What model mix keeps me within budget?
Costs that look tiny per request add up fast at scale, so teams balancing cost and quality need to design a model mix that stays within budget early. This tool extrapolates your current usage to the volume you are planning for, so budget surprises don't happen.
Start here: LLM Model Cost Comparison
Used unless you set active users below.
Results update automatically as you type.
Result
Cheapest: Llama 3.2 1B Instruct at $1.50/month
Workload: 1,000 in / 500 out × 100,000 requests/month
| Llama 3.2 1B Instruct | Meta | $0.0000150 | $1.50 | $18.00 | 16,000 |
| Llama 3.2 3b Instruct | Meta | $0.0000300 | $3.00 | $36.00 | 16,000 |
| Llama 3.1 8b Instruct | Meta | $0.0000400 | $4.00 | $48.00 | 131,072 |
| Ministral 3B | Mistral AI | $0.0000600 | $6.00 | $72.00 | 128,000 |
| GPT OSS 20B | OpenAI | $0.0000700 | $7.00 | $84.00 | 131,072 |
| gemma-3-4b-it | $0.0000800 | $8.00 | $96.00 | 128,000 | |
| Gemma 3 4B IT (Bedrock) | AWS Bedrock | $0.0000800 | $8.00 | $96.00 | 128,000 |
| Gemma 4 E2B IT (Bedrock) | AWS Bedrock | $0.0000800 | $8.00 | $96.00 | 131,072 |
| Llama 3.2 11B Vision Instruct | Meta | $0.0000825 | $8.25 | $99.00 | 16,000 |
| Qwen3.7 Flash | Alibaba | $0.0000846 | $8.46 | $101.52 | 991,000 |
| DeepSeek R1 Distill Llama 70B | DeepSeek | $0.0000950 | $9.50 | $114.00 | 128,000 |
| Gemma 3 12B IT | $0.000100 | $10.00 | $120.00 | 131,072 | |
| GPT OSS 120B | OpenAI | $0.000102 | $10.20 | $122.40 | 131,072 |
| Amazon Nova Micro | AWS Bedrock | $0.000105 | $10.50 | $126.00 | 128,000 |
| nova-micro-v1 (Bedrock) | AWS Bedrock | $0.000105 | $10.50 | $126.00 | 128,000 |
| Command R7B | Cohere | $0.000112 | $11.25 | $135.00 | 128,000 |
| Qwen3.5 9B | Alibaba | $0.000115 | $11.50 | $138.00 | 262,144 |
| Phi 4 | Microsoft | $0.000140 | $14.00 | $168.00 | 16,384 |
| Nemotron 3 Nano 30B A3B | Nvidia | $0.000150 | $15.00 | $180.00 | 262,144 |
| Ministral 3 3B (Bedrock) | AWS Bedrock | $0.000150 | $15.00 | $180.00 | 256,000 |
| Qwen Turbo | Alibaba | $0.000150 | $15.00 | $180.00 | 1,000,000 |
| Nemotron 3.5 Lightning 30B | Nvidia | $0.000150 | $15.00 | $180.00 | 1,000,000 |
| nvidia-nemotron-3-nano-30b-a3b | Nvidia | $0.000150 | $15.00 | $180.00 | 262,144 |
| gemma-4-26b-a4b-it | $0.000152 | $15.20 | $182.40 | 262,144 | |
| Gemma 3 27B IT | $0.000160 | $16.00 | $192.00 | 131,072 | |
| Qwen2.5-Coder 32B Instruct | Alibaba | $0.000160 | $16.00 | $192.00 | 131,072 |
| Mistral 7B Instruct v0.3 | Mistral AI | $0.000165 | $16.50 | $198.00 | 65,536 |
| Qwen3.5 Flash | Alibaba | $0.000172 | $17.25 | $207.00 | 1,000,000 |
| NVIDIA Nemotron Nano 9B v2 (Bedrock) | AWS Bedrock | $0.000175 | $17.50 | $210.00 | 128,000 |
| nova-lite-v1 (Bedrock) | AWS Bedrock | $0.000179 | $17.85 | $214.20 | 300,000 |
| Amazon Nova Lite | AWS Bedrock | $0.000180 | $18.00 | $216.00 | 300,000 |
| NVIDIA Nemotron Nano 3 30B (Bedrock) | AWS Bedrock | $0.000180 | $18.00 | $216.00 | 128,000 |
| GLM-5.3-Flash | Z.ai (Zhipu AI) | $0.000200 | $20.00 | $240.00 | 1,000,000 |
| Muse Spark 1.2 Contributor | Meta | $0.000200 | $20.00 | $240.00 | 1,048,576 |
| Muse Spark 1.3 Contributor | Meta | $0.000200 | $20.00 | $240.00 | 1,048,576 |
| Qwen-Omni Turbo | Alibaba | $0.000205 | $20.50 | $246.00 | 32,768 |
| Qwen3 30B A3b fp8 | Alibaba | $0.000218 | $21.84 | $262.08 | 32,768 |
| Mistral Small 3.2 24B Instruct | Mistral AI | $0.000219 | $21.88 | $262.50 | 256,000 |
| gpt-oss-20b (Bedrock) | AWS Bedrock | $0.000220 | $22.00 | $264.00 | 128,000 |
| Hy-MT2 Plus | Tencent | $0.000222 | $22.15 | $265.80 | 8,192 |
| Gemini 2.0 Flash-Lite | $0.000225 | $22.50 | $270.00 | 1,048,576 | |
| Ministral 3 8B (Bedrock) | AWS Bedrock | $0.000225 | $22.50 | $270.00 | 128,000 |
| Mistral Nemo | Mistral AI | $0.000225 | $22.50 | $270.00 | 128,000 |
| Open Mistral Nemo | Mistral AI | $0.000225 | $22.50 | $270.00 | 128,000 |
| Pixtral 12B | Mistral AI | $0.000225 | $22.50 | $270.00 | 128,000 |
| gemma-4-31b-it | $0.000225 | $22.50 | $270.00 | 262,144 | |
| Qwen3 30B A3B | Alibaba | $0.000225 | $22.50 | $270.00 | 41,000 |
| Google Gemma 3 12B (Bedrock) | AWS Bedrock | $0.000235 | $23.50 | $282.00 | 131,072 |
| GPT-5 Nano | OpenAI | $0.000250 | $25.00 | $300.00 | 400,000 |
| Qwen Flash | Alibaba | $0.000250 | $25.00 | $300.00 | 1,000,000 |
| Step 3.5 Flash | StepFun | $0.000250 | $25.00 | $300.00 | 256,000 |
| Llama 4 Scout 17B 16E Instruct | Meta | $0.000250 | $25.00 | $300.00 | 327,680 |
| Mistral Small 3.1 24B Instruct | Mistral AI | $0.000250 | $25.00 | $300.00 | 128,000 |
| Qwen3.8 27B | Alibaba | $0.000255 | $25.50 | $306.00 | 32,768 |
| GLM-4.7-Flash | Z.ai (Zhipu AI) | $0.000260 | $26.00 | $312.00 | 200,000 |
| Llama-3.3-70B-Instruct | Meta | $0.000260 | $26.00 | $312.00 | 128,000 |
| GLM-4.7-Flash (Bedrock) | AWS Bedrock | $0.000270 | $27.00 | $324.00 | 200,000 |
| GLM-4.7-FlashX | Z.ai (Zhipu AI) | $0.000270 | $27.00 | $324.00 | 200,000 |
| Llama 4 Scout | Meta | $0.000280 | $28.00 | $336.00 | 10,000,000 |
| MiMo-V2.5 | Xiaomi | $0.000280 | $28.00 | $336.00 | 1,048,576 |
| DeepSeek Chat | DeepSeek | $0.000280 | $28.00 | $336.00 | 1,000,000 |
| DeepSeek Reasoner | DeepSeek | $0.000280 | $28.00 | $336.00 | 1,000,000 |
| MiMo-V2-Flash | Xiaomi | $0.000280 | $28.00 | $336.00 | 262,144 |
| MiMo-V2-Omni | Xiaomi | $0.000280 | $28.00 | $336.00 | 262,144 |
| GPT-4.1 Nano | OpenAI | $0.000300 | $30.00 | $360.00 | 1,000,000 |
| Gemini 2.5 Flash-Lite | $0.000300 | $30.00 | $360.00 | 1,000,000 | |
| Gemini 2.0 Flash | $0.000300 | $30.00 | $360.00 | 1,048,576 | |
| Ministral 14B 3.0 (Bedrock) | AWS Bedrock | $0.000300 | $30.00 | $360.00 | 128,000 |
| Qwen2.5-Omni 7B | Alibaba | $0.000300 | $30.00 | $360.00 | 32,768 |
| deepseek-v4-1-flash | DeepSeek | $0.000300 | $30.00 | $360.00 | 1,000,000 |
| Qwen3 VL 32B Instruct | Alibaba | $0.000312 | $31.20 | $374.40 | 131,072 |
| Gemma 4 26B A4B IT (Bedrock) | AWS Bedrock | $0.000330 | $33.00 | $396.00 | 262,144 |
| Qwen3 VL 8B Instruct | Alibaba | $0.000330 | $33.00 | $396.00 | 131,072 |
| Gemma 4 31B IT (Bedrock) | AWS Bedrock | $0.000340 | $34.00 | $408.00 | 262,144 |
| MiniMax M2.1 Lightning | MiniMax | $0.000360 | $36.00 | $432.00 | 196,608 |
| Mistral 7B | Mistral AI | $0.000375 | $37.50 | $450.00 | 8,000 |
| Qwen3 Coder | Alibaba | $0.000380 | $38.00 | $456.00 | 262,000 |
| Qwen3.8 Flash | Alibaba | $0.000385 | $38.50 | $462.00 | 1,000,000 |
| Qwen3.8 Omni Flash | Alibaba | $0.000385 | $38.50 | $462.00 | 991,808 |
| Qwen3 VL 30B A3B Instruct | Alibaba | $0.000390 | $39.00 | $468.00 | 131,072 |
| Qwen-MT Turbo | Alibaba | $0.000405 | $40.50 | $486.00 | 16,384 |
| Google Gemma 3 27B Instruct (Bedrock) | AWS Bedrock | $0.000420 | $42.00 | $504.00 | 202,752 |
| Hunyuan A13B Instruct | Tencent | $0.000425 | $42.50 | $510.00 | 131,072 |
| Nemotron 3 Super 120B A12B | Nvidia | $0.000438 | $43.75 | $525.00 | 262,144 |
| qwen3-coder-next | Alibaba | $0.000446 | $44.55 | $534.60 | 262,144 |
| GPT-4o mini | OpenAI | $0.000450 | $45.00 | $540.00 | 128,000 |
| Mistral Small 4 | Mistral AI | $0.000450 | $45.00 | $540.00 | 131,000 |
| DeepSeek V4 Flash | DeepSeek | $0.000450 | $45.00 | $540.00 | 1,000,000 |
| Command R | Cohere | $0.000450 | $45.00 | $540.00 | 128,000 |
| gpt-oss-120b (Bedrock) | AWS Bedrock | $0.000450 | $45.00 | $540.00 | 128,000 |
| DeepSeek V4.1 Flash | DeepSeek | $0.000450 | $45.00 | $540.00 | 1,000,000 |
| DeepSeek R1 Distill Qwen 32B | DeepSeek | $0.000450 | $45.00 | $540.00 | 64,000 |
| NVIDIA Nemotron 3 Super 120B A12B (Bedrock) | AWS Bedrock | $0.000475 | $47.50 | $570.00 | 262,144 |
| DeepSeek V3.2 | DeepSeek | $0.000490 | $49.00 | $588.00 | 164,000 |
| Mistral Saba | Mistral AI | $0.000496 | $49.64 | $595.68 | 32,768 |
| NVIDIA Nemotron Nano 12B v2 VL BF16 (Bedrock) | AWS Bedrock | $0.000500 | $50.00 | $600.00 | 128,000 |
| Qwen2.5 7B Instruct | Alibaba | $0.000525 | $52.50 | $630.00 | 131,072 |
| Qwen-VL Plus | Alibaba | $0.000525 | $52.50 | $630.00 | 131,072 |
| Qwen3 8B | Alibaba | $0.000530 | $53.00 | $636.00 | 131,072 |
| DeepSeek V3.1 | DeepSeek | $0.000545 | $54.50 | $654.00 | 131,072 |
| Qwen 2.5 72B Instruct | Alibaba | $0.000561 | $56.10 | $673.20 | 131,072 |
| Hunyuan Hy3 | Tencent | $0.000600 | $60.00 | $720.00 | 262,144 |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | Meta | $0.000600 | $60.00 | $720.00 | 128,000 |
| Qwen3-VL 30B-A3B | Alibaba | $0.000600 | $60.00 | $720.00 | 131,072 |
| DeepSeek Chat V3.1 | DeepSeek | $0.000600 | $60.00 | $720.00 | 164,000 |
| DeepSeek V3.1 Terminus | DeepSeek | $0.000600 | $60.00 | $720.00 | 128,000 |
| Llama 3.1 70B Instruct | Meta | $0.000600 | $60.00 | $720.00 | 131,072 |
| Muse Glimmer 30B | Meta | $0.000600 | $60.00 | $720.00 | 131,072 |
| Qwen3 235B A22B FP8 | Alibaba | $0.000600 | $60.00 | $720.00 | 40,960 |
| QwQ 32B | Alibaba | $0.000600 | $60.00 | $720.00 | 32,768 |
| Qwen3 VL 235B A22B Instruct | Alibaba | $0.000640 | $64.00 | $768.00 | 262,144 |
| Llama 4 Maverick | Meta | $0.000645 | $64.50 | $774.00 | 1,000,000 |
| Qwen3 VL 30B A3B Thinking | Alibaba | $0.000700 | $70.00 | $840.00 | 131,072 |
| MiniMax 01 | MiniMax | $0.000700 | $70.04 | $840.48 | 1,000,192 |
| WizardLM-2 8x22B | Microsoft | $0.000740 | $73.95 | $887.40 | 65,536 |
| Step 3.7 Flash | StepFun | $0.000740 | $74.00 | $888.00 | 256,000 |
| Qwen/Qwen3-Next-80B-A3B-Instruct (Bedrock) | AWS Bedrock | $0.000750 | $75.00 | $900.00 | 262,000 |
| Qwen3.6 Flash | Alibaba | $0.000750 | $75.00 | $900.00 | 1,000,000 |
| GLM-4.5-Air | Z.ai (Zhipu AI) | $0.000750 | $75.00 | $900.00 | 131,072 |
| GLM-4.6V | Z.ai (Zhipu AI) | $0.000750 | $75.00 | $900.00 | 128,000 |
| DeepSeek V3 | DeepSeek | $0.000750 | $75.00 | $900.00 | 164,000 |
| MiniMax M1 | MiniMax | $0.000759 | $75.90 | $910.80 | 1,000,000 |
| GPT-5.6 Luna | OpenAI | $0.000800 | $80.00 | $960.00 | 1,050,000 |
| GPT 5.6 Luna Pro | OpenAI | $0.000800 | $80.00 | $960.00 | 1,050,000 |
| GPT-5.4 nano | OpenAI | $0.000825 | $82.50 | $990.00 | 400,000 |
| Devstral 2 | Mistral AI | $0.000850 | $85.00 | $1,020.00 | 262,000 |
| Grok Code Fast 1 | xAI | $0.000855 | $85.50 | $1,026.00 | 256,000 |
| DeepSeek V4 Pro | DeepSeek | $0.000870 | $87.00 | $1,044.00 | 1,000,000 |
| MiMo-V2.5-Pro | Xiaomi | $0.000870 | $87.00 | $1,044.00 | 1,048,576 |
| MiMo-V2-Pro | Xiaomi | $0.000870 | $87.00 | $1,044.00 | 1,048,576 |
| Claude Haiku 3 | Anthropic | $0.000875 | $87.50 | $1,050.00 | 200,000 |
| Qwen2.5-VL 7B Instruct | Alibaba | $0.000875 | $87.50 | $1,050.00 | 131,072 |
| GPT-5.6 Luna (India) (Bedrock) | AWS Bedrock | $0.000880 | $88.00 | $1,056.00 | 1,050,000 |
| Llama 3 70B Instruct | Meta | $0.000880 | $88.00 | $1,056.00 | 8,192 |
| Llama 3.3 70B | Meta | $0.000900 | $90.00 | $1,080.00 | 128,000 |
| MiniMax-M3 | MiniMax | $0.000900 | $90.00 | $1,080.00 | 1,000,000 |
| MiniMax-M2.7 | MiniMax | $0.000900 | $90.00 | $1,080.00 | 204,800 |
| MiniMax-M2 | MiniMax | $0.000900 | $90.00 | $1,080.00 | 196,608 |
| MiniMax M2 (Bedrock) | AWS Bedrock | $0.000900 | $90.00 | $1,080.00 | 204,608 |
| MiniMax-M2.1 | MiniMax | $0.000900 | $90.00 | $1,080.00 | 204,800 |
| MiniMax M2.1 (Bedrock) | AWS Bedrock | $0.000900 | $90.00 | $1,080.00 | 204,800 |
| MiniMax-M2.5 | MiniMax | $0.000900 | $90.00 | $1,080.00 | 204,800 |
| MiniMax M2.5 (Bedrock) | AWS Bedrock | $0.000900 | $90.00 | $1,080.00 | 196,608 |
| MiniMax M2-her | MiniMax | $0.000900 | $90.00 | $1,080.00 | 65,536 |
| meta-llama-3-3-70b-instruct | Meta | $0.000985 | $98.50 | $1,182.00 | 131,072 |
| Qwen3.6 35B-A3B | Alibaba | $0.000991 | $99.05 | $1,188.60 | 262,144 |
| Gemini 3.1 Flash Lite | $0.00100 | $100.00 | $1,200.00 | 1,048,576 | |
| Qwen Plus | Alibaba | $0.00100 | $100.00 | $1,200.00 | 1,000,000 |
| Qwen3-VL Plus | Alibaba | $0.00100 | $100.00 | $1,200.00 | 262,144 |
| Mixtral 8x7B | Mistral AI | $0.00105 | $105.00 | $1,260.00 | 32,000 |
| Qwen2.5 14B Instruct | Alibaba | $0.00105 | $105.00 | $1,260.00 | 131,072 |
| Qwen3 14B | Alibaba | $0.00105 | $105.00 | $1,260.00 | 131,072 |
| Qwen3 Coder Flash | Alibaba | $0.00105 | $105.00 | $1,260.00 | 1,000,000 |
| Qwen3 Coder Next (Bedrock) | AWS Bedrock | $0.00110 | $110.00 | $1,320.00 | 131,072 |
| GPT-4.1 Mini | OpenAI | $0.00120 | $120.00 | $1,440.00 | 1,000,000 |
| Qwen Plus Character (Japanese) | Alibaba | $0.00120 | $120.00 | $1,440.00 | 8,192 |
| GPT-5 Mini | OpenAI | $0.00125 | $125.00 | $1,500.00 | 128,000 |
| Mistral Large 3 | Mistral AI | $0.00125 | $125.00 | $1,500.00 | 262,000 |
| Mistral Large 3 (Bedrock) | AWS Bedrock | $0.00125 | $125.00 | $1,500.00 | 256,000 |
| GPT-3.5-turbo | OpenAI | $0.00125 | $125.00 | $1,500.00 | 16,385 |
| GPT-5.1 Codex mini | OpenAI | $0.00125 | $125.00 | $1,500.00 | 400,000 |
| Magistral Small | Mistral AI | $0.00125 | $125.00 | $1,500.00 | 128,000 |
| Qwen3.5 35B-A3B | Alibaba | $0.00125 | $125.00 | $1,500.00 | 262,144 |
| DeepSeek R1 | DeepSeek | $0.00125 | $125.00 | $1,500.00 | 128,000 |
| Qwen3-Omni Flash | Alibaba | $0.00126 | $126.00 | $1,512.00 | 65,536 |
| Kimi K2 Instruct | Moonshot AI | $0.00130 | $130.00 | $1,560.00 | 256,000 |
| Mistral Medium 3.1 | Mistral AI | $0.00140 | $140.00 | $1,680.00 | 131,000 |
| Devstral 2 123B (Bedrock) | AWS Bedrock | $0.00140 | $140.00 | $1,680.00 | 256,000 |
| Mistral Medium 3 | Mistral AI | $0.00140 | $140.00 | $1,680.00 | 131,072 |
| Qwen3.5 27B | Alibaba | $0.00150 | $150.00 | $1,800.00 | 262,144 |
| Sonar | Perplexity | $0.00150 | $150.00 | $1,800.00 | 128,000 |
| GLM-4.5V | Z.ai (Zhipu AI) | $0.00150 | $150.00 | $1,800.00 | 64,000 |
| Qwen3-Next 80B-A3B Instruct | Alibaba | $0.00150 | $150.00 | $1,800.00 | 131,072 |
| Gemini 2.5 Flash | $0.00155 | $155.00 | $1,860.00 | 1,000,000 | |
| Gemini 3.5 Flash Lite | $0.00155 | $155.00 | $1,860.00 | 1,048,576 | |
| Nova 2 Lite (Bedrock) | AWS Bedrock | $0.00155 | $155.00 | $1,860.00 | 1,000,000 |
| NVIDIA Nemotron 3 Ultra | Nvidia | $0.00158 | $157.50 | $1,890.00 | 262,144 |
| Qwen3-Coder 30B-A3B Instruct | Alibaba | $0.00158 | $157.50 | $1,890.00 | 262,144 |
| Qwen3.5 Plus | Alibaba | $0.00160 | $160.00 | $1,920.00 | 1,000,000 |
| Gemini 3 Flash | $0.00160 | $160.00 | $1,920.00 | 1,048,576 | |
| Kimi K2 | Moonshot AI | $0.00165 | $165.00 | $1,980.00 | 262,144 |
| MiniMax M1 80K | MiniMax | $0.00165 | $165.00 | $1,980.00 | 1,000,000 |
| GLM-4.5 | Z.ai (Zhipu AI) | $0.00170 | $170.00 | $2,040.00 | 131,072 |
| GLM-4.6 | Z.ai (Zhipu AI) | $0.00170 | $170.00 | $2,040.00 | 204,800 |
| GLM-4.7 | Z.ai (Zhipu AI) | $0.00170 | $170.00 | $2,040.00 | 204,800 |
| GLM-4.7 (Bedrock) | AWS Bedrock | $0.00170 | $170.00 | $2,040.00 | 204,800 |
| Qwen3 VL 235B A22B Thinking | Alibaba | $0.00172 | $172.05 | $2,064.60 | 131,072 |
| MiniMax-M2.5-highspeed | MiniMax | $0.00180 | $180.00 | $2,160.00 | 204,800 |
| MiniMax-M2.7-highspeed | MiniMax | $0.00180 | $180.00 | $2,160.00 | 204,800 |
| Kimi K2 Thinking | Moonshot AI | $0.00185 | $185.00 | $2,220.00 | 262,144 |
| Kimi K2 Thinking (Bedrock) | AWS Bedrock | $0.00185 | $185.00 | $2,220.00 | 262,143 |
| Qwen/Qwen3-VL-235B-A22B-Instruct (Bedrock) | AWS Bedrock | $0.00186 | $186.00 | $2,232.00 | 262,000 |
| Qwen3.6 Plus | Alibaba | $0.00200 | $200.00 | $2,400.00 | 1,000,000 |
| Qwen3.5 122B-A10B | Alibaba | $0.00200 | $200.00 | $2,400.00 | 262,144 |
| Qwen3.7 Plus | Alibaba | $0.00200 | $200.00 | $2,400.00 | 1,000,000 |
| QwQ Plus | Alibaba | $0.00200 | $200.00 | $2,400.00 | 131,072 |
| Kimi K2.5 | Moonshot AI | $0.00210 | $210.00 | $2,520.00 | 262,144 |
| Kimi K2.5 (Bedrock) | AWS Bedrock | $0.00210 | $210.00 | $2,520.00 | 262,143 |
| Qwen3-VL 235B-A22B | Alibaba | $0.00210 | $210.00 | $2,520.00 | 131,072 |
| Qwen2.5 32B Instruct | Alibaba | $0.00210 | $210.00 | $2,520.00 | 131,072 |
| Qwen3 235B-A22B | Alibaba | $0.00210 | $210.00 | $2,520.00 | 131,072 |
| Qwen3 32B | Alibaba | $0.00210 | $210.00 | $2,520.00 | 131,072 |
| GPT-3.5 Turbo Instruct | OpenAI | $0.00230 | $230.00 | $2,760.00 | 3,500 |
| Nova Pro 1.0 (Bedrock) | AWS Bedrock | $0.00240 | $239.70 | $2,876.40 | 300,000 |
| Amazon Nova Pro | AWS Bedrock | $0.00240 | $240.00 | $2,880.00 | 300,000 |
| Nemotron 3 Ultra 550B A55B | Nvidia | $0.00240 | $240.00 | $2,880.00 | 1,000,000 |
| Qwen-VL Max | Alibaba | $0.00240 | $240.00 | $2,880.00 | 131,072 |
| Qwen3.5 397B-A17B | Alibaba | $0.00240 | $240.00 | $2,880.00 | 262,144 |
| Qwen3.6 27B | Alibaba | $0.00240 | $240.00 | $2,880.00 | 262,144 |
| glm-5-2-fp8 | Z.ai (Zhipu AI) | $0.00240 | $240.00 | $2,880.00 | 393,216 |
| Grok 4.3 | xAI | $0.00250 | $250.00 | $3,000.00 | 1,000,000 |
| Grok 4.3 (Bedrock) | AWS Bedrock | $0.00250 | $250.00 | $3,000.00 | 1,000,000 |
| Grok 4.20 | xAI | $0.00250 | $250.00 | $3,000.00 | 2,000,000 |
| GLM-5.1 FP8 | Z.ai (Zhipu AI) | $0.00252 | $252.00 | $3,024.00 | 202,752 |
| GLM-5 | Z.ai (Zhipu AI) | $0.00260 | $260.00 | $3,120.00 | 204,800 |
| GLM-5 (Bedrock) | AWS Bedrock | $0.00260 | $260.00 | $3,120.00 | 202,752 |
| MiMo-V2.5-Pro-UltraSpeed | Xiaomi | $0.00261 | $261.00 | $3,132.00 | 1,048,576 |
| Gemini 3.6 Flash | $0.00262 | $262.50 | $3,150.00 | 1,048,576 | |
| Gemini 3.7 Flash | $0.00262 | $262.50 | $3,150.00 | 1,048,576 | |
| Gemini 3.8 Flash | $0.00262 | $262.50 | $3,150.00 | 1,048,576 | |
| Qwen3 Max Thinking | Alibaba | $0.00273 | $273.00 | $3,276.00 | 262,144 |
| Claude 3.5 Haiku | Anthropic | $0.00280 | $280.00 | $3,360.00 | 200,000 |
| Kimi K2.7 Code | Moonshot AI | $0.00295 | $295.00 | $3,540.00 | 262,144 |
| Kimi K2.6 | Moonshot AI | $0.00295 | $295.00 | $3,540.00 | 262,144 |
| o3 Mini High | OpenAI | $0.00299 | $299.00 | $3,588.00 | 200,000 |
| MAI-Code-1-Flash | Microsoft | $0.00300 | $300.00 | $3,600.00 | 256,000 |
| GPT-5.4 mini | OpenAI | $0.00300 | $300.00 | $3,600.00 | 400,000 |
| GLM-5-Turbo | Z.ai (Zhipu AI) | $0.00320 | $320.00 | $3,840.00 | 200,000 |
| GLM-5V-Turbo | Z.ai (Zhipu AI) | $0.00320 | $320.00 | $3,840.00 | 200,000 |
| o4-mini | OpenAI | $0.00330 | $330.00 | $3,960.00 | 200,000 |
| o3-mini | OpenAI | $0.00330 | $330.00 | $3,960.00 | 200,000 |
| o4 Mini High | OpenAI | $0.00330 | $330.00 | $3,960.00 | 200,000 |
| Muse Spark 1.1 | Meta | $0.00338 | $337.50 | $4,050.00 | 1,000,000 |
| Muse Spark 1.2 | Meta | $0.00338 | $337.50 | $4,050.00 | 1,048,576 |
| Muse Spark 1.3 | Meta | $0.00338 | $337.50 | $4,050.00 | 1,048,576 |
| Claude Haiku 4.5 | Anthropic | $0.00350 | $350.00 | $4,200.00 | 200,000 |
| Qwen3 Coder Plus | Alibaba | $0.00350 | $350.00 | $4,200.00 | 1,048,576 |
| Qwen3-Next 80B-A3B (Thinking) | Alibaba | $0.00350 | $350.00 | $4,200.00 | 131,072 |
| GLM-5.2 | Z.ai (Zhipu AI) | $0.00360 | $360.00 | $4,320.00 | 1,000,000 |
| GLM-5.1 | Z.ai (Zhipu AI) | $0.00360 | $360.00 | $4,320.00 | 200,000 |
| QVQ Max | Alibaba | $0.00360 | $360.00 | $4,320.00 | 131,072 |
| GLM-5.3 | Z.ai (Zhipu AI) | $0.00360 | $360.00 | $4,320.00 | 1,000,000 |
| GLM-5.2 | Mistral AI | $0.00360 | $360.00 | $4,320.00 | 1,000,000 |
| GLM-5.3 | Mistral AI | $0.00360 | $360.00 | $4,320.00 | 1,000,000 |
| GLM 5.2 Fast | Z.ai (Zhipu AI) | $0.00370 | $370.00 | $4,440.00 | 1,048,560 |
| GPT-5.6 Luna (Bedrock) | AWS Bedrock | $0.00400 | $400.00 | $4,800.00 | 272,000 |
| Qwen3 Max | Alibaba | $0.00420 | $420.00 | $5,040.00 | 262,144 |
| Qwen2.5 72B Instruct | Alibaba | $0.00420 | $420.00 | $5,040.00 | 131,072 |
| Qwen Max | Alibaba | $0.00480 | $480.00 | $5,760.00 | 32,768 |
| Qwen3.8 2.4T A95B | Alibaba | $0.00493 | $492.50 | $5,910.00 | 970,000 |
| Grok 4.5 | xAI | $0.00500 | $500.00 | $6,000.00 | 500,000 |
| Mixtral 8x22B | Mistral AI | $0.00500 | $500.00 | $6,000.00 | 64,000 |
| Grok 4.6 | xAI | $0.00500 | $500.00 | $6,000.00 | 500,000 |
| Qwen3.8 Max | Alibaba | $0.00500 | $500.00 | $6,000.00 | 1,000,000 |
| Mistral Large | Mistral AI | $0.00500 | $500.00 | $6,000.00 | 128,000 |
| Kimi K2 Thinking Turbo | Moonshot AI | $0.00515 | $515.00 | $6,180.00 | 262,144 |
| Qwen3-Coder 480B-A35B Instruct | Alibaba | $0.00525 | $525.00 | $6,300.00 | 262,144 |
| mistral-medium-3-5 | Mistral AI | $0.00525 | $525.00 | $6,300.00 | 256,000 |
| Mistral Medium 3.5 128B | Mistral AI | $0.00525 | $525.00 | $6,300.00 | 256,000 |
| Grok 4.6 (Bedrock) | AWS Bedrock | $0.00550 | $550.00 | $6,600.00 | 500,000 |
| Kimi K2.7 Code HighSpeed | Moonshot AI | $0.00590 | $590.00 | $7,080.00 | 262,144 |
| GPT-4.1 | OpenAI | $0.00600 | $600.00 | $7,200.00 | 1,000,000 |
| o3 | OpenAI | $0.00600 | $600.00 | $7,200.00 | 200,000 |
| Sonar Reasoning Pro | Perplexity | $0.00600 | $600.00 | $7,200.00 | 128,000 |
| Sonar Deep Research | Perplexity | $0.00600 | $600.00 | $7,200.00 | 128,000 |
| Gemini 3.5 Flash | $0.00600 | $600.00 | $7,200.00 | 1,048,576 | |
| o4-mini-deep-research | OpenAI | $0.00600 | $600.00 | $7,200.00 | 200,000 |
| Qwen-MT Plus | Alibaba | $0.00615 | $614.50 | $7,374.00 | 16,384 |
| GPT-5 | OpenAI | $0.00625 | $625.00 | $7,500.00 | 128,000 |
| Gemini 2.5 Pro | $0.00625 | $625.00 | $7,500.00 | 1,048,576 | |
| GPT-5.1 | OpenAI | $0.00625 | $625.00 | $7,500.00 | 400,000 |
| GPT-5.1 Codex | OpenAI | $0.00625 | $625.00 | $7,500.00 | 400,000 |
| GPT-5.1 Codex Max | OpenAI | $0.00625 | $625.00 | $7,500.00 | 400,000 |
| GPT-5-Codex | OpenAI | $0.00625 | $625.00 | $7,500.00 | 400,000 |
| Qwen3.7 Max | Alibaba | $0.00625 | $625.00 | $7,500.00 | 1,000,000 |
| Step 1 (32K) | StepFun | $0.00684 | $684.50 | $8,214.00 | 32,768 |
| Claude Sonnet 5 | Anthropic | $0.00700 | $700.00 | $8,400.00 | 1,000,000 |
| Claude Sonnet 5 (Bedrock) | AWS Bedrock | $0.00700 | $700.00 | $8,400.00 | 1,000,000 |
| GPT 5.6 Sol Pro | OpenAI | $0.00700 | $700.00 | $8,400.00 | 1,050,000 |
| Qwen2.5-VL 72B Instruct | Alibaba | $0.00700 | $700.00 | $8,400.00 | 131,072 |
| GPT-4o | OpenAI | $0.00750 | $750.00 | $9,000.00 | 128,000 |
| Command A | Cohere | $0.00750 | $750.00 | $9,000.00 | 256,000 |
| Command R+ | Cohere | $0.00750 | $750.00 | $9,000.00 | 128,000 |
| GPT-5.6 Terra | OpenAI | $0.00800 | $800.00 | $9,600.00 | 1,050,000 |
| Gemini 3.1 Pro Preview | $0.00800 | $800.00 | $9,600.00 | 1,048,576 | |
| GPT 5.6 Terra Pro | OpenAI | $0.00800 | $800.00 | $9,600.00 | 1,050,000 |
| Amazon Nova Premier | AWS Bedrock | $0.00875 | $875.00 | $10,500.00 | 1,000,000 |
| GPT-5.2 | OpenAI | $0.00875 | $875.00 | $10,500.00 | 400,000 |
| GPT-5.2 Codex | OpenAI | $0.00875 | $875.00 | $10,500.00 | 400,000 |
| GPT-5.3 Codex | OpenAI | $0.00875 | $875.00 | $10,500.00 | 400,000 |
| GPT-5.3 Codex Spark | OpenAI | $0.00875 | $875.00 | $10,500.00 | 128,000 |
| GPT-5.6 Terra (India) (Bedrock) | AWS Bedrock | $0.00880 | $880.00 | $10,560.00 | 1,050,000 |
| Claude 4 Sonnet | Anthropic | $0.00910 | $910.00 | $10,920.00 | 983,040 |
| GPT-5.4 | OpenAI | $0.0100 | $1,000.00 | $12,000.00 | 1,050,000 |
| GPT-5.6 Terra (Bedrock) | AWS Bedrock | $0.0100 | $1,000.00 | $12,000.00 | 272,000 |
| Claude Sonnet 4.6 | Anthropic | $0.0105 | $1,050.00 | $12,600.00 | 1,000,000 |
| Sonar Pro | Perplexity | $0.0105 | $1,050.00 | $12,600.00 | 200,000 |
| Kimi K3 | Moonshot AI | $0.0105 | $1,050.00 | $12,600.00 | 1,048,576 |
| Claude Sonnet 4.5 (latest) | Anthropic | $0.0105 | $1,050.00 | $12,600.00 | 1,000,000 |
| Grok 4 | xAI | $0.0105 | $1,050.00 | $12,600.00 | 256,000 |
| Kimi K3 Fast | Moonshot AI | $0.0105 | $1,050.00 | $12,600.00 | 1,048,560 |
| GPT-5.4 (Bedrock) | AWS Bedrock | $0.0110 | $1,100.00 | $13,200.00 | 272,000 |
| Anthropic Claude Sonnet 4.6 (Bedrock) | AWS Bedrock | $0.0116 | $1,155.00 | $13,860.00 | 1,000,000 |
| Step 2 (16K) | StepFun | $0.0134 | $1,343.00 | $16,116.00 | 16,384 |
| GPT-5.6 | OpenAI | $0.0140 | $1,400.00 | $16,800.00 | 1,050,000 |
| GPT-5.6 Sol | OpenAI | $0.0140 | $1,400.00 | $16,800.00 | 1,050,000 |
| Claude Opus 4.8 | Anthropic | $0.0175 | $1,750.00 | $21,000.00 | 1,000,000 |
| Claude Opus 4.8 (Bedrock) | AWS Bedrock | $0.0175 | $1,750.00 | $21,000.00 | 1,000,000 |
| Claude Opus 4.6 | Anthropic | $0.0175 | $1,750.00 | $21,000.00 | 1,000,000 |
| Claude Opus 4.6 (Bedrock) | AWS Bedrock | $0.0175 | $1,750.00 | $21,000.00 | 1,000,000 |
| Claude Opus 4.7 | Anthropic | $0.0175 | $1,750.00 | $21,000.00 | 1,000,000 |
| Claude Opus 4.7 (Bedrock) | AWS Bedrock | $0.0175 | $1,750.00 | $21,000.00 | 1,000,000 |
| Claude Opus 4.5 (latest) | Anthropic | $0.0175 | $1,750.00 | $21,000.00 | 200,000 |
| Claude Opus 5 | Anthropic | $0.0175 | $1,750.00 | $21,000.00 | 1,000,000 |
| Claude Opus 5 (Bedrock) | AWS Bedrock | $0.0192 | $1,925.00 | $23,100.00 | 1,000,000 |
| GPT-5.5 | OpenAI | $0.0200 | $2,000.00 | $24,000.00 | 1,050,000 |
| GPT-5.6 Sol (Bedrock) | AWS Bedrock | $0.0200 | $2,000.00 | $24,000.00 | 272,000 |
| GPT-5.5 (Bedrock) | AWS Bedrock | $0.0220 | $2,200.00 | $26,400.00 | 272,000 |
| GPT-4 Turbo | OpenAI | $0.0250 | $2,500.00 | $30,000.00 | 128,000 |
| o3-deep-research | OpenAI | $0.0300 | $3,000.00 | $36,000.00 | 200,000 |
| Claude Fable 5 | Anthropic | $0.0350 | $3,500.00 | $42,000.00 | 1,000,000 |
| Claude Fable 5 (Bedrock) | AWS Bedrock | $0.0350 | $3,500.00 | $42,000.00 | 1,000,000 |
| Claude Fable 5.1 | Anthropic | $0.0350 | $3,500.00 | $42,000.00 | 1,000,000 |
| GPT-6 Astra | OpenAI | $0.0350 | $3,500.00 | $42,000.00 | 1,050,000 |
| Claude Opus 5 Fast | Anthropic | $0.0350 | $3,500.00 | $42,000.00 | 1,000,000 |
| GPT 6 Astra Pro | OpenAI | $0.0350 | $3,500.00 | $42,000.00 | 1,050,000 |
| Claude Fable 5.1 (Bedrock) | AWS Bedrock | $0.0385 | $3,850.00 | $46,200.00 | 1,000,000 |
| GPT-6 Astra (Bedrock) | AWS Bedrock | $0.0385 | $3,850.00 | $46,200.00 | 1,050,000 |
| o1 | OpenAI | $0.0450 | $4,500.00 | $54,000.00 | 200,000 |
| Claude 4 Opus | Anthropic | $0.0450 | $4,500.00 | $54,000.00 | 192,512 |
| Claude Opus 4.1 (latest) | Anthropic | $0.0525 | $5,250.00 | $63,000.00 | 200,000 |
| GPT-4 | OpenAI | $0.0600 | $6,000.00 | $72,000.00 | 8,192 |
| o3-pro | OpenAI | $0.0600 | $6,000.00 | $72,000.00 | 200,000 |
| GPT-5 Pro | OpenAI | $0.0750 | $7,500.00 | $90,000.00 | 400,000 |
| GPT-5.2 Pro | OpenAI | $0.1050 | $10,500.00 | $126,000.00 | 400,000 |
| GPT-5.4 Pro | OpenAI | $0.1200 | $12,000.00 | $144,000.00 | 1,050,000 |
| GPT-5.5 Pro | OpenAI | $0.1200 | $12,000.00 | $144,000.00 | 1,050,000 |
| o1-pro | OpenAI | $0.4500 | $45,000.00 | $540,000.00 | 200,000 |
Then: AI Budget Planner
Results update automatically as you type.
Result
$1,000.00/month budget
Allocation across workloads
- Chat / assistants(50%)
- $500.00
- RAG / search(30%)
- $300.00
- Other (agents, media)(20%)
- $200.00
Why this isn't trivial
The part people underestimate: routing everything to one model over- or under-spends, so a blend of tiers usually hits budget and quality best. In practice the biggest savings come from routing easy requests to cheap models and hard ones to premium, so it is worth modelling before you commit.
How it's calculated
We estimate this by blending per-request costs by the share of traffic sent to each model tier. Every figure uses the current provider prices baked into the site (reviewed daily), and you can override any input to match your own assumptions.
Frequently asked questions
How do I split traffic?+
Route by difficulty or confidence — cheap by default, premium on escalation.
What blend hits my budget?+
The tool lets you tune the split until the blended cost fits your cap.
Are these prices up to date?+
Yes. The model prices behind this calculator are refreshed and reviewed daily, so your estimate reflects current provider rates rather than a stale snapshot.
Related
Premium vs budget model: what's the real cost difference?
Compare a premium and a budget model on real cost for the same workload to see the true gap.
How much would a cheaper model save me per year?
Project the annual savings from switching to a cheaper model at your volume.
What happens to my AI bill if I 10x my users?
Project your AI bill if usage grows 10x, and see which levers keep it under control.
How much will 1 million AI requests cost?
Estimate the cost of 1,000,000 AI requests at your token sizes and model choice.
Calculator
LLM Model Cost Comparison
Calculator
AI Budget Planner
Estimates for planning. Pricing data last reviewed 18 September 2026.