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
3566 个模型| 模型 | 提供商 | 输入 / 1M | 输出 / 1M | 上下文 | 最大输出 |
|---|---|---|---|---|---|
| gpt-4o-mini-search-previewgpt-4o-mini-search-preview | OpenAI | $0.15 | $0.60 | 128K | 16.4K |
| gpt-4o-mini-search-preview-2025-03-11gpt-4o-mini-search-preview-2025-03-11 | OpenAI | $0.15 | $0.60 | 128K | 16.4K |
| gpt-4o-minigpt-4o-mini | OpenAI | $0.15 | $0.60 | 128K | 16.4K |
| gpt-4o-mini-audio-previewgpt-4o-mini-audio-preview | OpenAI | $0.15 | $0.60 | 128K | 16.4K |
| gpt-4o-mini-audio-preview-2024-12-17gpt-4o-mini-audio-preview-2024-12-17 | OpenAI | $0.15 | $0.60 | 128K | 16.4K |
| openai/gpt-oss-120btogether_ai/openai/gpt-oss-120b | together_ai | $0.15 | $0.60 | 131.1K | 131.1K |
| Qwen/Qwen3-Next-80B-A3B-Thinkingtogether_ai/Qwen/Qwen3-Next-80B-A3B-Thinking | together_ai | $0.15 | $1.50 | 262.1K | — |
| Qwen/Qwen3-Next-80B-A3B-Instructtogether_ai/Qwen/Qwen3-Next-80B-A3B-Instruct | together_ai | $0.15 | $1.50 | 262.1K | — |
| openai/gpt-oss-120bgroq/openai/gpt-oss-120b | Groq | $0.15 | $0.60 | 131.1K | 65.5K |
| gemini-2.0-flashgemini-2.0-flash | $0.15 | $0.60 | 1M | 8.2K | |
| gemini-2.0-flash-001gemini-2.0-flash-001 | $0.15 | $0.60 | 1M | 8.2K | |
| openai.gpt-oss-120bbedrock_mantle/openai.gpt-oss-120b | bedrock_mantle | $0.15 | $0.60 | 131.1K | 16.4K |
| openai.gpt-oss-safeguard-120bbedrock_mantle/openai.gpt-oss-safeguard-120b | bedrock_mantle | $0.15 | $0.60 | 131.1K | 16K |
| gpt-4o-mini-2024-07-18azure/gpt-4o-mini-2024-07-18 | Azure | $0.15 | $0.60 | 128K | 16.4K |
| gpt-4o-mini-audio-preview-2024-12-17azure/gpt-4o-mini-audio-preview-2024-12-17 | Azure | $0.15 | $0.60 | 128K | 16.4K |
| global-standard/gpt-4o-miniazure/global-standard/gpt-4o-mini | Azure | $0.15 | $0.60 | 128K | 16.4K |
| gpt-4o-miniazure/gpt-4o-mini | Azure | $0.15 | $0.60 | 128K | 16.4K |
| mistral-nemo@latestvertex_ai/mistral-nemo@latest | $0.15 | $0.15 | 128K | 128K | |
| mistralai/Mistral-7B-Instruct-v0.1anyscale/mistralai/Mistral-7B-Instruct-v0.1 | anyscale | $0.15 | $0.15 | 16.4K | 16.4K |
| meta-llama/Llama-2-7b-chat-hfanyscale/meta-llama/Llama-2-7b-chat-hf | anyscale | $0.15 | $0.15 | 4.1K | 4.1K |
| HuggingFaceH4/zephyr-7b-betaanyscale/HuggingFaceH4/zephyr-7b-beta | anyscale | $0.15 | $0.15 | 16.4K | 16.4K |
| meta-llama/Meta-Llama-3-8B-Instructanyscale/meta-llama/Meta-Llama-3-8B-Instruct | anyscale | $0.15 | $0.15 | 8.2K | 8.2K |
| google/gemma-7b-itanyscale/google/gemma-7b-it | anyscale | $0.15 | $0.15 | 8.2K | 8.2K |
| mistralai/Mixtral-8x7B-Instruct-v0.1anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1 | anyscale | $0.15 | $0.15 | 16.4K | 16.4K |
| Qwen/QwQ-32Bnebius/Qwen/QwQ-32B | nebius | $0.15 | $0.45 | 32.8K | 32.8K |
| mistral.ministral-3-8b-instructmistral.ministral-3-8b-instruct | bedrock_converse | $0.15 | $0.15 | 128K | 8K |
| openai.gpt-oss-120b-1:0openai.gpt-oss-120b-1:0 | bedrock_converse | $0.15 | $0.60 | 128K | 16.4K |
| openai.gpt-oss-safeguard-120bopenai.gpt-oss-safeguard-120b | bedrock_converse | $0.15 | $0.60 | 128K | 16K |
| qwen.qwen3-32b-v1:0qwen.qwen3-32b-v1:0 | bedrock_converse | $0.15 | $0.60 | 32.8K | 8.2K |
| qwen.qwen3-coder-30b-a3b-v1:0qwen.qwen3-coder-30b-a3b-v1:0 | bedrock_converse | $0.15 | $0.60 | 262.1K | 16.4K |
| qwen.qwen3-next-80b-a3bqwen.qwen3-next-80b-a3b | bedrock_converse | $0.15 | $1.20 | 256K | 8K |
| qwen3-vl-8bllamagate/qwen3-vl-8b | llamagate | $0.15 | $0.55 | 32.8K | 8.2K |
| command-rcommand-r | Cohere | $0.15 | $0.60 | 128K | 4.1K |
| command-r-08-2024command-r-08-2024 | Cohere | $0.15 | $0.60 | 128K | 4.1K |
| openai/gpt-4o-minigmi/openai/gpt-4o-mini | gmi | $0.15 | $0.60 | 131.1K | 16.4K |
| us.meta.llama3-2-3b-instruct-v1:0us.meta.llama3-2-3b-instruct-v1:0 | Amazon | $0.15 | $0.15 | 128K | 4.1K |
| databricks-meta-llama-3-1-8b-instructdatabricks/databricks-meta-llama-3-1-8b-instruct | Databricks | $0.15 | $0.45 | 200K | 128K |
| databricks-gpt-oss-120bdatabricks/databricks-gpt-oss-120b | Databricks | $0.15 | $0.60 | 131.1K | 131.1K |
| databricks-gemma-3-12bdatabricks/databricks-gemma-3-12b | Databricks | $0.15 | $0.50 | 128K | 32K |
| databricks-glm-5-3-flashdatabricks/databricks-glm-5-3-flash | Databricks | $0.15 | $0.50 | 1M | 131.1K |
| databricks-qwen3-next-80b-a3b-instructdatabricks/databricks-qwen3-next-80b-a3b-instruct | Databricks | $0.15 | $1.20 | — | — |
| @cf/meta/llama-3.1-8b-instruct-fp8cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8 | cloudflare | $0.15 | $0.29 | 32K | 32K |
| ap-southeast-2/qwen.qwen3-next-80b-a3bbedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b | Amazon | $0.15 | $1.24 | 262.1K | 8.2K |
| us-gov-west-1/google.gemma-4-26b-a4bbedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b | bedrock_mantle | $0.16 | $0.48 | 256K | 256K |
| hy3aihubmix/hy3 | aihubmix | $0.16 | $0.62 | 256K | 128K |
| qwen3-vl-32b-instructqwen_ai_platform/qwen3-vl-32b-instruct | qwen_ai_platform | $0.16 | $0.64 | 131.1K | 32.8K |
| qwen3-vl-32b-thinkingqwen_ai_platform/qwen3-vl-32b-thinking | qwen_ai_platform | $0.16 | $2.87 | 131.1K | 32.8K |
| qwen3-vl-32b-thinkingqwencloud/qwen3-vl-32b-thinking | qwencloud | $0.16 | $2.87 | 131.1K | 32.8K |
| qwen3-vl-32b-instructqwencloud/qwen3-vl-32b-instruct | qwencloud | $0.16 | $0.64 | 131.1K | 32.8K |
| meta/llama-3.2-11bvercel_ai_gateway/meta/llama-3.2-11b | vercel_ai_gateway | $0.16 | $0.16 | 128K | 8.2K |
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 |
|---|---|---|
| gpt-4o-mini-search-preview | OpenAI | $0.0900 |
| gpt-4o-mini-search-preview-2025-03-11 | OpenAI | $0.0900 |
| gpt-4o-mini | OpenAI | $0.0900 |
| gpt-4o-mini-audio-preview | OpenAI | $0.0900 |
| gpt-4o-mini-audio-preview-2024-12-17 | OpenAI | $0.0900 |
| openai/gpt-oss-120b | together_ai | $0.0900 |
| Qwen/Qwen3-Next-80B-A3B-Thinking | together_ai | $0.1800 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | together_ai | $0.1800 |
| openai/gpt-oss-120b | Groq | $0.0900 |
| gemini-2.0-flash | $0.0900 | |
| gemini-2.0-flash-001 | $0.0900 | |
| openai.gpt-oss-120b | bedrock_mantle | $0.0900 |
| openai.gpt-oss-safeguard-120b | bedrock_mantle | $0.0900 |
| gpt-4o-mini-2024-07-18 | Azure | $0.0900 |
| gpt-4o-mini-audio-preview-2024-12-17 | Azure | $0.0900 |
| global-standard/gpt-4o-mini | Azure | $0.0900 |
| gpt-4o-mini | Azure | $0.0900 |
| mistral-nemo@latest | $0.0450 | |
| mistralai/Mistral-7B-Instruct-v0.1 | anyscale | $0.0450 |
| meta-llama/Llama-2-7b-chat-hf | anyscale | $0.0450 |
| HuggingFaceH4/zephyr-7b-beta | anyscale | $0.0450 |
| meta-llama/Meta-Llama-3-8B-Instruct | anyscale | $0.0450 |
| google/gemma-7b-it | anyscale | $0.0450 |
| mistralai/Mixtral-8x7B-Instruct-v0.1 | anyscale | $0.0450 |
| Qwen/QwQ-32B | nebius | $0.0750 |
| mistral.ministral-3-8b-instruct | bedrock_converse | $0.0450 |
| openai.gpt-oss-120b-1:0 | bedrock_converse | $0.0900 |
| openai.gpt-oss-safeguard-120b | bedrock_converse | $0.0900 |
| qwen.qwen3-32b-v1:0 | bedrock_converse | $0.0900 |
| qwen.qwen3-coder-30b-a3b-v1:0 | bedrock_converse | $0.0900 |