温云

Visit 温云

统一的LLM API网关，通过标准化端点提供多种AI模型的访问，具有有竞争力的价格和稳定性。

健康检查

45%近期可用性

历史记录 (72 条)

过去现在

支持的模型

模型	速度	延迟	测试数
moonshotai/kimi-k2-instruct-0905	66.42 t/s	0.82s	10

可用模型列表

共 187 个可用模型（最后更新：4/13/2026）

01-ai/yi-largecustomabacusai/dracarys-llama-3.1-70b-instructcustomadept/fuyu-8bcustomai21labs/jamba-1.5-large-instructcustomai21labs/jamba-1.5-mini-instructcustomaisingapore/sea-lion-7b-instructcustombaai/bge-m3custombaichuan-inc/baichuan2-13b-chatcustombigcode/starcoder2-15bcustombigcode/starcoder2-7bcustombytedance/seed-oss-36b-instructcustomdatabricks/dbrx-instructcustomdeepseek-ai/deepseek-coder-6.7b-instructcustomdeepseek-ai/deepseek-r1-distill-llama-8bcustomdeepseek-ai/deepseek-r1-distill-qwen-14bcustomdeepseek-ai/deepseek-r1-distill-qwen-32bcustomdeepseek-ai/deepseek-r1-distill-qwen-7bcustomdeepseek-ai/deepseek-v3.1customdeepseek-ai/deepseek-v3.1-terminuscustomdeepseek-ai/deepseek-v3.2customgoogle/codegemma-1.1-7bcustomgoogle/codegemma-7bcustomgoogle/deplotcustomgoogle/gemma-2-27b-itcustomgoogle/gemma-2-2b-itcustomgoogle/gemma-2-9b-itcustomgoogle/gemma-2bcustomgoogle/gemma-3-12b-itcustomgoogle/gemma-3-1b-itcustomgoogle/gemma-3-27b-itcustomgoogle/gemma-3-4b-itcustomgoogle/gemma-3n-e2b-itcustomgoogle/gemma-3n-e4b-itcustomgoogle/gemma-4-31b-itcustomgoogle/gemma-7bcustomgoogle/paligemmacustomgoogle/recurrentgemma-2bcustomgoogle/shieldgemma-9bcustomgotocompany/gemma-2-9b-cpt-sahabatai-instructcustomibm/granite-3.0-3b-a800m-instructcustomibm/granite-3.0-8b-instructcustomibm/granite-3.3-8b-instructcustomibm/granite-34b-code-instructcustomibm/granite-8b-code-instructcustomibm/granite-guardian-3.0-8bcustomigenius/colosseum_355b_instruct_16kcustomigenius/italia_10b_instruct_16kcustominstitute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1custominstitute-of-science-tokyo/llama-3.1-swallow-8b-instruct-v0.1custommarin/marin-8b-instructcustommediatek/breeze-7b-instructcustommeta/codellama-70bcustommeta/llama-3.1-405b-instructcustommeta/llama-3.1-70b-instructcustommeta/llama-3.1-8b-instructcustommeta/llama-3.2-11b-vision-instructcustommeta/llama-3.2-1b-instructcustommeta/llama-3.2-3b-instructcustommeta/llama-3.2-90b-vision-instructcustommeta/llama-3.3-70b-instructcustommeta/llama-4-maverick-17b-128e-instructcustommeta/llama-4-scout-17b-16e-instructcustommeta/llama-guard-4-12bcustommeta/llama2-70bcustommeta/llama3-70b-instructcustommeta/llama3-8b-instructcustommicrosoft/kosmos-2custommicrosoft/phi-3-medium-128k-instructcustommicrosoft/phi-3-medium-4k-instructcustommicrosoft/phi-3-mini-128k-instructcustommicrosoft/phi-3-mini-4k-instructcustommicrosoft/phi-3-small-128k-instructcustommicrosoft/phi-3-small-8k-instructcustommicrosoft/phi-3-vision-128k-instructcustommicrosoft/phi-3.5-mini-instructcustommicrosoft/phi-3.5-moe-instructcustommicrosoft/phi-3.5-vision-instructcustommicrosoft/phi-4-mini-flash-reasoningcustommicrosoft/phi-4-mini-instructcustommicrosoft/phi-4-multimodal-instructcustomminimaxai/minimax-m2.5customminimaxai/minimax-m2.7custommistralai/codestral-22b-instruct-v0.1custommistralai/devstral-2-123b-instruct-2512custommistralai/magistral-small-2506custommistralai/mamba-codestral-7b-v0.1custommistralai/mathstral-7b-v0.1custommistralai/ministral-14b-instruct-2512custommistralai/mistral-7b-instruct-v0.2custommistralai/mistral-7b-instruct-v0.3custommistralai/mistral-largecustommistralai/mistral-large-2-instructcustommistralai/mistral-large-3-675b-instruct-2512custommistralai/mistral-medium-3-instructcustommistralai/mistral-nemotroncustommistralai/mistral-small-24b-instructcustommistralai/mistral-small-3.1-24b-instruct-2503custommistralai/mistral-small-4-119b-2603custommistralai/mixtral-8x22b-instruct-v0.1custommistralai/mixtral-8x22b-v0.1custommistralai/mixtral-8x7b-instruct-v0.1custommoonshotai/kimi-k2-instructcustommoonshotai/kimi-k2-instruct-0905custommoonshotai/kimi-k2-thinkingcustommoonshotai/kimi-k2.5customnv-mistralai/mistral-nemo-12b-instructcustomnvidia/cosmos-reason2-8bcustomnvidia/embed-qa-4customnvidia/gliner-piicustomnvidia/llama-3.1-nemoguard-8b-content-safetycustomnvidia/llama-3.1-nemoguard-8b-topic-controlcustomnvidia/llama-3.1-nemotron-51b-instructcustomnvidia/llama-3.1-nemotron-70b-instructcustomnvidia/llama-3.1-nemotron-70b-rewardcustomnvidia/llama-3.1-nemotron-nano-4b-v1.1customnvidia/llama-3.1-nemotron-nano-8b-v1customnvidia/llama-3.1-nemotron-nano-vl-8b-v1customnvidia/llama-3.1-nemotron-safety-guard-8b-v3customnvidia/llama-3.1-nemotron-ultra-253b-v1customnvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1customnvidia/llama-3.2-nemoretriever-300m-embed-v1customnvidia/llama-3.2-nv-embedqa-1b-v1customnvidia/llama-3.2-nv-embedqa-1b-v2customnvidia/llama-3.3-nemotron-super-49b-v1customnvidia/llama-3.3-nemotron-super-49b-v1.5customnvidia/llama-nemotron-embed-1b-v2customnvidia/llama-nemotron-embed-vl-1b-v2customnvidia/llama3-chatqa-1.5-70bcustomnvidia/llama3-chatqa-1.5-8bcustomnvidia/mistral-nemo-minitron-8b-8k-instructcustomnvidia/mistral-nemo-minitron-8b-basecustomnvidia/nemoretriever-parsecustomnvidia/nemotron-3-nano-30b-a3bcustomnvidia/nemotron-3-super-120b-a12bcustomnvidia/nemotron-4-340b-instructcustomnvidia/nemotron-4-340b-rewardcustomnvidia/nemotron-4-mini-hindi-4b-instructcustomnvidia/nemotron-content-safety-reasoning-4bcustomnvidia/nemotron-mini-4b-instructcustomnvidia/nemotron-nano-12b-v2-vlcustomnvidia/nemotron-nano-3-30b-a3bcustomnvidia/nemotron-parsecustomnvidia/neva-22bcustomnvidia/nv-embed-v1customnvidia/nv-embedcode-7b-v1customnvidia/nv-embedqa-e5-v5customnvidia/nv-embedqa-mistral-7b-v2customnvidia/nvclipcustomnvidia/nvidia-nemotron-nano-9b-v2customnvidia/riva-translate-4b-instructcustomnvidia/riva-translate-4b-instruct-v1.1customnvidia/streampetrcustomnvidia/vilacustomopenai/gpt-oss-120bsubmodelopenai/gpt-oss-20bcustomopengpt-x/teuken-7b-instruct-commercial-v0.4customqwen/qwen2-7b-instructcustomqwen/qwen2.5-7b-instructcustomqwen/qwen2.5-coder-32b-instructcustomqwen/qwen2.5-coder-7b-instructcustomqwen/qwen3-coder-480b-a35b-instructcustomqwen/qwen3-next-80b-a3b-instructcustomqwen/qwen3-next-80b-a3b-thinkingcustomqwen/qwen3.5-122b-a10bcustomqwen/qwen3.5-397b-a17bcustomqwen/qwq-32bcustomrakuten/rakutenai-7b-chatcustomrakuten/rakutenai-7b-instructcustomsarvamai/sarvam-mcustomsnowflake/arctic-embed-lcustomspeakleash/bielik-11b-v2.3-instructcustomspeakleash/bielik-11b-v2.6-instructcustomstepfun-ai/step-3.5-flashcustomstockmark/stockmark-2-100b-instructcustomthudm/chatglm3-6bcustomtiiuae/falcon3-7b-instructcustomtokyotech-llm/llama-3-swallow-70b-instruct-v0.1customupstage/solar-10.7b-instructcustomutter-project/eurollm-9b-instructcustomwriter/palmyra-creative-122bcustomwriter/palmyra-fin-70b-32kcustomwriter/palmyra-med-70bcustomwriter/palmyra-med-70b-32kcustomyentinglin/llama-3-taiwan-70b-instructcustomz-ai/glm4.7customz-ai/glm5customzyphra/zamba2-7b-instructcustom

温云

健康检查

支持的模型

可用模型列表

最近测试记录

温云

健康检查

支持的模型

可用模型列表

最近测试记录

时间	模型	速度	延迟
Apr 12, 09:05 AM	moonshotai/kimi-k2-instruct-0905	70.43 t/s	0.84s
Apr 12, 09:03 AM	moonshotai/kimi-k2-instruct-0905	62.42 t/s	0.80s

温云

关于 温云

健康检查

支持的模型

可用模型列表

最近测试记录

温云

关于 温云

健康检查

支持的模型

可用模型列表

最近测试记录

关于温云

关于温云