Input and output cost per 1M tokens for every major model across all providers. Compare, filter, and calculate your monthly LLM spend.
| Provider ↕ | Model ↕ | Context ↕ | Type ↕ | Input / 1M tokens ↑ | Output / 1M tokens ↕ | Out/In ratio |
|---|---|---|---|---|---|---|
Amazon | Nova Micro | 128K | chat | $0.035 | $0.140 | 4.0× |
Meta | Llama 3.1 8B | 128K | chat | $0.055 | $0.055 | 1.0× |
Amazon | Nova Lite | 300K | chat | $0.060 | $0.240 | 4.0× |
Google | Gemini 1.5 Flash | 1M | chat | $0.075 | $0.300 | 4.0× |
OpenAI | GPT-4.1 nanoNEW | 1M | chat | $0.100 | $0.400 | 4.0× |
Google | Gemini 2.0 FlashNEW | 1M | chat | $0.100 | $0.400 | 4.0× |
Mistral | Mistral Small 3NEW | 32K | chat | $0.100 | $0.300 | 3.0× |
Meta | Llama 4 ScoutNEW | 10M | chat | $0.110 | $0.340 | 3.1× |
DeepSeek | DeepSeek V3 | 64K | chat | $0.140 | $0.280 | 2.0× |
DeepSeek | DeepSeek V2.5 | 128K | chat | $0.140 | $0.280 | 2.0× |
OpenAI | GPT-4o mini | 128K | chat | $0.150 | $0.600 | 4.0× |
Cohere | Command R | 128K | chat | $0.150 | $0.600 | 4.0× |
Meta | Llama 4 MaverickNEW | 1M | chat | $0.190 | $0.850 | 4.5× |
Mistral | Codestral | 32K | code | $0.200 | $0.600 | 3.0× |
xAI | Grok-2 Mini | 131K | chat | $0.200 | $1.00 | 5.0× |
Meta | Llama 3.3 70B | 128K | chat | $0.230 | $0.400 | 1.7× |
Anthropic | Claude 3 Haiku | 200K | chat | $0.250 | $1.25 | 5.0× |
Mistral | Mistral 7B | 32K | chat | $0.250 | $0.250 | 1.0× |
xAI | Grok-3 MiniNEW | 131K | reasoning | $0.300 | $0.500 | 1.7× |
OpenAI | GPT-4.1 miniNEW | 1M | chat | $0.400 | $1.60 | 4.0× |
OpenAI | GPT-3.5 Turbo | 16K | chat | $0.500 | $1.50 | 3.0× |
Google | Gemini 1.0 Pro | 32K | chat | $0.500 | $1.50 | 3.0× |
Meta | Llama 3.1 70B | 128K | chat | $0.520 | $0.750 | 1.4× |
DeepSeek | DeepSeek R1 | 64K | reasoning | $0.550 | $2.19 | 4.0× |
Anthropic | Claude 3.5 Haiku | 200K | chat | $0.800 | $4.00 | 5.0× |
Amazon | Nova Pro | 300K | chat | $0.800 | $3.20 | 4.0× |
OpenAI | o1-mini | 128K | reasoning | $1.10 | $4.40 | 4.0× |
OpenAI | o3-miniNEW | 200K | reasoning | $1.10 | $4.40 | 4.0× |
OpenAI | o4-miniNEW | 200K | reasoning | $1.10 | $4.40 | 4.0× |
Mistral | Mixtral 8x22B | 64K | chat | $1.20 | $1.20 | 1.0× |
Google | Gemini 2.5 ProNEW | 1M | reasoning | $1.25 | $10.00 | 8.0× |
Google | Gemini 1.5 Pro | 2M | chat | $1.25 | $5.00 | 4.0× |
OpenAI | GPT-4.1NEW | 1M | chat | $2.00 | $8.00 | 4.0× |
Mistral | Mistral Large 2 | 128K | chat | $2.00 | $6.00 | 3.0× |
xAI | Grok-2 | 131K | chat | $2.00 | $10.00 | 5.0× |
OpenAI | GPT-4o | 128K | chat | $2.50 | $10.00 | 4.0× |
Cohere | Command R+ | 128K | chat | $2.50 | $10.00 | 4.0× |
Cohere | Command ANEW | 256K | chat | $2.50 | $10.00 | 4.0× |
Meta | Llama 3.1 405B | 128K | chat | $2.70 | $2.70 | 1.0× |
Anthropic | Claude 3.5 Sonnet | 200K | chat | $3.00 | $15.00 | 5.0× |
Anthropic | Claude 3 Sonnet | 200K | chat | $3.00 | $15.00 | 5.0× |
Anthropic | Claude 3.7 SonnetNEW | 200K | reasoning | $3.00 | $15.00 | 5.0× |
Anthropic | Claude 4 SonnetNEW | 200K | chat | $3.00 | $15.00 | 5.0× |
xAI | Grok-3NEW | 131K | chat | $3.00 | $15.00 | 5.0× |
OpenAI | GPT-4 Turbo | 128K | chat | $10.00 | $30.00 | 3.0× |
OpenAI | o3NEW | 200K | reasoning | $10.00 | $40.00 | 4.0× |
OpenAI | o1 | 200K | reasoning | $15.00 | $60.00 | 4.0× |
Anthropic | Claude 3 Opus | 200K | chat | $15.00 | $75.00 | 5.0× |
OpenAI | GPT-4 | 8K | chat | $30.00 | $60.00 | 2.0× |
Adjust the sliders to estimate your real monthly LLM bill based on token usage and call volume.
Tokflo tells you whether those tokens are generating a return. Not just what it costs — what it's worth. VPT, TCC, and Margin At Risk alerts built in.
Free to start · No credit card · Tokflo is in early access
Tokflo wraps your LLM client in 2 lines of code and tells you Value-per-Token, Margin at Risk, and Task Completion Cost — metrics that don't exist in any other tool.
Pricing data sourced from official provider documentation and API pricing pages. Updated within 48 hours of any change. All prices in USD per 1M tokens. Prices may vary by region, volume, or API tier. tokflo.dev