Cheapest models for long replies
Ranked by output rate per 1M tokens. The example uses 1000 input tokens and 2000 output tokens, which is closer to support chat and writing than a short completion.
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 | Long example | 10k requests | |
|---|---|---|---|---|---|---|---|---|
| 1 | Llama 3.2 1B (Groq) | Groq | 128K | $0.040/1M | $0.040/1M | $0.00012 | $1.2 | Cost |
| 2 | Llama 3.2 3B (Groq) | Groq | 128K | $0.060/1M | $0.060/1M | $0.00018 | $1.8 | Cost |
| 3 | Llama 3.2 3B (Together) | Together AI | 128K | $0.060/1M | $0.060/1M | $0.00018 | $1.8 | Cost |
| 4 | Gemma 7B (Groq) | Groq | 8K | $0.070/1M | $0.070/1M | $0.00021 | $2.1 | Cost |
| 5 | Llama 3.1 8B Instant (Groq) | Groq | 128K | $0.050/1M | $0.080/1M | $0.00021 | $2.1 | Cost |
| 6 | Llama 3.2 3B (Fireworks) | Fireworks | 128K | $0.100/1M | $0.100/1M | $0.0003 | $3.00 | Cost |
| 7 | Gemini 1.5 Flash-8B | 1M | $0.037/1M | $0.150/1M | $0.000337 | $3.37 | Cost | |
| 8 | Command R7B | Cohere | 128K | $0.037/1M | $0.150/1M | $0.000337 | $3.37 | Cost |
| 9 | Ministral 8B | Mistral | 128K | $0.150/1M | $0.150/1M | $0.00045 | $4.5 | Cost |
| 10 | Mistral Nemo | Mistral | 128K | $0.150/1M | $0.150/1M | $0.00045 | $4.5 | Cost |
| 11 | Pixtral 12B | Mistral | 128K | $0.150/1M | $0.150/1M | $0.00045 | $4.5 | Cost |
| 12 | Mistral Small | Mistral | 128K | $0.060/1M | $0.180/1M | $0.00042 | $4.2 | Cost |
| 13 | Llama 3.2 11B Vision (Groq) | Groq | 128K | $0.180/1M | $0.180/1M | $0.00054 | $5.4 | Cost |
| 14 | Llama 3.1 8B (Together) | Together AI | 128K | $0.180/1M | $0.180/1M | $0.00054 | $5.4 | Cost |
| 15 | Gemma 2 9B (Groq) | Groq | 8K | $0.200/1M | $0.200/1M | $0.0006 | $6.00 | Cost |
| 16 | Llama Guard 3 8B (Groq) | Groq | 8K | $0.200/1M | $0.200/1M | $0.0006 | $6.00 | Cost |
| 17 | Mistral 7B (Together) | Together AI | 33K | $0.200/1M | $0.200/1M | $0.0006 | $6.00 | Cost |
| 18 | Llama 3.1 8B (Fireworks) | Fireworks | 128K | $0.200/1M | $0.200/1M | $0.0006 | $6.00 | Cost |
| 19 | MythoMax L2 13B (Fireworks) | Fireworks | 4K | $0.200/1M | $0.200/1M | $0.0006 | $6.00 | Cost |
| 20 | Mixtral 8x7B (Groq) | Groq | 33K | $0.240/1M | $0.240/1M | $0.00072 | $7.2 | Cost |
| 21 | Mistral Tiny | Mistral | 33K | $0.250/1M | $0.250/1M | $0.00075 | $7.5 | Cost |
| 22 | DeepSeek Coder | DeepSeek | 128K | $0.140/1M | $0.280/1M | $0.0007 | $7.00 | Cost |
| 23 | DeepSeek V4 Flash | DeepSeek | 1M | $0.140/1M | $0.280/1M | $0.0007 | $7.00 | Cost |
| 24 | DeepSeek VL | DeepSeek | 4K | $0.140/1M | $0.280/1M | $0.0007 | $7.00 | Cost |
| 25 | Gemini 1.5 Flash | 1M | $0.075/1M | $0.300/1M | $0.000675 | $6.75 | Cost | |
| 26 | Gemini 2.0 Flash-Lite | 1M | $0.075/1M | $0.300/1M | $0.000675 | $6.75 | Cost | |
| 27 | Qwen2.5 7B (Together) | Together AI | 33K | $0.300/1M | $0.300/1M | $0.0009 | $9.00 | Cost |
| 28 | Llama 4 Scout (Groq) | Groq | 128K | $0.110/1M | $0.340/1M | $0.00079 | $7.9 | Cost |
| 29 | QwQ 32B (Groq) | Groq | 128K | $0.290/1M | $0.390/1M | $0.00107 | $10.7 | Cost |
| 30 | GPT-5 Nano | OpenAI | 128K | $0.050/1M | $0.400/1M | $0.00085 | $8.5 | Cost |
| 31 | GPT-4.1 Nano | OpenAI | 1M | $0.100/1M | $0.400/1M | $0.0009 | $9.00 | Cost |
| 32 | Gemini 2.0 Flash | 1M | $0.100/1M | $0.400/1M | $0.0009 | $9.00 | Cost | |
| 33 | Gemini 2.5 Flash-Lite | 1M | $0.100/1M | $0.400/1M | $0.0009 | $9.00 | Cost | |
| 34 | Gemma 3 27B | 128K | $0.200/1M | $0.400/1M | $0.001 | $10.00 | Cost | |
| 35 | DeepSeek Chat | DeepSeek | 128K | $0.280/1M | $0.420/1M | $0.00112 | $11.2 | Cost |
| 36 | Grok 2 Mini | xAI | 131K | $0.200/1M | $0.500/1M | $0.0012 | $12.00 | Cost |
| 37 | Grok 4 Fast | xAI | 256K | $0.200/1M | $0.500/1M | $0.0012 | $12.00 | Cost |
| 38 | Grok 3 Mini | xAI | 131K | $0.300/1M | $0.500/1M | $0.0013 | $13.00 | Cost |
| 39 | Qwen3 32B (Groq) | Groq | 131K | $0.290/1M | $0.590/1M | $0.00147 | $14.7 | Cost |
| 40 | GPT-4o mini | OpenAI | 128K | $0.150/1M | $0.600/1M | $0.00135 | $13.5 | Cost |
| 41 | Command R | Cohere | 128K | $0.150/1M | $0.600/1M | $0.00135 | $13.5 | Cost |
| 42 | Command R (08-2024) | Cohere | 128K | $0.150/1M | $0.600/1M | $0.00135 | $13.5 | Cost |
| 43 | Mistral Saba | Mistral | 33K | $0.200/1M | $0.600/1M | $0.0014 | $14.00 | Cost |
| 44 | DeepSeek R1 Distill Qwen 32B | DeepSeek | 128K | $0.300/1M | $0.600/1M | $0.0015 | $15.00 | Cost |
| 45 | Command Light | Cohere | 4K | $0.300/1M | $0.600/1M | $0.0015 | $15.00 | Cost |
| 46 | Open Mixtral 8x7B | Mistral | 33K | $0.700/1M | $0.700/1M | $0.0021 | $21.00 | Cost |
| 47 | Llama 3.3 70B (Groq) | Groq | 128K | $0.590/1M | $0.790/1M | $0.00217 | $21.7 | Cost |
| 48 | Qwen2.5 Coder 32B (Together) | Together AI | 33K | $0.800/1M | $0.800/1M | $0.0024 | $24.00 | Cost |
| 49 | Llama 4 Maverick (Together) | Together AI | 1M | $0.270/1M | $0.850/1M | $0.00197 | $19.7 | Cost |
| 50 | DeepSeek V4 Pro | DeepSeek | 1M | $0.435/1M | $0.870/1M | $0.002175 | $21.75 | Cost |
| 51 | Llama 4 Maverick (Fireworks) | Fireworks | 1M | $0.220/1M | $0.880/1M | $0.00198 | $19.8 | Cost |
| 52 | Llama 3.1 70B (Together) | Together AI | 128K | $0.880/1M | $0.880/1M | $0.00264 | $26.4 | Cost |
| 53 | Llama 3.3 70B (Together) | Together AI | 128K | $0.880/1M | $0.880/1M | $0.00264 | $26.4 | Cost |
| 54 | DeepSeek R1 (Fireworks) | Fireworks | 128K | $0.900/1M | $0.900/1M | $0.0027 | $27.00 | Cost |
| 55 | DeepSeek V3 (Fireworks) | Fireworks | 128K | $0.900/1M | $0.900/1M | $0.0027 | $27.00 | Cost |
| 56 | Llama 3.1 70B (Fireworks) | Fireworks | 128K | $0.900/1M | $0.900/1M | $0.0027 | $27.00 | Cost |
| 57 | Llama 3.3 70B (Fireworks) | Fireworks | 128K | $0.900/1M | $0.900/1M | $0.0027 | $27.00 | Cost |
| 58 | Mixtral 8x22B (Fireworks) | Fireworks | 66K | $0.900/1M | $0.900/1M | $0.0027 | $27.00 | Cost |
| 59 | Qwen2.5 32B (Fireworks) | Fireworks | 33K | $0.900/1M | $0.900/1M | $0.0027 | $27.00 | Cost |
| 60 | Qwen2.5 72B (Fireworks) | Fireworks | 33K | $0.900/1M | $0.900/1M | $0.0027 | $27.00 | Cost |
| 61 | Llama 3.3 70B SpecDec (Groq) | Groq | 8K | $0.590/1M | $0.990/1M | $0.00257 | $25.7 | Cost |
| 62 | DeepSeek R1 Distill Llama 70B (Groq) | Groq | 128K | $0.750/1M | $0.990/1M | $0.00273 | $27.3 | Cost |
| 63 | DeepSeek V3 | DeepSeek | 128K | $0.270/1M | $1.10/1M | $0.00247 | $24.7 | Cost |
| 64 | GPT-5.6 Luna | OpenAI | 1.1M | $0.200/1M | $1.20/1M | $0.0026 | $26.00 | Cost |
| 65 | Mixtral 8x22B (Together) | Together AI | 66K | $1.20/1M | $1.20/1M | $0.0036 | $36.00 | Cost |
| 66 | Qwen2.5 72B (Together) | Together AI | 33K | $1.20/1M | $1.20/1M | $0.0036 | $36.00 | Cost |
| 67 | Claude 3 Haiku | Anthropic | 200K | $0.250/1M | $1.25/1M | $0.00275 | $27.5 | Cost |
| 68 | DeepSeek V3 (Together) | Together AI | 128K | $1.25/1M | $1.25/1M | $0.00375 | $37.5 | Cost |
| 69 | Gemini 3.1 Flash-Lite | 1M | $0.250/1M | $1.50/1M | $0.00325 | $32.5 | Cost | |
| 70 | GPT-3.5 Turbo | OpenAI | 16K | $0.500/1M | $1.50/1M | $0.0035 | $35.00 | Cost |
| 71 | Gemini 1.0 Pro | 33K | $0.500/1M | $1.50/1M | $0.0035 | $35.00 | Cost | |
| 72 | Mistral Large 3 | Mistral | 128K | $0.500/1M | $1.50/1M | $0.0035 | $35.00 | Cost |
| 73 | GPT-4.1 Mini | OpenAI | 1M | $0.400/1M | $1.60/1M | $0.0036 | $36.00 | Cost |
| 74 | GPT-5 Mini | OpenAI | 128K | $0.250/1M | $2.00/1M | $0.00425 | $42.5 | Cost |
| 75 | Mistral Medium 3 | Mistral | 128K | $0.400/1M | $2.00/1M | $0.0044 | $44.00 | Cost |
| 76 | Command Nightly | Cohere | 128K | $1.00/1M | $2.00/1M | $0.005 | $50.00 | Cost |
| 77 | DeepSeek R1 | DeepSeek | 128K | $0.550/1M | $2.19/1M | $0.00493 | $49.3 | Cost |
| 78 | DeepSeek Reasoner | DeepSeek | 128K | $0.550/1M | $2.19/1M | $0.00493 | $49.3 | Cost |
| 79 | Gemini 2.5 Flash | 1M | $0.300/1M | $2.50/1M | $0.0053 | $53.00 | Cost | |
| 80 | Gemini 3 Flash | 1M | $0.500/1M | $3.00/1M | $0.0065 | $65.00 | Cost | |
| 81 | Codestral | Mistral | 256K | $1.00/1M | $3.00/1M | $0.007 | $70.00 | Cost |
| 82 | Claude 3.5 Haiku | Anthropic | 200K | $0.800/1M | $4.00/1M | $0.0088 | $88.00 | Cost |
| 83 | o1-mini | OpenAI | 128K | $1.10/1M | $4.40/1M | $0.0099 | $99.00 | Cost |
| 84 | o3-mini | OpenAI | 200K | $1.10/1M | $4.40/1M | $0.0099 | $99.00 | Cost |
| 85 | o4-mini | OpenAI | 200K | $1.10/1M | $4.40/1M | $0.0099 | $99.00 | Cost |
| 86 | Claude Haiku 4.5 | Anthropic | 200K | $1.00/1M | $5.00/1M | $0.011 | $110.00 | Cost |
| 87 | Gemini 1.5 Pro | 2M | $1.25/1M | $5.00/1M | $0.01125 | $112.5 | Cost | |
| 88 | Gemini 2.0 Pro Exp | 2M | $1.25/1M | $5.00/1M | $0.01125 | $112.5 | Cost | |
| 89 | Grok 4.6 | xAI | 500K | $2.00/1M | $6.00/1M | $0.014 | $140.00 | Cost |
| 90 | Mistral Large (2407) | Mistral | 128K | $2.00/1M | $6.00/1M | $0.014 | $140.00 | Cost |
| 91 | Open Mixtral 8x22B | Mistral | 66K | $2.00/1M | $6.00/1M | $0.014 | $140.00 | Cost |
| 92 | DeepSeek R1 (Together) | Together AI | 128K | $3.00/1M | $7.00/1M | $0.017 | $170.00 | Cost |
| 93 | GPT-4.1 | OpenAI | 1M | $2.00/1M | $8.00/1M | $0.018 | $180.00 | Cost |
| 94 | GPT-4.1 (2025-04-14) | OpenAI | 1M | $2.00/1M | $8.00/1M | $0.018 | $180.00 | Cost |
| 95 | o3 | OpenAI | 200K | $2.00/1M | $8.00/1M | $0.018 | $180.00 | Cost |
| 96 | GPT-5 | OpenAI | 400K | $1.25/1M | $10.00/1M | $0.02125 | $212.5 | Cost |
| 97 | Gemini 2.5 Pro | 1M | $1.25/1M | $10.00/1M | $0.02125 | $212.5 | Cost | |
| 98 | Claude Sonnet 5 | Anthropic | 1M | $2.00/1M | $10.00/1M | $0.022 | $220.00 | Cost |
| 99 | Grok 2 | xAI | 131K | $2.00/1M | $10.00/1M | $0.022 | $220.00 | Cost |
| 100 | Grok 2 Vision | xAI | 33K | $2.00/1M | $10.00/1M | $0.022 | $220.00 | Cost |
| 101 | GPT-4o | OpenAI | 128K | $2.50/1M | $10.00/1M | $0.0225 | $225.00 | Cost |
| 102 | GPT-4o (2024-08-06) | OpenAI | 128K | $2.50/1M | $10.00/1M | $0.0225 | $225.00 | Cost |
| 103 | Command A | Cohere | 256K | $2.50/1M | $10.00/1M | $0.0225 | $225.00 | Cost |
| 104 | Command R+ | Cohere | 128K | $2.50/1M | $10.00/1M | $0.0225 | $225.00 | Cost |
| 105 | Command R+ (08-2024) | Cohere | 128K | $2.50/1M | $10.00/1M | $0.0225 | $225.00 | Cost |
| 106 | GPT-5.6 Terra | OpenAI | 1.1M | $2.00/1M | $12.00/1M | $0.026 | $260.00 | Cost |
| 107 | Gemini 3.1 Pro | 1M | $2.00/1M | $12.00/1M | $0.026 | $260.00 | Cost | |
| 108 | Claude 3.5 Sonnet | Anthropic | 200K | $3.00/1M | $15.00/1M | $0.033 | $330.00 | Cost |
| 109 | Claude 3 Sonnet | Anthropic | 200K | $3.00/1M | $15.00/1M | $0.033 | $330.00 | Cost |
| 110 | Claude Sonnet 4.6 | Anthropic | 1M | $3.00/1M | $15.00/1M | $0.033 | $330.00 | Cost |
| 111 | Grok 3 | xAI | 131K | $3.00/1M | $15.00/1M | $0.033 | $330.00 | Cost |
| 112 | Grok 4 | xAI | 256K | $3.00/1M | $15.00/1M | $0.033 | $330.00 | Cost |
| 113 | ChatGPT-4o Latest | OpenAI | 128K | $5.00/1M | $15.00/1M | $0.035 | $350.00 | Cost |
| 114 | Grok Beta | xAI | 131K | $5.00/1M | $15.00/1M | $0.035 | $350.00 | Cost |
| 115 | Grok Vision Beta | xAI | 8K | $5.00/1M | $15.00/1M | $0.035 | $350.00 | Cost |
| 116 | Claude 2.1 | Anthropic | 200K | $8.00/1M | $24.00/1M | $0.056 | $560.00 | Cost |
| 117 | Claude Opus 4.6 | Anthropic | 1M | $5.00/1M | $25.00/1M | $0.055 | $550.00 | Cost |
| 118 | Claude Opus 4.8 | Anthropic | 1M | $5.00/1M | $25.00/1M | $0.055 | $550.00 | Cost |
| 119 | GPT-5.6 Sol | OpenAI | 1.1M | $5.00/1M | $30.00/1M | $0.065 | $650.00 | Cost |
| 120 | GPT-4 Turbo | OpenAI | 128K | $10.00/1M | $30.00/1M | $0.07 | $700.00 | Cost |
| 121 | o1 | OpenAI | 200K | $15.00/1M | $60.00/1M | $0.135 | $1350.00 | Cost |
| 122 | o1-preview | OpenAI | 128K | $15.00/1M | $60.00/1M | $0.135 | $1350.00 | Cost |
| 123 | GPT-4 | OpenAI | 8K | $30.00/1M | $60.00/1M | $0.15 | $1500.00 | Cost |
| 124 | Claude 3 Opus | Anthropic | 200K | $15.00/1M | $75.00/1M | $0.165 | $1650.00 | Cost |
Related tools
LLM cost calculator · Cheapest LLM API · 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
- Why rank by output?
- Long answers are billed on output tokens, which are usually more expensive than input. A cheap input rate can still be a costly chat model.
- What is the long example?
- 1000 input tokens and 2000 output tokens at standard rates, no cache and no batch.
- Can I change the mix?
- Yes. Open Cost on any row and set your own output size and monthly volume.