grok-4.20-beta-0309-reasoning
xAI 的 grok-4.20-beta-0309-reasoning 模型。支持文本、图像输入和文本输出。
- Starting price
- Input / Output · 1M
- Context
- 1M
- Maximum input window
- Modalities
- →
- Released
- Mar 2026
Pricing by Supplier
Capabilities / Supported modalities
Provider & data privacy
Grok tokenizer (BPE)Performance
About grok-4.20-beta-0309-reasoning
xAI 的 grok-4.20-beta-0309-reasoning 模型。支持文本、图像输入和文本输出。
Use cases and prompting
Starting points for evaluation; supported inputs and options are listed in API access.
Use cases to explore
- Draft and revise text with explicit audience, tone and format requirements.
- Summarize supplied documents and compare answers against the original sources.
Practical tips
Separate instructions from source material, describe the desired output and provide an example. Test tool use or structured output only when listed as supported.
Example prompt
Summarize the following document in five bullet points. Separate confirmed facts from open questions, cite the relevant passages and do not invent missing information. Document: [paste your text]
API access
Code samples
/v1/chat/completions| Parameter | Type | Default / range | Description |
|---|---|---|---|
reasoning_effort | enum | = medium | Controls how much the model thinks before answering |
max_completion_tokens | integer | >= 1 | Maximum tokens including hidden reasoning tokens |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
user | string | — | End-user identifier for abuse monitoring |
Replace <YOUR_API_KEY> with the API key from your token settings.
Authentication
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
Supported parameters
| Parameter | Type | Default / range | Description |
|---|---|---|---|
reasoning_effort | enum | = medium | Controls how much the model thinks before answering |
max_completion_tokens | integer | >= 1 | Maximum tokens including hidden reasoning tokens |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
user | string | — | End-user identifier for abuse monitoring |
Rate limits
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| xAI | 390 | 156K | 7.8K |
RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply per token group.
Frequently asked questions about grok-4.20-beta-0309-reasoning
What is grok-4.20-beta-0309-reasoning?
xAI 的 grok-4.20-beta-0309-reasoning 模型。支持文本、图像输入和文本输出。
How do I call grok-4.20-beta-0309-reasoning?
Create an API key with access to grok-4.20-beta-0309-reasoning, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
How is grok-4.20-beta-0309-reasoning priced?
Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.
What is the context window of grok-4.20-beta-0309-reasoning?
The model catalog lists a context window of 1000000 tokens. Check the selected endpoint for request limits.
How should I evaluate grok-4.20-beta-0309-reasoning for my project?
Separate instructions from source material, describe the desired output and provide an example. Test tool use or structured output only when listed as supported.