LLM API prices per million tokens
Output tokens usually cost three to five times input tokens, so a single price per model is meaningless. Both are shown here, plus a blended figure at a 3:1 input-to-output ratio, which is roughly what a chat workload looks like.
- Models priced
- 1040
- Vendors
- 11
- Blend ratio
- 3:1
LLM API cost calculator
Your traffic, priced across every model.
| Model | Vendor | $/1M in | $/1M out | Context | Monthly cost |
|---|---|---|---|---|---|
| llama-3.1-8b-instructCheapest | OpenRouter | $0.020 | $0.040 | 131,072 | $1.92 |
| Llama-3.2-1B-Instruct | Together AI | $0.060 | $0.060 | 131,072 | $4.68 |
| Llama-3.2-3B-Instruct | Together AI | $0.060 | $0.060 | 131,072 | $4.68 |
| gpt-5-nano:batch | OpenRouter | $0.025 | $0.200 | 400,000 | $5.10 |
| llama-3.2-1b-instruct | OpenRouter | $0.027 | $0.201 | 60,000 | $5.24 |
| gpt-4.1-nano:batch | OpenRouter | $0.050 | $0.200 | 1,047,576 | $6.60 |
| claude-haiku-5.5:batch | OpenRouter | $0.050 | $0.250 | 1,000,000 | $7.50 |
| llama-3.2-3b-instruct | OpenRouter | $0.050 | $0.330 | 131,072 | $8.94 |
| gpt-4o-mini:batch | OpenRouter | $0.075 | $0.300 | 128,000 | $9.90 |
| gpt-5-nano | OpenAI | $0.050 | $0.400 | 272,000 | $10.20 |
| llama-4-scout | OpenRouter | $0.100 | $0.300 | 1,310,720 | $11.40 |
| llama-3.3-70b-instruct | OpenRouter | $0.100 | $0.320 | 131,072 | $11.76 |
| gemini-2.5-flash-lite | Google AI | $0.100 | $0.400 | 1,048,576 | $13.20 |
| gemini-2.5-flash-lite-preview-09-2025 | Google AI | $0.100 | $0.400 | 1,048,576 | $13.20 |
| gpt-4.1-nano | OpenAI | $0.100 | $0.400 | 1,047,576 | $13.20 |
| claude-haiku-5-5 | Anthropic | $0.100 | $0.500 | 1,000,000 | $15.00 |
| claude-haiku-5.5 | OpenRouter | $0.100 | $0.500 | 1,000,000 | $15.00 |
| claude-haiku-latest | OpenRouter | $0.100 | $0.500 | 1,000,000 | $15.00 |
| Llama-3-8b-chat-hf | Together AI | $0.200 | $0.200 | 8,192 | $15.60 |
| gpt-5.6-luna:batch | OpenRouter | $0.100 | $0.600 | 1,050,000 | $16.80 |
| gpt-5.6-luna-pro:batch | OpenRouter | $0.100 | $0.600 | 1,050,000 | $16.80 |
| gpt-5.4-nano:batch | OpenRouter | $0.100 | $0.625 | 400,000 | $17.25 |
| gpt-4o-mini | OpenAI | $0.150 | $0.600 | 128,000 | $19.80 |
| gpt-4o-mini-audio-preview-2024-12-17 | OpenAI | $0.150 | $0.600 | 128,000 | $19.80 |
| gpt-4o-mini-search-preview | OpenAI | $0.150 | $0.600 | 128,000 | $19.80 |
| Llama-4-Scout-17B-16E-Instruct | Together AI | $0.180 | $0.590 | 1,048,576 | $21.42 |
| llama-4-maverick | OpenRouter | $0.188 | $0.652 | 524,288 | $22.99 |
| deepseek-v3.2-exp | OpenRouter | $0.270 | $0.410 | 163,840 | $23.58 |
| deepseek-v3.2 | DeepSeek | $0.280 | $0.400 | 163,840 | $24.00 |
| deepseek-chat | DeepSeek | $0.280 | $0.420 | 131,072 | $24.36 |
| deepseek-reasoner | DeepSeek | $0.280 | $0.420 | 131,072 | $24.36 |
| gpt-5-mini:batch | OpenRouter | $0.125 | $1.00 | 400,000 | $25.50 |
| gpt-4.1-mini:batch | OpenRouter | $0.200 | $0.800 | 1,047,576 | $26.40 |
| llama-3.1-70b-instruct | OpenRouter | $0.400 | $0.400 | 131,072 | $31.20 |
| deepseek-chat-v3.1 | OpenRouter | $0.250 | $0.950 | 163,840 | $32.10 |
| gpt-5.6-luna | OpenAI | $0.200 | $1.20 | 922,000 | $33.60 |
| gpt-5.6-luna-pro | OpenRouter | $0.200 | $1.20 | 1,050,000 | $33.60 |
| deepseek-v3.1-terminus | OpenRouter | $0.270 | $1.00 | 163,840 | $34.20 |
| gpt-5.4-nano | OpenAI | $0.200 | $1.25 | 272,000 | $34.50 |
| deepseek-v3 | DeepSeek | $0.270 | $1.10 | 65,536 | $36.00 |
| deepseek-chat-v3-0324 | OpenRouter | $0.290 | $1.14 | 163,840 | $37.92 |
| command-a-plus | OpenRouter | $0.300 | $1.50 | 192,000 | $45.00 |
| gpt-5-mini | OpenAI | $0.250 | $2.00 | 272,000 | $51.00 |
| gpt-5.1-codex-mini | OpenRouter | $0.250 | $2.00 | 400,000 | $51.00 |
| gpt-4.1-mini | OpenAI | $0.400 | $1.60 | 1,047,576 | $52.80 |
| mistral-large-2512 | Mistral AI | $0.500 | $1.50 | 262,144 | $57.00 |
| mistral-large-3 | Mistral AI | $0.500 | $1.50 | 262,144 | $57.00 |
| gpt-5.4-mini:batch | OpenRouter | $0.375 | $2.25 | 400,000 | $63.00 |
| gemini-2.5-flash | Google AI | $0.300 | $2.50 | 1,048,576 | $63.00 |
| gemini-2.5-flash-preview-09-2025 | Google AI | $0.300 | $2.50 | 1,048,576 | $63.00 |
| deepseek-v3p1 | Fireworks AI | $0.560 | $1.68 | 128,000 | $63.84 |
| deepseek-v3p1-terminus | Fireworks AI | $0.560 | $1.68 | 128,000 | $63.84 |
| deepseek-v3p2 | Fireworks AI | $0.560 | $1.68 | 163,840 | $63.84 |
| DeepSeek-V3.1 | Together AI | $0.600 | $1.70 | 131,072 | $66.60 |
| Llama-3.1-Nemotron-70B-Instruct-HF | Together AI | $0.880 | $0.880 | 32,768 | $68.64 |
| deepseek-v3-0324 | Fireworks AI | $0.900 | $0.900 | 163,840 | $70.20 |
| o3-mini:batch | OpenRouter | $0.550 | $2.20 | 200,000 | $72.60 |
| o4-mini:batch | OpenRouter | $0.550 | $2.20 | 200,000 | $72.60 |
| claude-haiku-4.5:batch | OpenRouter | $0.500 | $2.50 | 200,000 | $75.00 |
| mistral-large-4 | Mistral AI | $0.680 | $2.09 | 1,048,576 | $78.42 |
Prices last checked: . Base data from LiteLLM (MIT), overlaid with vendor pricing pages; OpenRouter from its own API. Methodology · Attribution
Well-known models
Standard tier of each model, ranked by blended cost per million tokens at 3:1 input to output. Batch and pro tiers are on each model's page.
| Source | |||||||
|---|---|---|---|---|---|---|---|
| llama-3.1-8b-instruct Best value | OpenRouter | $0.020 | $0.040 | — | 131,072 | $0.025 | ↗ |
| Llama-3.2-1B-Instruct | Together AI | $0.060 | $0.060 | — | 131,072 | $0.060 | ↗ |
| Llama-3.2-3B-Instruct | Together AI | $0.060 | $0.060 | — | 131,072 | $0.060 | ↗ |
| gpt-5-nano | OpenAI | $0.050 | $0.400 | $0.005 | 272,000 | $0.138 | ↗ |
| llama-4-scout | OpenRouter | $0.100 | $0.300 | — | 1,310,720 | $0.150 | ↗ |
| llama-3.3-70b-instruct | OpenRouter | $0.100 | $0.320 | — | 131,072 | $0.155 | ↗ |
| gpt-4.1-nano | OpenAI | $0.100 | $0.400 | $0.025 | 1,047,576 | $0.175 | ↗ |
| gemini-2.5-flash-lite | Google AI | $0.100 | $0.400 | $0.010 | 1,048,576 | $0.175 | ↗ |
| claude-haiku-5-5 | Anthropic | $0.100 | $0.500 | $0.010 | 1,000,000 | $0.200 | ↗ |
| Llama-3-8b-chat-hf | Together AI | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| gpt-4o-mini | OpenAI | $0.150 | $0.600 | $0.075 | 128,000 | $0.263 | ↗ |
| llama-4-maverick | OpenRouter | $0.188 | $0.652 | $0.050 | 524,288 | $0.304 | ↗ |
| deepseek-v3.2 | DeepSeek | $0.280 | $0.400 | $0.028 | 163,840 | $0.310 | ↗ |
| deepseek-chat | DeepSeek | $0.280 | $0.420 | $0.028 | 131,072 | $0.315 | ↗ |
| deepseek-reasoner | DeepSeek | $0.280 | $0.420 | $0.028 | 131,072 | $0.315 | ↗ |
| llama-3.1-70b-instruct | OpenRouter | $0.400 | $0.400 | — | 131,072 | $0.400 | ↗ |
| gpt-5.6-luna | OpenAI | $0.200 | $1.20 | $0.020 | 922,000 | $0.450 | ↗ |
| gpt-5.4-nano | OpenAI | $0.200 | $1.25 | $0.020 | 272,000 | $0.463 | ↗ |
| deepseek-v3 | DeepSeek | $0.270 | $1.10 | $0.070 | 65,536 | $0.477 | ↗ |
| command-a-plus | OpenRouter | $0.300 | $1.50 | $0.150 | 192,000 | $0.600 | ↗ |
| gpt-5-mini | OpenAI | $0.250 | $2.00 | $0.025 | 272,000 | $0.688 | ↗ |
| gpt-5.1-codex-mini | OpenRouter | $0.250 | $2.00 | $0.030 | 400,000 | $0.688 | ↗ |
| gpt-4.1-mini | OpenAI | $0.400 | $1.60 | $0.100 | 1,047,576 | $0.700 | ↗ |
| mistral-large-3 | Mistral AI | $0.500 | $1.50 | $0.050 | 262,144 | $0.750 | ↗ |
| gemini-2.5-flash | Google AI | $0.300 | $2.50 | $0.030 | 1,048,576 | $0.850 | ↗ |
| DeepSeek-V3.1 | Together AI | $0.600 | $1.70 | — | 131,072 | $0.875 | ↗ |
| Llama-3.1-Nemotron-70B-Instruct-HF | Together AI | $0.880 | $0.880 | — | 32,768 | $0.880 | ↗ |
| mistral-large-4 | Mistral AI | $0.680 | $2.09 | $0.068 | 1,048,576 | $1.03 | ↗ |
| mistral-large-4-0 | Mistral AI | $0.680 | $2.09 | $0.068 | 1,048,576 | $1.03 | ↗ |
| grok-4.3 | xAI | $1.25 | $2.50 | $0.200 | 1,000,000 | $1.56 | ↗ |
| grok-4.20 | xAI | $1.25 | $2.50 | $0.200 | 1,000,000 | $1.56 | ↗ |
| gpt-5.4-mini | OpenAI | $0.750 | $4.50 | $0.075 | 272,000 | $1.69 | ↗ |
| o3-mini | OpenAI | $1.10 | $4.40 | $0.550 | 200,000 | $1.93 | ↗ |
| o4-mini | OpenAI | $1.10 | $4.40 | $0.275 | 200,000 | $1.93 | ↗ |
| claude-haiku-4-5 | Anthropic | $1.00 | $5.00 | $0.100 | 200,000 | $2.00 | ↗ |
| mistral-large | OpenRouter | $2.00 | $6.00 | $0.200 | 128,000 | $3.00 | ↗ |
| grok-4.5 | xAI | $2.00 | $6.00 | $0.300 | 500,000 | $3.00 | ↗ |
| grok-4.6 | xAI | $2.00 | $6.00 | $0.500 | 500,000 | $3.00 | ↗ |
| grok-4.7 | xAI | $2.00 | $6.00 | $0.500 | 500,000 | $3.00 | ↗ |
| gpt-5.1 | OpenAI | $1.25 | $10.00 | $0.125 | 272,000 | $3.44 | ↗ |
| gpt-5 | OpenAI | $1.25 | $10.00 | $0.125 | 272,000 | $3.44 | ↗ |
| gemini-2.5-pro | Google AI | $1.25 | $10.00 | $0.125 | 1,048,576 | $3.44 | ↗ |
| gpt-5.1-codex | OpenRouter | $1.25 | $10.00 | $0.130 | 400,000 | $3.44 | ↗ |
| gpt-4.1 | OpenAI | $2.00 | $8.00 | $0.500 | 1,047,576 | $3.50 | ↗ |
| o3 | OpenAI | $2.00 | $8.00 | $0.500 | 200,000 | $3.50 | ↗ |
| Llama-3.1-405B-Instruct | Together AI | $3.50 | $3.50 | — | 4,096 | $3.50 | ↗ |
| claude-sonnet-5-5 | Anthropic | $2.00 | $10.00 | $0.100 | 1,000,000 | $4.00 | ↗ |
| claude-sonnet-5 | Anthropic | $2.00 | $10.00 | $0.200 | 1,000,000 | $4.00 | ↗ |
| gpt-4o | OpenAI | $2.50 | $10.00 | $1.25 | 128,000 | $4.38 | ↗ |
| command-a | OpenRouter | $2.50 | $10.00 | — | 256,000 | $4.38 | ↗ |
| gpt-5.6-terra | OpenAI | $2.00 | $12.00 | $0.200 | 922,000 | $4.50 | ↗ |
| gpt-5.2 | OpenAI | $1.75 | $14.00 | $0.175 | 272,000 | $4.81 | ↗ |
| gpt-5.3-chat | OpenAI | $1.75 | $14.00 | $0.175 | 128,000 | $4.81 | ↗ |
| gpt-5.2-codex | OpenRouter | $1.75 | $14.00 | $0.175 | 400,000 | $4.81 | ↗ |
| gpt-5.3-codex | OpenRouter | $1.75 | $14.00 | $0.175 | 400,000 | $4.81 | ↗ |
| gpt-5.4 | OpenAI | $2.50 | $15.00 | $0.250 | 1,050,000 | $5.63 | ↗ |
| claude-sonnet-4-5 | Anthropic | $3.00 | $15.00 | $0.300 | 200,000 | $6.00 | ↗ |
| claude-sonnet-4-6 | Anthropic | $3.00 | $15.00 | $0.300 | 1,000,000 | $6.00 | ↗ |
| claude-opus-5-5 | Anthropic | $4.00 | $20.00 | $0.200 | 1,000,000 | $8.00 | ↗ |
| gpt-5.6-sol | OpenAI | $4.00 | $20.00 | $0.400 | 922,000 | $8.00 | ↗ |
| gpt-5.6 | OpenAI | $4.00 | $20.00 | $0.400 | 922,000 | $8.00 | ↗ |
| claude-opus-4-5 | Anthropic | $5.00 | $25.00 | $0.500 | 200,000 | $10.00 | ↗ |
| claude-opus-4-6 | Anthropic | $5.00 | $25.00 | $0.500 | 1,000,000 | $10.00 | ↗ |
| claude-opus-4-7 | Anthropic | $5.00 | $25.00 | $0.500 | 1,000,000 | $10.00 | ↗ |
| claude-opus-4-8 | Anthropic | $5.00 | $25.00 | $0.500 | 1,000,000 | $10.00 | ↗ |
| claude-opus-5 | Anthropic | $5.00 | $25.00 | $0.500 | 1,000,000 | $10.00 | ↗ |
| gpt-5.5 | OpenAI | $5.00 | $30.00 | $0.500 | 1,050,000 | $11.25 | ↗ |
| gpt-4-turbo | OpenAI | $10.00 | $30.00 | — | 128,000 | $15.00 | ↗ |
| o1 | OpenAI | $15.00 | $60.00 | $7.50 | 200,000 | $26.25 | ↗ |
| gpt-5.5-cyber | OpenAI | $12.50 | $75.00 | $1.25 | — | $28.13 | ↗ |
| gpt-5.6-cyber | OpenAI | $12.50 | $75.00 | $1.25 | 400,000 | $28.13 | ↗ |
| claude-opus-4.1 | OpenRouter | $15.00 | $75.00 | $1.50 | 200,000 | $30.00 | ↗ |
| gpt-4 | OpenAI | $30.00 | $60.00 | — | 8,192 | $37.50 | ↗ |
Prices last checked: . Methodology
Vendors
Top price pages
The providers, GPUs, domains, models and comparisons people look up most.