Cheapest LLM API
Models ranked by input rate per 1M tokens, then by an example request of 1000 input tokens and 500 output tokens. The 10k requests column is that example times 10,000 calls. Open a row to price your own prompt.
All pricing ranks · Cheapest LLM API · Cheapest frontier · Cheapest long replies · Long context · Price one prompt · Cost calculator
Ranked by published rates
| # | Model | Provider | Context | Input / 1M | Output / 1M | Example | 10k requests | |
|---|---|---|---|---|---|---|---|---|
| 1 | Gemini 1.5 Flash-8B | 1M | $0.037/1M | $0.150/1M | $0.000112 | $1.12 | Cost | |
| 2 | Command R7B | Cohere | 128K | $0.037/1M | $0.150/1M | $0.000112 | $1.12 | Cost |
| 3 | Llama 3.2 1B (Groq) | Groq | 128K | $0.040/1M | $0.040/1M | $0.00006 | $0.6 | Cost |
| 4 | Llama 3.1 8B Instant (Groq) | Groq | 128K | $0.050/1M | $0.080/1M | $0.00009 | $0.9 | Cost |
| 5 | GPT-5 Nano | OpenAI | 128K | $0.050/1M | $0.400/1M | $0.00025 | $2.5 | Cost |
| 6 | Llama 3.2 3B (Groq) | Groq | 128K | $0.060/1M | $0.060/1M | $0.00009 | $0.9 | Cost |
| 7 | Llama 3.2 3B (Together) | Together AI | 128K | $0.060/1M | $0.060/1M | $0.00009 | $0.9 | Cost |
| 8 | Mistral Small | Mistral | 128K | $0.060/1M | $0.180/1M | $0.00015 | $1.5 | Cost |
| 9 | Gemma 7B (Groq) | Groq | 8K | $0.070/1M | $0.070/1M | $0.000105 | $1.05 | Cost |
| 10 | Gemini 1.5 Flash | 1M | $0.075/1M | $0.300/1M | $0.000225 | $2.25 | Cost | |
| 11 | Gemini 2.0 Flash-Lite | 1M | $0.075/1M | $0.300/1M | $0.000225 | $2.25 | Cost | |
| 12 | Llama 3.2 3B (Fireworks) | Fireworks | 128K | $0.100/1M | $0.100/1M | $0.00015 | $1.5 | Cost |
| 13 | GPT-4.1 Nano | OpenAI | 1M | $0.100/1M | $0.400/1M | $0.0003 | $3.00 | Cost |
| 14 | Gemini 2.0 Flash | 1M | $0.100/1M | $0.400/1M | $0.0003 | $3.00 | Cost | |
| 15 | Gemini 2.5 Flash-Lite | 1M | $0.100/1M | $0.400/1M | $0.0003 | $3.00 | Cost | |
| 16 | Llama 4 Scout (Groq) | Groq | 128K | $0.110/1M | $0.340/1M | $0.00028 | $2.8 | Cost |
| 17 | DeepSeek Coder | DeepSeek | 128K | $0.140/1M | $0.280/1M | $0.00028 | $2.8 | Cost |
| 18 | DeepSeek V4 Flash | DeepSeek | 1M | $0.140/1M | $0.280/1M | $0.00028 | $2.8 | Cost |
| 19 | DeepSeek VL | DeepSeek | 4K | $0.140/1M | $0.280/1M | $0.00028 | $2.8 | Cost |
| 20 | Ministral 8B | Mistral | 128K | $0.150/1M | $0.150/1M | $0.000225 | $2.25 | Cost |
| 21 | Mistral Nemo | Mistral | 128K | $0.150/1M | $0.150/1M | $0.000225 | $2.25 | Cost |
| 22 | Pixtral 12B | Mistral | 128K | $0.150/1M | $0.150/1M | $0.000225 | $2.25 | Cost |
| 23 | GPT-4o mini | OpenAI | 128K | $0.150/1M | $0.600/1M | $0.00045 | $4.5 | Cost |
| 24 | Command R | Cohere | 128K | $0.150/1M | $0.600/1M | $0.00045 | $4.5 | Cost |
| 25 | Command R (08-2024) | Cohere | 128K | $0.150/1M | $0.600/1M | $0.00045 | $4.5 | Cost |
| 26 | Llama 3.2 11B Vision (Groq) | Groq | 128K | $0.180/1M | $0.180/1M | $0.00027 | $2.7 | Cost |
| 27 | Llama 3.1 8B (Together) | Together AI | 128K | $0.180/1M | $0.180/1M | $0.00027 | $2.7 | Cost |
| 28 | Gemma 2 9B (Groq) | Groq | 8K | $0.200/1M | $0.200/1M | $0.0003 | $3.00 | Cost |
| 29 | Llama Guard 3 8B (Groq) | Groq | 8K | $0.200/1M | $0.200/1M | $0.0003 | $3.00 | Cost |
| 30 | Mistral 7B (Together) | Together AI | 33K | $0.200/1M | $0.200/1M | $0.0003 | $3.00 | Cost |
| 31 | Llama 3.1 8B (Fireworks) | Fireworks | 128K | $0.200/1M | $0.200/1M | $0.0003 | $3.00 | Cost |
| 32 | MythoMax L2 13B (Fireworks) | Fireworks | 4K | $0.200/1M | $0.200/1M | $0.0003 | $3.00 | Cost |
| 33 | Gemma 3 27B | 128K | $0.200/1M | $0.400/1M | $0.0004 | $4.00 | Cost | |
| 34 | Grok 2 Mini | xAI | 131K | $0.200/1M | $0.500/1M | $0.00045 | $4.5 | Cost |
| 35 | Grok 4 Fast | xAI | 256K | $0.200/1M | $0.500/1M | $0.00045 | $4.5 | Cost |
| 36 | Mistral Saba | Mistral | 33K | $0.200/1M | $0.600/1M | $0.0005 | $5.00 | Cost |
| 37 | GPT-5.6 Luna | OpenAI | 1.1M | $0.200/1M | $1.20/1M | $0.0008 | $8.00 | Cost |
| 38 | Llama 4 Maverick (Fireworks) | Fireworks | 1M | $0.220/1M | $0.880/1M | $0.00066 | $6.6 | Cost |
| 39 | Mixtral 8x7B (Groq) | Groq | 33K | $0.240/1M | $0.240/1M | $0.00036 | $3.6 | Cost |
| 40 | Mistral Tiny | Mistral | 33K | $0.250/1M | $0.250/1M | $0.000375 | $3.75 | Cost |
| 41 | Claude 3 Haiku | Anthropic | 200K | $0.250/1M | $1.25/1M | $0.000875 | $8.75 | Cost |
| 42 | Gemini 3.1 Flash-Lite | 1M | $0.250/1M | $1.50/1M | $0.001 | $10.00 | Cost | |
| 43 | GPT-5 Mini | OpenAI | 128K | $0.250/1M | $2.00/1M | $0.00125 | $12.5 | Cost |
| 44 | Llama 4 Maverick (Together) | Together AI | 1M | $0.270/1M | $0.850/1M | $0.000695 | $6.95 | Cost |
| 45 | DeepSeek V3 | DeepSeek | 128K | $0.270/1M | $1.10/1M | $0.00082 | $8.2 | Cost |
| 46 | DeepSeek Chat | DeepSeek | 128K | $0.280/1M | $0.420/1M | $0.00049 | $4.9 | Cost |
| 47 | QwQ 32B (Groq) | Groq | 128K | $0.290/1M | $0.390/1M | $0.000485 | $4.85 | Cost |
| 48 | Qwen3 32B (Groq) | Groq | 131K | $0.290/1M | $0.590/1M | $0.000585 | $5.85 | Cost |
| 49 | Qwen2.5 7B (Together) | Together AI | 33K | $0.300/1M | $0.300/1M | $0.00045 | $4.5 | Cost |
| 50 | Grok 3 Mini | xAI | 131K | $0.300/1M | $0.500/1M | $0.00055 | $5.5 | Cost |
| 51 | DeepSeek R1 Distill Qwen 32B | DeepSeek | 128K | $0.300/1M | $0.600/1M | $0.0006 | $6.00 | Cost |
| 52 | Command Light | Cohere | 4K | $0.300/1M | $0.600/1M | $0.0006 | $6.00 | Cost |
| 53 | Gemini 2.5 Flash | 1M | $0.300/1M | $2.50/1M | $0.00155 | $15.5 | Cost | |
| 54 | GPT-4.1 Mini | OpenAI | 1M | $0.400/1M | $1.60/1M | $0.0012 | $12.00 | Cost |
| 55 | Mistral Medium 3 | Mistral | 128K | $0.400/1M | $2.00/1M | $0.0014 | $14.00 | Cost |
| 56 | DeepSeek V4 Pro | DeepSeek | 1M | $0.435/1M | $0.870/1M | $0.00087 | $8.7 | Cost |
| 57 | GPT-3.5 Turbo | OpenAI | 16K | $0.500/1M | $1.50/1M | $0.00125 | $12.5 | Cost |
| 58 | Gemini 1.0 Pro | 33K | $0.500/1M | $1.50/1M | $0.00125 | $12.5 | Cost | |
| 59 | Mistral Large 3 | Mistral | 128K | $0.500/1M | $1.50/1M | $0.00125 | $12.5 | Cost |
| 60 | Gemini 3 Flash | 1M | $0.500/1M | $3.00/1M | $0.002 | $20.00 | Cost | |
| 61 | DeepSeek R1 | DeepSeek | 128K | $0.550/1M | $2.19/1M | $0.001645 | $16.45 | Cost |
| 62 | DeepSeek Reasoner | DeepSeek | 128K | $0.550/1M | $2.19/1M | $0.001645 | $16.45 | Cost |
| 63 | Llama 3.3 70B (Groq) | Groq | 128K | $0.590/1M | $0.790/1M | $0.000985 | $9.85 | Cost |
| 64 | Llama 3.3 70B SpecDec (Groq) | Groq | 8K | $0.590/1M | $0.990/1M | $0.001085 | $10.85 | Cost |
| 65 | Open Mixtral 8x7B | Mistral | 33K | $0.700/1M | $0.700/1M | $0.00105 | $10.5 | Cost |
| 66 | DeepSeek R1 Distill Llama 70B (Groq) | Groq | 128K | $0.750/1M | $0.990/1M | $0.001245 | $12.45 | Cost |
| 67 | Qwen2.5 Coder 32B (Together) | Together AI | 33K | $0.800/1M | $0.800/1M | $0.0012 | $12.00 | Cost |
| 68 | Claude 3.5 Haiku | Anthropic | 200K | $0.800/1M | $4.00/1M | $0.0028 | $28.00 | Cost |
| 69 | Llama 3.1 70B (Together) | Together AI | 128K | $0.880/1M | $0.880/1M | $0.00132 | $13.2 | Cost |
| 70 | Llama 3.3 70B (Together) | Together AI | 128K | $0.880/1M | $0.880/1M | $0.00132 | $13.2 | Cost |
| 71 | DeepSeek R1 (Fireworks) | Fireworks | 128K | $0.900/1M | $0.900/1M | $0.00135 | $13.5 | Cost |
| 72 | DeepSeek V3 (Fireworks) | Fireworks | 128K | $0.900/1M | $0.900/1M | $0.00135 | $13.5 | Cost |
| 73 | Llama 3.1 70B (Fireworks) | Fireworks | 128K | $0.900/1M | $0.900/1M | $0.00135 | $13.5 | Cost |
| 74 | Llama 3.3 70B (Fireworks) | Fireworks | 128K | $0.900/1M | $0.900/1M | $0.00135 | $13.5 | Cost |
| 75 | Mixtral 8x22B (Fireworks) | Fireworks | 66K | $0.900/1M | $0.900/1M | $0.00135 | $13.5 | Cost |
| 76 | Qwen2.5 32B (Fireworks) | Fireworks | 33K | $0.900/1M | $0.900/1M | $0.00135 | $13.5 | Cost |
| 77 | Qwen2.5 72B (Fireworks) | Fireworks | 33K | $0.900/1M | $0.900/1M | $0.00135 | $13.5 | Cost |
| 78 | Command Nightly | Cohere | 128K | $1.00/1M | $2.00/1M | $0.002 | $20.00 | Cost |
| 79 | Codestral | Mistral | 256K | $1.00/1M | $3.00/1M | $0.0025 | $25.00 | Cost |
| 80 | Claude Haiku 4.5 | Anthropic | 200K | $1.00/1M | $5.00/1M | $0.0035 | $35.00 | Cost |
| 81 | o1-mini | OpenAI | 128K | $1.10/1M | $4.40/1M | $0.0033 | $33.00 | Cost |
| 82 | o3-mini | OpenAI | 200K | $1.10/1M | $4.40/1M | $0.0033 | $33.00 | Cost |
| 83 | o4-mini | OpenAI | 200K | $1.10/1M | $4.40/1M | $0.0033 | $33.00 | Cost |
| 84 | Mixtral 8x22B (Together) | Together AI | 66K | $1.20/1M | $1.20/1M | $0.0018 | $18.00 | Cost |
| 85 | Qwen2.5 72B (Together) | Together AI | 33K | $1.20/1M | $1.20/1M | $0.0018 | $18.00 | Cost |
| 86 | DeepSeek V3 (Together) | Together AI | 128K | $1.25/1M | $1.25/1M | $0.001875 | $18.75 | Cost |
| 87 | Gemini 1.5 Pro | 2M | $1.25/1M | $5.00/1M | $0.00375 | $37.5 | Cost | |
| 88 | Gemini 2.0 Pro Exp | 2M | $1.25/1M | $5.00/1M | $0.00375 | $37.5 | Cost | |
| 89 | GPT-5 | OpenAI | 400K | $1.25/1M | $10.00/1M | $0.00625 | $62.5 | Cost |
| 90 | Gemini 2.5 Pro | 1M | $1.25/1M | $10.00/1M | $0.00625 | $62.5 | Cost | |
| 91 | Grok 4.6 | xAI | 500K | $2.00/1M | $6.00/1M | $0.005 | $50.00 | Cost |
| 92 | Mistral Large (2407) | Mistral | 128K | $2.00/1M | $6.00/1M | $0.005 | $50.00 | Cost |
| 93 | Open Mixtral 8x22B | Mistral | 66K | $2.00/1M | $6.00/1M | $0.005 | $50.00 | Cost |
| 94 | GPT-4.1 | OpenAI | 1M | $2.00/1M | $8.00/1M | $0.006 | $60.00 | Cost |
| 95 | GPT-4.1 (2025-04-14) | OpenAI | 1M | $2.00/1M | $8.00/1M | $0.006 | $60.00 | Cost |
| 96 | o3 | OpenAI | 200K | $2.00/1M | $8.00/1M | $0.006 | $60.00 | Cost |
| 97 | Claude Sonnet 5 | Anthropic | 1M | $2.00/1M | $10.00/1M | $0.007 | $70.00 | Cost |
| 98 | Grok 2 | xAI | 131K | $2.00/1M | $10.00/1M | $0.007 | $70.00 | Cost |
| 99 | Grok 2 Vision | xAI | 33K | $2.00/1M | $10.00/1M | $0.007 | $70.00 | Cost |
| 100 | GPT-5.6 Terra | OpenAI | 1.1M | $2.00/1M | $12.00/1M | $0.008 | $80.00 | Cost |
| 101 | Gemini 3.1 Pro | 1M | $2.00/1M | $12.00/1M | $0.008 | $80.00 | Cost | |
| 102 | GPT-4o | OpenAI | 128K | $2.50/1M | $10.00/1M | $0.0075 | $75.00 | Cost |
| 103 | GPT-4o (2024-08-06) | OpenAI | 128K | $2.50/1M | $10.00/1M | $0.0075 | $75.00 | Cost |
| 104 | Command A | Cohere | 256K | $2.50/1M | $10.00/1M | $0.0075 | $75.00 | Cost |
| 105 | Command R+ | Cohere | 128K | $2.50/1M | $10.00/1M | $0.0075 | $75.00 | Cost |
| 106 | Command R+ (08-2024) | Cohere | 128K | $2.50/1M | $10.00/1M | $0.0075 | $75.00 | Cost |
| 107 | DeepSeek R1 (Together) | Together AI | 128K | $3.00/1M | $7.00/1M | $0.0065 | $65.00 | Cost |
| 108 | Claude 3.5 Sonnet | Anthropic | 200K | $3.00/1M | $15.00/1M | $0.0105 | $105.00 | Cost |
| 109 | Claude 3 Sonnet | Anthropic | 200K | $3.00/1M | $15.00/1M | $0.0105 | $105.00 | Cost |
| 110 | Claude Sonnet 4.6 | Anthropic | 1M | $3.00/1M | $15.00/1M | $0.0105 | $105.00 | Cost |
| 111 | Grok 3 | xAI | 131K | $3.00/1M | $15.00/1M | $0.0105 | $105.00 | Cost |
| 112 | Grok 4 | xAI | 256K | $3.00/1M | $15.00/1M | $0.0105 | $105.00 | Cost |
| 113 | ChatGPT-4o Latest | OpenAI | 128K | $5.00/1M | $15.00/1M | $0.0125 | $125.00 | Cost |
| 114 | Grok Beta | xAI | 131K | $5.00/1M | $15.00/1M | $0.0125 | $125.00 | Cost |
| 115 | Grok Vision Beta | xAI | 8K | $5.00/1M | $15.00/1M | $0.0125 | $125.00 | Cost |
| 116 | Claude Opus 4.6 | Anthropic | 1M | $5.00/1M | $25.00/1M | $0.0175 | $175.00 | Cost |
| 117 | Claude Opus 4.8 | Anthropic | 1M | $5.00/1M | $25.00/1M | $0.0175 | $175.00 | Cost |
| 118 | GPT-5.6 Sol | OpenAI | 1.1M | $5.00/1M | $30.00/1M | $0.02 | $200.00 | Cost |
| 119 | Claude 2.1 | Anthropic | 200K | $8.00/1M | $24.00/1M | $0.02 | $200.00 | Cost |
| 120 | GPT-4 Turbo | OpenAI | 128K | $10.00/1M | $30.00/1M | $0.025 | $250.00 | Cost |
| 121 | o1 | OpenAI | 200K | $15.00/1M | $60.00/1M | $0.045 | $450.00 | Cost |
| 122 | o1-preview | OpenAI | 128K | $15.00/1M | $60.00/1M | $0.045 | $450.00 | Cost |
| 123 | Claude 3 Opus | Anthropic | 200K | $15.00/1M | $75.00/1M | $0.0525 | $525.00 | Cost |
| 124 | GPT-4 | OpenAI | 8K | $30.00/1M | $60.00/1M | $0.06 | $600.00 | Cost |
Related tools
LLM cost calculator · Compare model prices · Cache savings · Batch pricing
Related guides
How LLM API pricing works · How prompt cost is calculated · Prompt caching explained · Exact vs Approx
Sources and references
Official documentation used for definitions, counting methods, or rate cards. Always confirm critical budgets on the provider page.
Pricing rank FAQ
- How is cheapest ranked?
- We sort by published input rate per 1M tokens. Ties break on the example request (1000 input and 500 output). This is a price rank, not a quality score.
- What is the example cost?
- One request using 1000 input tokens and 500 output tokens at published standard rates, with no cache hit and no batch discount.
- Are these live API prices?
- No. Rates are curated from official provider pages and stamped with a checked date. Confirm critical budgets on the provider’s pricing page.