xAI
Best for Coding
Coding-focused model with 256K context, image input, function calling, and structured outputs.
At a glance
API model ID: grok-build-0.1
Capabilities & boundaries
Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.
The model card confirms reasoning, but the reviewed documentation does not specify a supported effort list or default for Grok Build 0.1. Do not assume none, high or xhigh works like the settings on other Grok models; verify the exact API behavior before sending those parameters.
Put it to work
Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.
Workflow 01
Keep an improvement small enough to inspect and test.
Refactor only the function below to improve readability while preserving its public behavior and signature. First describe its observable behavior and edge cases. Then provide a minimal patch and focused equivalence tests. Do not change callers, add dependencies or rewrite unrelated code. Flag any behavior you cannot infer from the supplied context.
Workflow 02
Expose missing cases before broad implementation work.
Create a test matrix for this parser using the specification and current implementation below. Cover valid input, empty input, malformed values, boundary lengths and error handling. Include concrete inputs and expected outcomes justified by the specification. Separate confirmed requirements from assumptions and identify which assumptions need clarification.
Workflow 03
Draft an adapter without hiding data loss or unsafe assumptions.
Compare these two TypeScript interfaces and the example payloads. Propose a small adapter between them, documenting field mappings, defaults and validation failures. Do not silently discard required information or use any to bypass a mismatch. Include tests for successful conversion and incompatible inputs, and state which checks you have not executed.
Developer reference
These are global xAI API reference prices, not EZ Ai Assist subscription prices.
View EZ Ai Assist plans| Token type | < 200,000prompt tokens | ≥ 200,000prompt tokens |
|---|---|---|
| Input | $1.00 | $2.00 |
| Cached input | $0.20 | $0.40 |
| Output | $2.00 | $4.00 |
| Usage | Rate and unit |
|---|---|
| Web Search | $5.00per 1,000 calls |
| X Search: posts | $5.00per 1,000 posts fetched |
| X Search: profiles | $10.00per 1,000 profiles fetched |
| Code execution | $5.00per 1,000 calls |
Common questions
No. This page documents the grok-build-0.1 API model. A coding application or CLI provides its own environment, tools and permissions and may use a different model. Selecting the model alone does not connect a repository or grant shell access.
Start with bounded tasks such as a function refactor, parser test plan or typed adapter. Supply the relevant code, requirements and error messages. Validate the patch with actual tests before expanding to a larger workflow.
The card lists a 256,000-token context and text/image input with text output. A separate maximum output and training cutoff are not verified. The app can impose different limits from the provider's reference API.
The card confirms reasoning support but does not list configurable effort values or a default. This guide does not borrow settings from Grok 4.5, 4.6 or 4.7. Check current endpoint documentation before supplying an effort parameter.
The public card associates grok-code-fast-1 and related IDs with grok-build-0.1. An alias can continue resolving after the underlying model changes. Use explicit IDs and rerun evaluations when reproducibility matters.
Below 200,000 prompt tokens, rates are $1 input, $0.20 cached input and $2 output per million tokens. At or above the threshold, those rates double for the full request. Tool usage and reasoning can add to the total.
The model card says Batch API is unsupported. Tool calling still requires an appropriate integration, and provider capability is not a guarantee of EZ Ai Assist feature availability. Check the app for supported tools and subscription terms.
Check the source
Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.
Same provider
xAI
Coding and knowledge-work model with 500K context, image input, and configurable reasoning effort.
xAI
Coding and agentic model with 500K context, structured outputs, and four reasoning effort levels.
xAI
Coding and engineering model with 500K context, image input, tool calling, and configurable reasoning.
xAI
1M-context model for instruction-driven work and tool calling, with configurable reasoning that can be disabled.