Estimate cost |
| grok-4.20-0309-reasoning | xAI | $1.25 | $2.5 | 1,000,000 | short context | Estimate cost |
| grok-4.20-multi-agent-0309 | xAI | $1.25 | $2.5 | 1,000,000 | short context | Estimate cost |
| grok-4.3 | xAI | $1.25 | $2.5 | 1,000,000 | short context | Estimate cost |
| grok-4.5 | xAI | $2 | $6 | 500,000 | short context | Estimate cost |
| grok-4.6 | xAI | $2 | $6 | 500,000 | short context | Estimate cost |
Last verified · Source ↗
Only active candidates with documented values for this ranking are included. Prices retain the tier and deployment condition shown below.
| Model | Provider | Input USD / 1M | Output USD / 1M | Cached input USD / 1M | Context tokens | Price condition | Cost |
|---|---|---|---|---|---|---|---|
| grok-4.20-0309-non-reasoning | xAI | $1.25 | $2.5 | $0.2 | 1,000,000 | short context | Estimate cost |
| grok-4.20-0309-reasoning | xAI | $1.25 | $2.5 | $0.2 | 1,000,000 | short context | Estimate cost |
| grok-4.20-multi-agent-0309 | xAI | $1.25 | $2.5 | $0.2 | 1,000,000 | short context | Estimate cost |
| grok-4.3 | xAI | $1.25 | $2.5 | $0.2 | 1,000,000 | short context | Estimate cost |
| grok-4.5 | xAI | $2 | $6 | $0.3 | 500,000 | short context | Estimate cost |
| grok-4.6 | xAI | $2 | $6 | $0.5 | 500,000 | short context | Estimate cost |
| grok-build-0.1 | xAI | $1 | $2 | $0.2 | 256,000 | short context | Estimate cost |
Last verified · Source ↗
These rankings describe numerical properties, not universal quality. Compare a candidate on the complete task: whether it uses evidence correctly, follows required structure and produces an output your application can validate.
For long inputs, test retrieval and prompt assembly separately. A large supported window does not tell you whether the relevant detail will be used reliably in every task. Measure whether a focused source selection improves the answer before making larger prompts the default.
The applicable pricing condition can change with prompt length. Compare the selected candidates under the tier that matches the actual assembled request. Official documentation.
Deprecations and replacements
Review release notes and migration guidance before replacing a deployed model or endpoint. A retirement notice has a timing and scope; a future announced change should not be treated as already effective. Official documentation.
Keep a migration record containing the old and new identifiers, request-shape changes and the saved tasks that were reevaluated. If rollback is still possible, preserve that configuration while the new candidate is observed under real workload variation.
A successful response is only the first migration check. Confirm that structured fields, citations, tool arguments and completion handling still satisfy the application. Changes in timing or token usage also need to be reflected in operational budgets.
Naming and versions
xAI distinguishes family aliases, latest aliases and versioned model identifiers. Choose the naming behavior intentionally: an alias can simplify updates, while a specific version makes the deployed target more explicit. Official documentation.
Do not construct a guessed identifier from a marketing name or copy a retired example without checking it. Keep model and endpoint validation separate; a valid model sent to an incorrect route still fails.
Use xAI key permissions if a listed model is inaccessible, error diagnosis for the actual rejection and the xAI hub for the complete operating reference.
Use the AI API cost calculator to turn the model and workload you are considering into an estimate.
Last verified · Source ↗
Frequently asked questions
Does an image-capable text model generate images?
Does a model automatically retrieve current information?
What does the context ranking prove?
Should I use an alias or a dated identifier?
What should be checked after a model replacement?
Sources
Last verified · Source ↗