数据状态
同步自 OpenRouter Providers · 109 家托管商 · source=openrouter · 2026-09-18T19:57:00.334Z
Venice
总部 美国 · 机房 US
36 模型50 端点日可用 95.7%
托管模型36
端点50
日可用率均95.7%
最低输入 $/M$0.060
最大上下文1.0M
托管端点 · 50
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| dolphin-mistral-24b-venice-edition cognitivecomputations/dolphin-mistral-24b-venice-edition | venice/fp16 | fp16 | 128k | $0.200 | $0.900 | 100.00% | 100.00% | 100.00% | — | — | — |
| qwen3.5-35b-a3b qwen/qwen3.5-35b-a3b | venice | — | 256k | $0.313 | $1.25 | 100.00% | 100.00% | 99.96% | — | — | — |
| qwen3.6-35b-a3b qwen/qwen3.6-35b-a3b | venice/fp8 | fp8 | 256k | $0.100 | $1.00 | 100.00% | 100.00% | 99.91% | — | — | — |
| glm-4.6 z-ai/glm-4.6 | venice/fp4 | fp4 | 198k | $0.430 | $1.75 | 100.00% | 100.00% | 99.8% | — | — | — |
| mistral-small-3.2-24b-instruct mistralai/mistral-small-3.2-24b-instruct | venice/fp8 | fp8 | 256k | $0.094 | $0.250 | 99.5% | 99.9% | 99.8% | — | — | — |
| qwen3.5-9b qwen/qwen3.5-9b | venice/fp8 | fp8 | 256k | $0.100 | $0.150 | 99.93% | 99.92% | 99.8% | — | — | — |
| qwen3.5-9b qwen/qwen3.5-9b | venice/fp8 | fp8 | 256k | $0.100 | $0.150 | 99.93% | 99.92% | 99.8% | — | — | — |
| deepseek-v3.2 deepseek/deepseek-v3.2 | venice | — | 160k | $0.268 | $0.390 | 100.00% | 100.00% | 99.5% | — | — | — |
| kimi-k2.5 moonshotai/kimi-k2.5 | venice | — | 256k | $0.532 | $3.32 | 99.6% | 99.7% | 99.5% | — | — | — |
| deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 | venice | — | 1M | $0.175 | $0.350 | 99.5% | 99.8% | 99.1% | — | — | — |
| deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 | venice | — | 1M | $0.175 | $0.350 | 99.5% | 99.8% | 99.1% | — | — | — |
| deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 | venice | — | 1M | $0.175 | $0.350 | 99.5% | 99.8% | 99.1% | — | — | — |
| qwen3.8-2.4t-a95b qwen/qwen3.8-2.4t-a95b | venice | — | 262k | $2.00 | $6.00 | — | — | 98.9% | — | — | — |
| qwen3.8-2.4t-a95b qwen/qwen3.8-2.4t-a95b | venice | — | 262k | $2.00 | $6.00 | — | — | 98.9% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | venice/fp8 | fp8 | 1M | $1.40 | $4.40 | 99.8% | 99.9% | 98.8% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | venice/fp8 | fp8 | 1M | $1.40 | $4.40 | 99.8% | 99.9% | 98.8% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | venice/fp8 | fp8 | 1M | $1.40 | $4.40 | 99.8% | 99.9% | 98.8% | — | — | — |
| qwen3.6-27b qwen/qwen3.6-27b | venice/fp8 | fp8 | 256k | $0.325 | $3.25 | 100.00% | 98.2% | 98.6% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | venice/fp4 | fp4 | 256k | $0.120 | $0.360 | 98.6% | 98.5% | 98.4% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | venice/fp4 | fp4 | 256k | $0.120 | $0.360 | 98.6% | 98.5% | 98.4% | — | — | — |
| deepseek-v4-pro-0813 deepseek/deepseek-v4-pro-0813 | venice | — | 1M | $1.65 | $4.95 | — | — | 98.3% | — | — | — |
| deepseek-v4-pro-0813 deepseek/deepseek-v4-pro-0813 | venice | — | 1M | $1.65 | $4.95 | — | — | 98.3% | — | — | — |
| glm-5 z-ai/glm-5 | venice/fp8 | fp8 | 198k | $1.00 | $3.20 | — | 100.00% | 98.0% | — | — | — |
| nemotron-3-ultra-550b-a55b nvidia/nemotron-3-ultra-550b-a55b | venice/fp8 | fp8 | 256k | $0.625 | $3.13 | 97.0% | 97.9% | 97.8% | — | — | — |
| nemotron-3-ultra-550b-a55b nvidia/nemotron-3-ultra-550b-a55b | venice/fp8 | fp8 | 256k | $0.625 | $3.13 | 97.0% | 97.9% | 97.8% | — | — | — |
| deepseek-v4.1-flash deepseek/deepseek-v4.1-flash | venice/fp8 | fp8 | 1M | $0.375 | $1.50 | 99.8% | 99.9% | 97.8% | — | — | — |
| qwen3-235b-a22b-2507 qwen/qwen3-235b-a22b-2507 | venice/fp8 | fp8 | 128k | $0.150 | $0.750 | 99.5% | 95.0% | 97.6% | — | — | — |
| deepseek-v4-flash deepseek/deepseek-v4-flash | venice | — | 1M | $0.097 | $0.193 | 98.6% | 97.9% | 97.3% | — | — | — |
| qwen3.8-27b qwen/qwen3.8-27b | venice/fp8 | fp8 | 262k | $0.450 | $3.20 | — | 98.6% | 97.2% | — | — | — |
| qwen3.8-27b qwen/qwen3.8-27b | venice/fp8 | fp8 | 262k | $0.450 | $3.20 | — | 98.6% | 97.2% | — | — | — |
| qwen3.5-397b-a17b qwen/qwen3.5-397b-a17b | venice | — | 128k | $0.750 | $4.50 | 95.9% | 90.1% | 97.1% | — | — | — |
| mimo-v2.5 xiaomi/mimo-v2.5 | venice/fp8 | fp8 | 1M | $0.400 | $2.00 | 100.00% | 100.00% | 97.0% | — | — | — |
| gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | venice/bf16 | bf16 | 256k | $0.130 | $0.400 | 99.9% | 99.6% | 97.0% | — | — | — |
| gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | venice/bf16 | bf16 | 256k | $0.130 | $0.400 | 99.9% | 99.6% | 97.0% | — | — | — |
| glm-5.3-flash z-ai/glm-5.3-flash | venice | — | 1.0M | $0.150 | $0.500 | 70.3% | 91.5% | 96.6% | — | — | — |
| glm-5.3-flash z-ai/glm-5.3-flash | venice | — | 1.0M | $0.150 | $0.500 | 70.3% | 91.5% | 96.6% | — | — | — |
| minimax-m3 minimax/minimax-m3 | venice/fp8 | fp8 | 524k | $0.300 | $1.20 | 100.00% | 99.91% | 95.8% | — | — | — |
| minimax-m3 minimax/minimax-m3 | venice/fp8 | fp8 | 524k | $0.300 | $1.20 | 100.00% | 99.91% | 95.8% | — | — | — |
| qwen3-vl-235b-a22b-instruct qwen/qwen3-vl-235b-a22b-instruct | venice/fp8 | fp8 | 128k | $0.210 | $1.90 | 89.7% | 83.4% | 95.5% | — | — | — |
| glm-5.3 z-ai/glm-5.3 | venice | — | 1M | $1.40 | $4.40 | — | 99.1% | 95.3% | — | — | — |
| glm-5.3 z-ai/glm-5.3 | venice | — | 1M | $1.40 | $4.40 | — | 99.1% | 95.3% | — | — | — |
| glm-4.7-flash z-ai/glm-4.7-flash | venice/fp8 | fp8 | 128k | $0.060 | $0.400 | — | 89.3% | 95.0% | — | — | — |
| deepseek-v4-pro deepseek/deepseek-v4-pro | venice | — | 1M | $1.65 | $3.30 | 99.8% | 97.4% | 94.6% | — | — | — |
| qwen3-coder qwen/qwen3-coder | venice/fp8 | fp8 | 256k | $0.350 | $1.50 | — | — | 92.3% | — | — | — |
| glm-5.1 z-ai/glm-5.1 | venice/fp8 | fp8 | 200k | $1.40 | $4.40 | 97.7% | 99.8% | 92.2% | — | — | — |
| glm-4.7 z-ai/glm-4.7 | venice/fp4 | fp4 | 198k | $0.400 | $1.93 | 98.8% | 96.3% | 92.0% | — | — | — |
| qwen3-235b-a22b-thinking-2507 qwen/qwen3-235b-a22b-thinking-2507 | venice/fp8 | fp8 | 128k | $0.450 | $3.50 | — | — | 82.3% | — | — | — |
| kimi-k2.6 moonshotai/kimi-k2.6 | venice/int4 | int4 | 256k | $0.750 | $3.50 | — | 51.7% | 74.4% | — | — | — |
| kimi-k2.7-code moonshotai/kimi-k2.7-code | venice/int4 | int4 | 256k | $0.750 | $3.50 | — | — | 74.3% | — | — | — |
| minimax-m2.5 minimax/minimax-m2.5 | venice | — | 198k | $0.270 | $0.950 | — | — | 64.9% | — | — | — |
覆盖模型 · 36
dolphin-mistral-24b-venice-editionqwen3.5-35b-a3bqwen3.6-35b-a3bglm-4.6mistral-small-3.2-24b-instructqwen3.5-9bdeepseek-v3.2kimi-k2.5deepseek-v4-flash-0731qwen3.8-2.4t-a95bglm-5.2qwen3.6-27bgemma-4-31b-itdeepseek-v4-pro-0813glm-5nemotron-3-ultra-550b-a55bdeepseek-v4.1-flashqwen3-235b-a22b-2507deepseek-v4-flashqwen3.8-27bqwen3.5-397b-a17bmimo-v2.5gemma-4-26b-a4b-itglm-5.3-flashminimax-m3qwen3-vl-235b-a22b-instructglm-5.3glm-4.7-flashdeepseek-v4-proqwen3-coderglm-5.1glm-4.7qwen3-235b-a22b-thinking-2507kimi-k2.6kimi-k2.7-codeminimax-m2.5
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。
関連ツール
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 ↗