mirror of
https://git.openapi.site/https://github.com/desirecore/config-center.git
synced 2026-06-06 10:50:53 +08:00
4.0 KiB
4.0 KiB
详细字段取值表 - compute/providers/xai.json
- provider:
xai - priceCurrency:
USD - generatedAt:
2026-04-23T15:11:31.654Z
来源
- https://docs.x.ai/docs/models
- https://docs.x.ai/developers/models
- https://docs.x.ai/developers/model-capabilities/text/reasoning
- https://docs.x.ai/developers/provisioned-throughput
- https://zenmux.ai/models
- https://zenmux.ai/api/v1/models
grok-4.20-0309-reasoning
- ZenMux匹配级别:
ambiguous - ZenMux候选:
x-ai/grok-4-fast-non-reasoning、x-ai/grok-4、x-ai/grok-4.2-fast-non-reasoning、x-ai/grok-4.1-fast-non-reasoning、x-ai/grok-4-fast
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|---|---|---|---|---|
modelName |
"grok-4.20-0309-reasoning" |
"grok-4.20-0309-reasoning" |
待确认 | ZenMux无稳定匹配 |
displayName |
"Grok 4.20 Reasoning" |
"Grok 4.20 Reasoning" |
保持 | 展示字段，需按产品命名策略 |
serviceType |
["chat","reasoning"] |
["chat","reasoning"] |
保持 | 服务路由字段，优先本项目约定 |
contextWindow |
2000000 |
2000000 |
保持 | xAI 官方 Models and Pricing 页面 https://docs.x.ai/developers/models 标注 Grok 4.20 的 context window 为 2,000,000 |
maxOutputTokens |
16384 |
16384 |
待确认 | 已查 https://docs.x.ai/developers/models 与 https://docs.x.ai/developers/models/grok-4.20-0309-reasoning ，官方页面公开了 context 与价格，但未见独立 max output tokens 规格 |
inputPrice |
2 |
2 |
待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
outputPrice |
6 |
6 |
待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
capabilities |
["chat","reasoning","code","vision","tool_use"] |
["chat","reasoning","code","vision","tool_use"] |
保持 | ZenMux无明确能力映射差异 |
defaultTemperature |
1 |
1 |
待确认 | 官方通常不提供默认采样参数 |
defaultTopP |
1 |
1 |
待确认 | 官方通常不提供默认采样参数 |
extra |
{} |
{} |
待确认 | 扩展字段为本地schema，需业务侧定义 |
grok-4-1-fast-reasoning
- ZenMux匹配级别:
ambiguous - ZenMux候选:
x-ai/grok-4.1-fast-non-reasoning、x-ai/grok-4.1-fast、x-ai/grok-4-fast-non-reasoning、x-ai/grok-4-fast、x-ai/grok-4.2-fast-non-reasoning
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|---|---|---|---|---|
modelName |
"grok-4-1-fast-reasoning" |
"grok-4-1-fast-reasoning" |
待确认 | ZenMux无稳定匹配 |
displayName |
"Grok 4.1 Fast Reasoning" |
"Grok 4.1 Fast Reasoning" |
保持 | 展示字段，需按产品命名策略 |
serviceType |
["chat","reasoning"] |
["chat","reasoning"] |
保持 | 服务路由字段，优先本项目约定 |
contextWindow |
2000000 |
2000000 |
保持 | xAI 官方旧版 Models and Pricing 页面 https://docs.x.ai/docs/models?cluster=us-east-1%2F 列出 grok-4-fast-reasoning 的 Context 为 2,000,000；官方 reasoning 文档同时表明当前命名使用 grok-4-1-fast |
maxOutputTokens |
16384 |
16384 |
待确认 | 已查 https://docs.x.ai/developers/model-capabilities/text/reasoning 、https://docs.x.ai/developers/provisioned-throughput 与 https://docs.x.ai/docs/models?cluster=us-east-1%2F ，页面能确认模型存在与 context，但未见独立 max output tokens 规格 |
inputPrice |
0.2 |
0.2 |
待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
outputPrice |
0.5 |
0.5 |
待确认 | ZenMux无稳定价格可用，需官方价格页复核 |
capabilities |
["chat","reasoning","code","vision","tool_use","fast","long_context"] |
["chat","reasoning","code","vision","tool_use","fast","long_context"] |
保持 | ZenMux无明确能力映射差异 |
defaultTemperature |
1 |
1 |
待确认 | 官方通常不提供默认采样参数 |
defaultTopP |
1 |
1 |
待确认 | 官方通常不提供默认采样参数 |
extra |
{} |
{} |
待确认 | 扩展字段为本地schema，需业务侧定义 |