大模型价格表
对比 1861 个大模型价格。按成本、Context Window 或供应商排序。
API pricing — pay-per-token rates from each provider's official API. Not subscription plans (ChatGPT Plus, Claude Pro, etc.).
1,861 个模型
快捷：
| 能力 | |||||||
|---|---|---|---|---|---|---|---|
| eu.twelvelabs.pegasus-1-2-v1:0 | AWS Bedrock | Free | $7.50 | — | — | ||
| twelvelabs.pegasus-1-2-v1:0 | AWS Bedrock | Free | $7.50 | — | — | ||
| us.twelvelabs.pegasus-1-2-v1:0 | AWS Bedrock | Free | $7.50 | — | — | ||
| pplx-70b-online | Perplexity | Free | $2.80 | 4.1K | 4.1K | ||
| pplx-7b-online | Perplexity | Free | $0.280 | 4.1K | 4.1K | ||
| sonar-medium-online | Perplexity | Free | $1.80 | 12K | 12K | ||
| sonar-small-online | Perplexity | Free | $0.280 | 12K | 12K | ||
| accounts/fireworks/models/flux-1-dev-controlnet-union | Fireworks AI | $0.0010 | $0.0010 | 4.1K | 4.1K | ||
| gemini-1.5-flash-exp-0827 | $0.0047 | $0.0047 | 1M | 8.2K | |||
| fireworks-ai-embedding-up-to-150m | Fireworks AI | $0.0080 | Free | — | — | ||
| Qwen/Qwen2.5-Coder-7B | Nebius | $0.010 | $0.030 | 32.8K | 32.8K | ||
| Qwen/Qwen2.5-Coder-3B-Instruct | Nscale | $0.010 | $0.030 | — | — | ||
| Qwen/Qwen2.5-Coder-7B-Instruct | Nscale | $0.010 | $0.030 | — | — | ||
| llama3.2-11b-vision-instruct | Lambda | $0.015 | $0.025 | 131.1K | 131.1K | ||
| llama3.2-3b-instruct | Lambda | $0.015 | $0.025 | 131.1K | 131.1K | ||
| fireworks-ai-embedding-150m-to-350m | Fireworks AI | $0.016 | Free | — | — | ||
| meta-llama/Llama-3.2-3B-Instruct | DeepInfra | $0.020 | $0.020 | 131.1K | 131.1K | ||
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | DeepInfra | $0.020 | $0.030 | 131.1K | 131.1K | ||
| mistralai/Mistral-Nemo-Instruct-2407 | DeepInfra | $0.020 | $0.040 | 131.1K | 131.1K | ||
| meta-llama/Llama-Guard-3-8B | Nebius | $0.020 | $0.060 | 128K | 128K | ||
| meta-llama/Meta-Llama-3.1-8B-Instruct | Nebius | $0.020 | $0.060 | 128K | 128K | ||
| Qwen/Qwen2-VL-7B-Instruct | Nebius | $0.020 | $0.060 | 131.1K | 131.1K | ||
| meta-llama/llama-3.1-8b-instruct | Novita AI | $0.020 | $0.050 | 16.4K | 16.4K | ||
| paddlepaddle/paddleocr-vl | Novita AI | $0.020 | $0.020 | 16.4K | 16.4K | ||
| openai/gpt-oss-20b | OpenRouter | $0.020 | $0.100 | 131.1K | 32.8K | ||
| amazon/titan-embed-text-v2 | Vercel AI | $0.020 | Free | — | — | ||
| hermes3-8b | Lambda | $0.025 | $0.040 | 131.1K | 131.1K | ||
| lfm-7b | Lambda | $0.025 | $0.040 | 131.1K | 131.1K | ||
| llama3.1-8b-instruct | Lambda | $0.025 | $0.040 | 131.1K | 131.1K | ||
| deepseek-ai/DeepSeek-R1-Distill-Llama-8B | Nscale | $0.025 | $0.025 | — | — | ||
| meta-llama/Meta-Llama-3-8B-Instruct | DeepInfra | $0.030 | $0.060 | 8.2K | 8.2K | ||
| meta-llama/Meta-Llama-3.1-8B-Instruct | DeepInfra | $0.030 | $0.050 | 131.1K | 131.1K | ||
| gemma3-4b | LlamaGate | $0.030 | $0.080 | 128K | 8.2K | ||
| llama-3.1-8b | LlamaGate | $0.030 | $0.050 | 131.1K | 8.2K | ||
| deepseek/deepseek-ocr | Novita AI | $0.030 | $0.030 | 8.2K | 8.2K | ||
| meta-llama/llama-3.2-3b-instruct | Novita AI | $0.030 | $0.050 | 32.8K | 32K | ||
| qwen/qwen3-4b-fp8 | Novita AI | $0.030 | $0.030 | 128K | 20K | ||
| meta-llama/Llama-3.1-8B-Instruct | Nscale | $0.030 | $0.030 | — | — | ||
| ibm-granite/granite-3.3-8b-instruct | Replicate | $0.030 | $0.250 | — | — | ||
| amazon.nova-micro-v1:0 | AWS Bedrock | $0.035 | $0.140 | 128K | 10K | ||
| nova-micro-v1 | AWS Bedrock | $0.035 | $0.140 | 128K | 10K | ||
| us.amazon.nova-micro-v1:0 | AWS Bedrock | $0.035 | $0.140 | 128K | 10K | ||
| qwen/qwen3-8b-fp8 | Novita AI | $0.035 | $0.138 | 128K | 20K | ||
| zai-org/autoglm-phone-9b-multilingual | Novita AI | $0.035 | $0.138 | 65.5K | 65.5K | ||
| amazon/nova-micro | Vercel AI | $0.035 | $0.140 | 128K | 8.2K | ||
| apac.amazon.nova-micro-v1:0 | AWS Bedrock | $0.037 | $0.148 | 128K | 10K | ||
| google.gemma-3-4b-it | AWS Bedrock | $0.040 | $0.080 | 128K | 8.2K | ||
| mistral.voxtral-mini-3b-2507 | AWS Bedrock | $0.040 | $0.040 | 128K | 8.2K | ||
| ministral-3b | Azure | $0.040 | $0.040 | 128K | 4.1K | ||
| google/gemma-3-4b-it | DeepInfra | $0.040 | $0.080 | 131.1K | 131.1K |
第 1 页 / 共 38 页