全球 AI 模型价格与规格对比
比较模型公开价格、上下文窗口与能力，按任务和提供商筛选。
模型列表
3564 个模型| 模型 | 提供商 | 输入 / 1M | 输出 / 1M | 上下文 | 最大输出 |
|---|---|---|---|---|---|
| nvidia.nemotron-nano-3-30bnvidia.nemotron-nano-3-30b | bedrock_converse | $0.06 | $0.24 | 256K | 8K |
| amazon.nova-lite-v1:0amazon.nova-lite-v1:0 | bedrock_converse | $0.06 | $0.24 | 300K | 10K |
| us.amazon.nova-lite-v1:0us.amazon.nova-lite-v1:0 | bedrock_converse | $0.06 | $0.24 | 300K | 10K |
| Qwen/Qwen2.5-32B-Instructnebius/Qwen/Qwen2.5-32B-Instruct | nebius | $0.06 | $0.20 | 128K | 128K |
| nvidia/Nemotron-3-Nano-Omninebius/nvidia/Nemotron-3-Nano-Omni | nebius | $0.06 | $0.24 | 262.1K | 262.1K |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3Bnebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | nebius | $0.06 | $0.24 | 262.1K | 262.1K |
| poolside/laguna-xs-2.1openrouter/poolside/laguna-xs-2.1 | openrouter | $0.06 | $0.12 | 262.1K | 32.8K |
| nvidia/Nemotron-3_5-Lightningnebius/nvidia/Nemotron-3_5-Lightning | nebius | $0.06 | $0.24 | 1M | 1M |
| FW-Nemotron-Lightning-3.5-30B-A3Bazure_ai/FW-Nemotron-Lightning-3.5-30B-A3B | Azure | $0.06 | $0.22 | 262.1K | — |
| inclusionAI/Ling-3.0-flashdeepinfra/inclusionAI/Ling-3.0-flash | DeepInfra | $0.06 | $0.18 | 131.1K | — |
| zai-org/GLM-4.7-Flashdeepinfra/zai-org/GLM-4.7-Flash | DeepInfra | $0.06 | $0.40 | 202.8K | — |
| z-ai/glm-5.3-flash:batchopenrouter/z-ai/glm-5.3-flash:batch | openrouter | $0.06 | $0.20 | 1M | 131.1K |
| inclusionai/ling-3.0-flashnovita/inclusionai/ling-3.0-flash | novita | $0.06 | $0.18 | 262.1K | 32.8K |
| nvidia/NVIDIA-Nemotron-Nano-9B-v2together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2 | together_ai | $0.06 | $0.25 | 131.1K | — |
| nvidia/nemotron-3-nano-30b-a3bopenrouter/nvidia/nemotron-3-nano-30b-a3b | openrouter | $0.06 | $0.24 | 262.1K | 235.9K |
| inclusionai/ling-3.0-flash-fastnovita/inclusionai/ling-3.0-flash-fast | novita | $0.06 | $0.18 | 262.1K | 32.8K |
| meta-llama/Llama-3.2-3B-Instructtogether_ai/meta-llama/Llama-3.2-3B-Instruct | together_ai | $0.06 | $0.06 | 131.1K | — |
| meta-llama/Llama-3.2-1B-Instructtogether_ai/meta-llama/Llama-3.2-1B-Instruct | together_ai | $0.06 | $0.06 | 131.1K | — |
| coding-glm-5.3aihubmix/coding-glm-5.3 | aihubmix | $0.06 | $0.22 | 1M | 131.1K |
| cc-glm-5.1aihubmix/cc-glm-5.1 | aihubmix | $0.06 | $0.22 | 200K | 131.1K |
| amazon/nova-lite-v1openrouter/amazon/nova-lite-v1 | openrouter | $0.06 | $0.24 | 300K | 5.1K |
| ibm-granite/granite-4.2-8bopenrouter/ibm-granite/granite-4.2-8b | openrouter | $0.06 | $0.25 | 131.1K | 118K |
| google/gemma-3n-E4B-ittogether_ai/google/gemma-3n-E4B-it | together_ai | $0.06 | $0.12 | 32.8K | 32.8K |
| Qwen/Qwen2.5-Coder-32B-Instructnscale/Qwen/Qwen2.5-Coder-32B-Instruct | nscale | $0.06 | $0.20 | — | — |
| mistral-small-3-2-2506mistral/mistral-small-3-2-2506 | Mistral | $0.06 | $0.18 | 131.1K | 131.1K |
| deepseek/deepseek-r1-0528-qwen3-8bnovita/deepseek/deepseek-r1-0528-qwen3-8b | novita | $0.06 | $0.09 | 128K | 32K |
| nova-lite-v1amazon-nova/nova-lite-v1 | amazon_nova | $0.06 | $0.24 | 300K | 10K |
| openai/gpt-oss-120bsail/openai/gpt-oss-120b | sail | $0.06 | $0.40 | 131.1K | 131.1K |
| z-ai/glm-4.7-flashopenrouter/z-ai/glm-4.7-flash | openrouter | $0.06 | $0.40 | 200K | 118K |
| @cf/zai-org/glm-4.7-flashcloudflare/@cf/zai-org/glm-4.7-flash | cloudflare | $0.06 | $0.40 | 131.1K | 131.1K |
| apac.amazon.nova-lite-v1:0apac.amazon.nova-lite-v1:0 | bedrock_converse | $0.06 | $0.25 | 300K | 10K |
| qwen/qwen3.5-flash-02-23openrouter/qwen/qwen3.5-flash-02-23 | openrouter | $0.07 | $0.26 | 1M | 65.5K |
| z-ai/glm-5.2openrouter/z-ai/glm-5.2 | openrouter | $0.07 | $4.30 | 1M | 943.7K |
| google/gemma-4-26B-A4B-itdeepinfra/google/gemma-4-26B-A4B-it | DeepInfra | $0.07 | $0.34 | 262.1K | — |
| zai-org/glm-4.7-flashnovita/zai-org/glm-4.7-flash | novita | $0.07 | $0.40 | 200K | 128K |
| qwen/qwen3-coder-30b-a3b-instructopenrouter/qwen/qwen3-coder-30b-a3b-instruct | openrouter | $0.07 | $0.28 | 262.1K | 235.9K |
| microsoft/phi-4openrouter/microsoft/phi-4 | openrouter | $0.07 | $0.14 | 16.4K | 14.7K |
| mistral-7b-instructperplexity/mistral-7b-instruct | Perplexity | $0.07 | $0.28 | 4.1K | 4.1K |
| mixtral-8x7b-instructperplexity/mixtral-8x7b-instruct | Perplexity | $0.07 | $0.28 | 4.1K | 4.1K |
| sonar-small-chatperplexity/sonar-small-chat | Perplexity | $0.07 | $0.28 | 16.4K | 16.4K |
| pplx-7b-chatperplexity/pplx-7b-chat | Perplexity | $0.07 | $0.28 | 8.2K | 8.2K |
| openai/gpt-oss-20b-maasvertex_ai/openai/gpt-oss-20b-maas | $0.07 | $0.25 | 131.1K | 32.8K | |
| mistral/devstral-smallvercel_ai_gateway/mistral/devstral-small | vercel_ai_gateway | $0.07 | $0.28 | 128K | 128K |
| openai.gpt-oss-20b-1:0openai.gpt-oss-20b-1:0 | bedrock_converse | $0.07 | $0.30 | 128K | 16.4K |
| openai.gpt-oss-safeguard-20bopenai.gpt-oss-safeguard-20b | bedrock_converse | $0.07 | $0.20 | 128K | 16K |
| zai.glm-4.7-flashzai.glm-4.7-flash | bedrock_converse | $0.07 | $0.40 | 203K | 128K |
| microsoft/phi-4deepinfra/microsoft/phi-4 | DeepInfra | $0.07 | $0.14 | 16.4K | 16.4K |
| databricks-gpt-oss-20bdatabricks/databricks-gpt-oss-20b | Databricks | $0.07 | $0.30 | 131.1K | 131.1K |
| openai.gpt-oss-20bbedrock_mantle/openai.gpt-oss-20b | bedrock_mantle | $0.07 | $0.30 | 131.1K | 16.4K |
| openai.gpt-oss-safeguard-20bbedrock_mantle/openai.gpt-oss-safeguard-20b | bedrock_mantle | $0.07 | $0.20 | 131.1K | 16K |
估算调用费用
按公开单价估算。阶梯价、缓存、批量折扣和税费可能改变实际账单。
| 模型 | 提供商 | 预计费用 |
|---|---|---|
| nvidia.nemotron-nano-3-30b | bedrock_converse | $0.0360 |
| amazon.nova-lite-v1:0 | bedrock_converse | $0.0360 |
| us.amazon.nova-lite-v1:0 | bedrock_converse | $0.0360 |
| Qwen/Qwen2.5-32B-Instruct | nebius | $0.0320 |
| nvidia/Nemotron-3-Nano-Omni | nebius | $0.0360 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | nebius | $0.0360 |
| poolside/laguna-xs-2.1 | openrouter | $0.0240 |
| nvidia/Nemotron-3_5-Lightning | nebius | $0.0360 |
| FW-Nemotron-Lightning-3.5-30B-A3B | Azure | $0.0340 |
| inclusionAI/Ling-3.0-flash | DeepInfra | $0.0300 |
| zai-org/GLM-4.7-Flash | DeepInfra | $0.0520 |
| z-ai/glm-5.3-flash:batch | openrouter | $0.0320 |
| inclusionai/ling-3.0-flash | novita | $0.0300 |
| nvidia/NVIDIA-Nemotron-Nano-9B-v2 | together_ai | $0.0370 |
| nvidia/nemotron-3-nano-30b-a3b | openrouter | $0.0360 |
| inclusionai/ling-3.0-flash-fast | novita | $0.0300 |
| meta-llama/Llama-3.2-3B-Instruct | together_ai | $0.0180 |
| meta-llama/Llama-3.2-1B-Instruct | together_ai | $0.0180 |
| coding-glm-5.3 | aihubmix | $0.0340 |
| cc-glm-5.1 | aihubmix | $0.0340 |
| amazon/nova-lite-v1 | openrouter | $0.0360 |
| ibm-granite/granite-4.2-8b | openrouter | $0.0370 |
| google/gemma-3n-E4B-it | together_ai | $0.0240 |
| Qwen/Qwen2.5-Coder-32B-Instruct | nscale | $0.0320 |
| mistral-small-3-2-2506 | Mistral | $0.0300 |
| deepseek/deepseek-r1-0528-qwen3-8b | novita | $0.0210 |
| nova-lite-v1 | amazon_nova | $0.0360 |
| openai/gpt-oss-120b | sail | $0.0520 |
| z-ai/glm-4.7-flash | openrouter | $0.0521 |
| @cf/zai-org/glm-4.7-flash | cloudflare | $0.0521 |