数据状态
同步自 OpenRouter Providers · 101 家托管商 · source=openrouter · 2026-08-01T19:40:44.845Z
Cloudflare
总部 美国
15 模型17 端点日可用 99.7%
托管模型15
端点17
日可用率均99.7%
最低输入 $/M$0.017
最大上下文393k
托管端点 · 17
来自 OpenRouter 各模型 Endpoints API：同一模型可能有多量化 / 多区域端点。
| 模型 | Tag | 量化 | 上下文 | 输入 | 输出 | 5m | 30m | 1d | 延迟 | 吞吐 | 缓存 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| granite-4.0-h-micro ibm-granite/granite-4.0-h-micro | cloudflare | — | 131k | $0.017 | $0.112 | 100.00% | 100.00% | 100.00% | — | — | — |
| llama-3.2-1b-instruct meta-llama/llama-3.2-1b-instruct | cloudflare | — | 60k | $0.027 | $0.201 | — | 100.00% | 100.00% | — | — | — |
| mistral-small-3.1-24b-instruct mistralai/mistral-small-3.1-24b-instruct | cloudflare | — | 128k | $0.351 | $0.555 | 100.00% | 100.00% | 100.00% | — | — | — |
| qwen-2.5-coder-32b-instruct qwen/qwen-2.5-coder-32b-instruct | cloudflare | — | 33k | $0.660 | $1.00 | — | — | 100.00% | — | — | — |
| llama-3.2-3b-instruct meta-llama/llama-3.2-3b-instruct | cloudflare | — | 80k | $0.051 | $0.335 | 100.00% | 100.00% | 99.99% | — | — | — |
| deepseek-v4-flash deepseek/deepseek-v4-flash | cloudflare | — | 384k | $0.140 | $0.280 | 100.00% | 100.00% | 99.98% | — | — | — |
| kimi-k2.7-code moonshotai/kimi-k2.7-code | cloudflare | — | 262k | $0.950 | $4.00 | — | — | 99.97% | — | — | — |
| deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 | cloudflare/fp8 | fp8 | 384k | $0.140 | $0.280 | 100.00% | 100.00% | 99.96% | — | — | — |
| llama-3.1-8b-instruct meta-llama/llama-3.1-8b-instruct | cloudflare/fp8 | fp8 | 32k | $0.152 | $0.287 | 100.00% | 100.00% | 99.94% | — | — | — |
| deepseek-v4-pro deepseek/deepseek-v4-pro | cloudflare | — | 393k | $1.74 | $3.48 | 100.00% | 100.00% | 99.9% | — | — | — |
| gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | cloudflare | — | 256k | $0.100 | $0.300 | 99.9% | 99.93% | 99.9% | — | — | — |
| gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | cloudflare | — | 256k | $0.100 | $0.300 | 99.9% | 99.93% | 99.9% | — | — | — |
| kimi-k2.6 moonshotai/kimi-k2.6 | cloudflare | — | 262k | $0.950 | $4.00 | 97.1% | 99.5% | 99.9% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | cloudflare | — | 262k | $1.40 | $4.40 | — | 100.00% | 99.6% | — | — | — |
| glm-4.7-flash z-ai/glm-4.7-flash | cloudflare | — | 131k | $0.061 | $0.400 | 100.00% | 90.2% | 98.9% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | cloudflare/fast | — | 262k | $2.10 | $6.60 | 100.00% | 100.00% | 98.9% | — | — | — |
| llama-3.3-70b-instruct meta-llama/llama-3.3-70b-instruct | cloudflare/fp8 | fp8 | 24k | $0.293 | $2.25 | 96.5% | 97.0% | 97.7% | — | — | — |
覆盖模型 · 15
元数据与端点观测同步自 OpenRouter 公开 API。GrokCode 不做路由转发；自建测速请用 API 实验室。
站内推荐
同系工具：Clavue CLI / imux IDE / clavue-2.1
Clavue · CLI 与 Agent 平台
CLI / GUI Agent 运行时、设备登录、会员额度与 OpenAI 兼容 API（api.clavue.com）。开发脚本、CI 与本地工具一条链路。
打开 Clavue ↗imux · 原生 macOS AI IDE
Clavue 平台的原生 IDE：多 Agent 分屏、Ghostty 级终端、Agent Chat、浏览器自动化与 Supervisor——不是又一个 Electron 壳。
了解 imux ↗Clavue 2.1 · 产品级大模型
旗舰模型 clavue-2.1（及 fast / pro / rev）：适合复杂推理与长程 Agent 循环。Chat、imux、API 共用会员额度。
查看模型 ↗