Cohere (Trial) 免费 API 详情
实测于 2026-08-23 00:30 +08:00(来源:oneapi 生产 DB Channel 表直读)
渠道 slug: | 详情页 URL:
1. 渠道介绍
Cohere 提供企业级语言模型试用层。7 个对话模型(Command-A 推理系列、Command-R 通用任务、Aya-Expanse 多语言)加上 5 个嵌入模型用于 RAG。试用密钥:20 RPM 硬限制,每端点每月 1000 次调用。嵌入模型未在推理端点测试。
2. 实测支持模型列表
口径:models_total = 12(Channel.models 全量直读);chat = 7;audio = 0;embedding = 5;moderation = 0
对话模型(7 个)
- command-a-03-2025
- command-a-plus-05-2026
- command-a-reasoning-08-2025
- command-r7b-12-2024
- command-r-plus-08-2024
- command-r-08-2024
- c4ai-aya-expanse-32b
嵌入模型(5 个)
- embed-v4.0
- embed-english-v3.0
- embed-multilingual-v3.0
- embed-english-light-v3.0
- embed-multilingual-light-v3.0
3. 注册方法
待定
4. 使用方法
Base URL:
待定
5. 实测数据
待 it 基准实测 JSON 到料后填充。每数据点标注「实测于 YYYY-MM-DD HH:MM」。
| 指标 |
值 |
备注 |
| HTTP 状态码 |
待填 |
实测 /models 端点 |
| 首 token 延迟 |
待填 |
ms |
| 完整响应时间 |
待填 |
ms |
| TPS |
待填 |
tokens/sec |
| RPM 限制 |
待填 |
429 实测门槛 |
| TPM 限制 |
待填 |
429 实测门槛 |
| 日调用上限 |
待填 |
429 实测门槛 |
6. 优缺点总结
优点:
- 7 个对话模型包括推理系列
- 5 个嵌入模型用于 RAG
- 企业级质量
缺点:
- 硬限制:20 RPM,每月 1000 次
- 嵌入模型未做推理测试
本页由内容维护员于 2026-08-25 生成,数据以 oneapi 权威 JSON 为准。
Cohere (Trial) Free API Details
Verified on 2026-08-23 00:30 +08:00 (source: OneAPI production DB Channel table direct read)
Channel slug: | Detail URL:
1. Channel Overview
Cohere offers enterprise-grade language models with a trial tier. 7 chat models (Command-A series for reasoning, Command-R for general tasks, Aya-Expanse for multilingual) plus 5 embedding models for RAG. Trial keys: 20 RPM hard limit, 1000 calls/month per endpoint. Embedding models not tested on inference endpoints.
2. Verified Supported Models
Scope: models_total = 12 (full Channel.models direct read); chat = 7; audio = 0; embedding = 5; moderation = 0
Chat Models (7)
- command-a-03-2025
- command-a-plus-05-2026
- command-a-reasoning-08-2025
- command-r7b-12-2024
- command-r-plus-08-2024
- command-r-08-2024
- c4ai-aya-expanse-32b
Embedding Models (5)
- embed-v4.0
- embed-english-v3.0
- embed-multilingual-v3.0
- embed-english-light-v3.0
- embed-multilingual-light-v3.0
3. Registration
TBD
4. Usage
Base URL:
TBD
5. Verified Metrics
待 it 基准实测 JSON 到料后填充。每数据点标注「实测于 YYYY-MM-DD HH:MM」。
| Metric |
Value |
Notes |
| HTTP Status |
TBD |
via /models endpoint |
| Time to First Token |
TBD |
ms |
| Total Response Time |
TBD |
ms |
| TPS |
TBD |
tokens/sec |
| RPM Limit |
TBD |
429 threshold (probed) |
| TPM Limit |
TBD |
429 threshold (probed) |
| Daily Limit |
TBD |
429 threshold (probed) |
6. Pros & Cons
Pros:
- 7 chat models including reasoning series
- 5 embedding models for RAG
- Enterprise-grade quality
Cons:
- Hard limit: 20 RPM, 1000 calls/month
- Embedding models not inference-tested
本页由内容维护员于 2026-08-25 生成,数据以 oneapi 权威 JSON 为准。