Calculate LLM API Costs
Enter your monthly input and output token volume to evaluate costs across models.
Quick Ratio:
1,000,000 tokens
1,000,000 tokens
Note: Batch API or Cached Input pricing is shown where offered by the provider. Models without support are listed as "Not offered".
Model Cost Comparison
193 models Mode: standard · Input: 1,000,000 · Output: 1,000,000
| Provider | Model | Input (1M) | Output (1M) | Calc. Input Cost | Calc. Output Cost | Total Cost |
|---|---|---|---|---|---|---|
OpenAI | gpt-6-astra long context: $20.00 in / $75.00 out | $10.00 | $50.00 | $10.00 | $50.00 | $60.00 |
OpenAI | gpt-6.1-sol long context: $4.00 in / $15.00 out | $2.00 | $10.00 | $2.00 | $10.00 | $12.00 |
OpenAI | gpt-6-luna long context: $0.20 in / $0.75 out | $0.10 | $0.50 | $0.10 | $0.50 | $0.60 |
OpenAI | gpt-6-sol long context: $4.00 in / $15.00 out | $2.00 | $10.00 | $2.00 | $10.00 | $12.00 |
OpenAI | gpt-5.6-sol long context: $8.00 in / $30.00 out | $4.00 | $20.00 | $4.00 | $20.00 | $24.00 |
OpenAI | gpt-5.6-terra long context: $4.00 in / $18.00 out | $2.00 | $12.00 | $2.00 | $12.00 | $14.00 |
OpenAI | gpt-5.6-luna long context: $0.40 in / $1.80 out | $0.20 | $1.20 | $0.20 | $1.20 | $1.40 |
OpenAI | gpt-5.5 Prices for <272K context length; long context: $10.00 in / $45.00 out | $5.00 | $30.00 | $5.00 | $30.00 | $35.00 |
OpenAI | gpt-5.5-pro Prices for <272K context length; long context: $60.00 in / $270.00 out | $30.00 | $180.00 | $30.00 | $180.00 | $210.00 |
OpenAI | gpt-5.4 Prices for <272K context length; long context: $5.00 in / $22.50 out | $2.50 | $15.00 | $2.50 | $15.00 | $17.50 |
OpenAI | gpt-5.4-mini | $0.75 | $4.50 | $0.75 | $4.50 | $5.25 |
OpenAI | gpt-5.4-nano | $0.20 | $1.25 | $0.20 | $1.25 | $1.45 |
OpenAI | gpt-5.4-pro Prices for <272K context length; long context: $60.00 in / $270.00 out | $30.00 | $180.00 | $30.00 | $180.00 | $210.00 |
OpenAI | gpt-5.2 | $1.75 | $14.00 | $1.75 | $14.00 | $15.75 |
OpenAI | gpt-5.2-pro | $21.00 | $168.00 | $21.00 | $168.00 | $189.00 |
OpenAI | gpt-5.1 | $1.25 | $10.00 | $1.25 | $10.00 | $11.25 |
OpenAI | gpt-5 | $1.25 | $10.00 | $1.25 | $10.00 | $11.25 |
OpenAI | gpt-5-mini | $0.25 | $2.00 | $0.25 | $2.00 | $2.25 |
OpenAI | gpt-5-nano | $0.05 | $0.40 | $0.05 | $0.40 | $0.45 |
OpenAI | gpt-5-pro | $15.00 | $120.00 | $15.00 | $120.00 | $135.00 |
OpenAI | gpt-4.1 | $2.00 | $8.00 | $2.00 | $8.00 | $10.00 |
OpenAI | gpt-4.1-mini | $0.40 | $1.60 | $0.40 | $1.60 | $2.00 |
OpenAI | gpt-4.1-nano | $0.10 | $0.40 | $0.10 | $0.40 | $0.50 |
OpenAI | gpt-4o | $2.50 | $10.00 | $2.50 | $10.00 | $12.50 |
OpenAI | gpt-4o-2024-05-13 | $5.00 | $15.00 | $5.00 | $15.00 | $20.00 |
OpenAI | gpt-4o-mini | $0.15 | $0.60 | $0.15 | $0.60 | $0.75 |
OpenAI | o1 | $15.00 | $60.00 | $15.00 | $60.00 | $75.00 |
OpenAI | o1-pro | $150.00 | $600.00 | $150.00 | $600.00 | $750.00 |
OpenAI | o3-pro | $20.00 | $80.00 | $20.00 | $80.00 | $100.00 |
OpenAI | o3 | $2.00 | $8.00 | $2.00 | $8.00 | $10.00 |
OpenAI | o4-mini | $1.10 | $4.40 | $1.10 | $4.40 | $5.50 |
OpenAI | o3-mini | $1.10 | $4.40 | $1.10 | $4.40 | $5.50 |
OpenAI | gpt-4-turbo-2024-04-09 | $10.00 | $30.00 | $10.00 | $30.00 | $40.00 |
OpenAI | gpt-4-0613 | $30.00 | $60.00 | $30.00 | $60.00 | $90.00 |
OpenAI | gpt-3.5-turbo | $0.50 | $1.50 | $0.50 | $1.50 | $2.00 |
OpenAI | gpt-3.5-turbo-0125 | $0.50 | $1.50 | $0.50 | $1.50 | $2.00 |
OpenAI | gpt-3.5-turbo-1106 | $1.00 | $2.00 | $1.00 | $2.00 | $3.00 |
OpenAI | gpt-3.5-turbo-instruct | $1.50 | $2.00 | $1.50 | $2.00 | $3.50 |
OpenAI | davinci-002 | $2.00 | $2.00 | $2.00 | $2.00 | $4.00 |
OpenAI | babbage-002 | $0.40 | $0.40 | $0.40 | $0.40 | $0.80 |
OpenAI | gpt-5.6-cyber | $12.50 | $75.00 | $12.50 | $75.00 | $87.50 |
OpenAI | gpt-5.5-cyber | $12.50 | $75.00 | $12.50 | $75.00 | $87.50 |
OpenAI | chat-latest ChatGPT model | $5.00 | $30.00 | $5.00 | $30.00 | $35.00 |
OpenAI | gpt-5.3-codex Codex model | $1.75 | $14.00 | $1.75 | $14.00 | $15.75 |
OpenAI | gpt-5-search-api Search model | $1.25 | $10.00 | $1.25 | $10.00 | $11.25 |
Anthropic | Claude Fable 5.1 | $10.00 | $50.00 | $10.00 | $50.00 | $60.00 |
Anthropic | Claude Mythos 5.1 Limited availability | $10.00 | $50.00 | $10.00 | $50.00 | $60.00 |
Anthropic | Claude Fable 5 | $10.00 | $50.00 | $10.00 | $50.00 | $60.00 |
Anthropic | Claude Mythos 5 Limited availability | $10.00 | $50.00 | $10.00 | $50.00 | $60.00 |
Anthropic | Claude Opus 5 | $5.00 | $25.00 | $5.00 | $25.00 | $30.00 |
Anthropic | Claude Opus 4.8 | $5.00 | $25.00 | $5.00 | $25.00 | $30.00 |
Anthropic | Claude Opus 4.7 | $5.00 | $25.00 | $5.00 | $25.00 | $30.00 |
Anthropic | Claude Opus 4.6 | $5.00 | $25.00 | $5.00 | $25.00 | $30.00 |
Anthropic | Claude Opus 4.5 | $5.00 | $25.00 | $5.00 | $25.00 | $30.00 |
Anthropic | Claude Sonnet 5 | $2.00 | $10.00 | $2.00 | $10.00 | $12.00 |
Anthropic | Claude Sonnet 4.6 | $3.00 | $15.00 | $3.00 | $15.00 | $18.00 |
Anthropic | Claude Sonnet 4.5 | $3.00 | $15.00 | $3.00 | $15.00 | $18.00 |
Anthropic | Claude Haiku 4.5 | $1.00 | $5.00 | $1.00 | $5.00 | $6.00 |
Google Gemini | Gemini 3.8 Flash Through Dec 31, 2026; from Jan 1, 2027: $1.50 input, $7.50 output, $0.15 cached | $0.75 | $3.75 | $0.75 | $3.75 | $4.50 |
Google Gemini | Gemini 3.7 Flash Through Dec 31, 2026; from Jan 1, 2027: $1.50 input, $7.50 output, $0.15 cached | $0.75 | $3.75 | $0.75 | $3.75 | $4.50 |
Google Gemini | Gemini 3.6 Flash Through Dec 31, 2026; from Jan 1, 2027: $1.50 input, $7.50 output, $0.15 cached | $0.75 | $3.75 | $0.75 | $3.75 | $4.50 |
Google Gemini | Gemini 3.5 Flash | $1.50 | $9.00 | $1.50 | $9.00 | $10.50 |
Google Gemini | Gemini 3.5 Flash-Lite | $0.30 | $2.50 | $0.30 | $2.50 | $2.80 |
Google Gemini | Gemini 3.1 Flash-Lite Audio: $0.50 input, $0.05 cached | $0.25 | $1.50 | $0.25 | $1.50 | $1.75 |
Google Gemini | Gemini 3.1 Pro Preview Prompts ≤200K tokens; over 200K: $4.00 input, $18.00 output, $0.40 cached | $2.00 | $12.00 | $2.00 | $12.00 | $14.00 |
Google Gemini | Gemini 3 Flash Preview Audio: $1.00 input, $0.10 cached | $0.50 | $3.00 | $0.50 | $3.00 | $3.50 |
Google Gemini | Gemini 2.5 Pro Prompts ≤200K tokens; over 200K: $2.50 input, $15.00 output, $0.25 cached | $1.25 | $10.00 | $1.25 | $10.00 | $11.25 |
Google Gemini | Gemini 2.5 Flash Audio: $1.00 input, $0.10 cached | $0.30 | $2.50 | $0.30 | $2.50 | $2.80 |
Google Gemini | Gemini 2.5 Flash-Lite Audio: $0.30 input, $0.03 cached | $0.10 | $0.40 | $0.10 | $0.40 | $0.50 |
Grok (xAI) | Grok 4.7 Prompts < 200K tokens. At ≥ 200K the whole request bills $4.00 in / $1.00 cached / $12.00 out. | $2.00 | $6.00 | $2.00 | $6.00 | $8.00 |
Grok (xAI) | Grok 4.6 Prompts < 200K tokens. At ≥ 200K the whole request bills $4.00 in / $1.00 cached / $12.00 out. | $2.00 | $6.00 | $2.00 | $6.00 | $8.00 |
Grok (xAI) | Grok 4.5 Prompts < 200K tokens. At ≥ 200K the whole request bills $4.00 in / $0.60 cached / $12.00 out. | $2.00 | $6.00 | $2.00 | $6.00 | $8.00 |
Grok (xAI) | Grok 4.3 Prompts < 200K tokens. At ≥ 200K the whole request bills $2.50 in / $0.40 cached / $5.00 out. | $1.25 | $2.50 | $1.25 | $2.50 | $3.75 |
Grok (xAI) | Grok 4.20 Reasoning Prompts < 200K tokens. At ≥ 200K the whole request bills $2.50 in / $0.40 cached / $5.00 out. | $1.25 | $2.50 | $1.25 | $2.50 | $3.75 |
Grok (xAI) | Grok 4.20 Non-Reasoning Prompts < 200K tokens. At ≥ 200K the whole request bills $2.50 in / $0.40 cached / $5.00 out. | $1.25 | $2.50 | $1.25 | $2.50 | $3.75 |
Grok (xAI) | Grok Build 0.1 Prompts < 200K tokens. At ≥ 200K the whole request bills $2.00 in / $0.40 cached / $4.00 out. | $1.00 | $2.00 | $1.00 | $2.00 | $3.00 |
Grok (xAI) | Grok 4.20 Multi-Agent Prompts < 200K tokens. At ≥ 200K the whole request bills $2.50 in / $0.40 cached / $5.00 out. | $1.25 | $2.50 | $1.25 | $2.50 | $3.75 |
Mistral AI | Mistral Medium 3.5 | $1.50 | $7.50 | $1.50 | $7.50 | $9.00 |
Mistral AI | Mistral Small 4 | $0.15 | $0.60 | $0.15 | $0.60 | $0.75 |
Mistral AI | Mistral Large 3 | $0.50 | $1.50 | $0.50 | $1.50 | $2.00 |
Mistral AI | Codestral | $0.30 | $0.90 | $0.30 | $0.90 | $1.20 |
Mistral AI | Ministral 3 (3B) | $0.10 | $0.10 | $0.10 | $0.10 | $0.20 |
Mistral AI | Ministral 3 (8B) | $0.15 | $0.15 | $0.15 | $0.15 | $0.30 |
Mistral AI | Ministral 3 (14B) | $0.20 | $0.20 | $0.20 | $0.20 | $0.40 |
Cohere | Command A | $2.50 | $10.00 | $2.50 | $10.00 | $12.50 |
Cohere | Command R (08-2024) | $0.15 | $0.60 | $0.15 | $0.60 | $0.75 |
Cohere | Command R+ (08-2024) | $2.50 | $10.00 | $2.50 | $10.00 | $12.50 |
Cohere | Command R7B (12-2024) | $0.0375 | $0.15 | $0.0375 | $0.15 | $0.1875 |
DeepSeek | DeepSeek V4.1 Flash Peak price; off-peak is half (peak hours: 01:00-04:00 and 06:00-10:00 UTC, Monday through Friday, excluding Chinese public holidays). Legacy names deepseek-v4-flash, deepseek-v4-flash-vision-exp still work; those models are retired and bill at this price. | $0.30 | $1.20 | $0.30 | $1.20 | $1.50 |
DeepSeek | DeepSeek V4 Pro (0813) Peak price; off-peak is half (peak hours: 01:00-04:00 and 06:00-10:00 UTC, Monday through Friday, excluding Chinese public holidays). | $1.32 | $3.96 | $1.32 | $3.96 | $5.28 |
Qwen (Alibaba) | Qwen3.8 Max Singapore (international) rate; cache-hit rate is only shown in the console. | $2.00 | $6.00 | $2.00 | $6.00 | $8.00 |
Qwen (Alibaba) | Qwen3.7 Max Singapore (international) rate. | $2.50 | $7.50 | $2.50 | $7.50 | $10.00 |
Qwen (Alibaba) | Qwen3.6 Max Preview Singapore (international) rate; tiered by prompt length, ≤128K shown; 128K–256K $2.00 in / $12.00 out. | $1.30 | $7.80 | $1.30 | $7.80 | $9.10 |
Qwen (Alibaba) | Qwen3 Max Singapore (international) rate; tiered by prompt length, ≤32K shown; 32K–128K $2.40 in / $12.00 out; 128K–256K $3.00 in / $15.00 out. | $1.20 | $6.00 | $1.20 | $6.00 | $7.20 |
Qwen (Alibaba) | Qwen Max Singapore (international) rate. | $1.60 | $6.40 | $1.60 | $6.40 | $8.00 |
Qwen (Alibaba) | Qwen3.7 Plus Singapore (international) rate; tiered by prompt length, ≤256K shown; 256K–1M $1.20 in / $4.80 out; list price shown (limited-time 20% off running when read). | $0.40 | $1.60 | $0.40 | $1.60 | $2.00 |
Qwen (Alibaba) | Qwen3.6 Plus Singapore (international) rate; tiered by prompt length, ≤256K shown; 256K–1M $2.00 in / $6.00 out. | $0.50 | $3.00 | $0.50 | $3.00 | $3.50 |
Qwen (Alibaba) | Qwen3.5 Plus Singapore (international) rate; tiered by prompt length, ≤256K shown; 256K–1M $0.50 in / $3.00 out. | $0.40 | $2.40 | $0.40 | $2.40 | $2.80 |
Qwen (Alibaba) | Qwen Plus Singapore (international) rate; tiered by prompt length, ≤256K shown; 256K–1M $1.20 in / $3.60 out; thinking-mode output $4.00. | $0.40 | $1.20 | $0.40 | $1.20 | $1.60 |
Qwen (Alibaba) | Qwen3.8 Flash Singapore (international) rate; cache-hit rate is only shown in the console. | $0.15 | $0.47 | $0.15 | $0.47 | $0.62 |
Qwen (Alibaba) | Qwen3.7 Flash Singapore (international) rate; tiered by prompt length, ≤32K shown; 32K–256K $0.10 in / $0.40 out; 256K–1M $0.20 in / $0.80 out. | $0.03 | $0.13 | $0.03 | $0.13 | $0.16 |
Qwen (Alibaba) | Qwen3.6 Flash Singapore (international) rate; tiered by prompt length, ≤256K shown; 256K–1M $1.00 in / $4.00 out. | $0.25 | $1.50 | $0.25 | $1.50 | $1.75 |
Qwen (Alibaba) | Qwen3.5 Flash Singapore (international) rate. | $0.10 | $0.40 | $0.10 | $0.40 | $0.50 |
Qwen (Alibaba) | Qwen Flash Singapore (international) rate; tiered by prompt length, ≤256K shown; 256K–1M $0.25 in / $2.00 out. | $0.05 | $0.40 | $0.05 | $0.40 | $0.45 |
Qwen (Alibaba) | Qwen Turbo Singapore (international) rate; thinking-mode output $0.50. | $0.05 | $0.20 | $0.05 | $0.20 | $0.25 |
Qwen (Alibaba) | QwQ Plus Singapore (international) rate. | $0.80 | $2.40 | $0.80 | $2.40 | $3.20 |
Qwen (Alibaba) | Qwen3 Coder Plus Singapore (international) rate; tiered by prompt length, ≤32K shown; 32K–128K $1.80 in / $9.00 out; 128K–256K $3.00 in / $15.00 out; 256K–1M $6.00 in / $60.00 out. | $1.00 | $5.00 | $1.00 | $5.00 | $6.00 |
Qwen (Alibaba) | Qwen3 Coder Flash Singapore (international) rate; tiered by prompt length, ≤32K shown; 32K–128K $0.50 in / $2.50 out; 128K–256K $0.80 in / $4.00 out; 256K–1M $1.60 in / $9.60 out. | $0.30 | $1.50 | $0.30 | $1.50 | $1.80 |
Qwen (Alibaba) | Qwen3.8 2.4T A95B Singapore (international) rate; cache-hit rate is only shown in the console. | $2.00 | $6.00 | $2.00 | $6.00 | $8.00 |
Qwen (Alibaba) | Qwen3.8 27B Singapore (international) rate. | $0.50 | $3.00 | $0.50 | $3.00 | $3.50 |
Qwen (Alibaba) | Qwen3.6 35B A3B Singapore (international) rate. | $0.375 | $2.25 | $0.375 | $2.25 | $2.63 |
Qwen (Alibaba) | Qwen3.6 27B Singapore (international) rate. | $0.60 | $3.60 | $0.60 | $3.60 | $4.20 |
Qwen (Alibaba) | Qwen3.5 397B A17B Singapore (international) rate. | $0.60 | $3.60 | $0.60 | $3.60 | $4.20 |
Qwen (Alibaba) | Qwen3.5 122B A10B Singapore (international) rate. | $0.40 | $3.20 | $0.40 | $3.20 | $3.60 |
Qwen (Alibaba) | Qwen3.5 27B Singapore (international) rate. | $0.30 | $2.40 | $0.30 | $2.40 | $2.70 |
Qwen (Alibaba) | Qwen3.5 35B A3B Singapore (international) rate. | $0.25 | $2.00 | $0.25 | $2.00 | $2.25 |
Qwen (Alibaba) | Qwen3 Next 80B A3B Thinking Singapore (international) rate. | $0.15 | $1.20 | $0.15 | $1.20 | $1.35 |
Qwen (Alibaba) | Qwen3 Next 80B A3B Instruct Singapore (international) rate. | $0.15 | $1.20 | $0.15 | $1.20 | $1.35 |
Qwen (Alibaba) | Qwen3 235B A22B Thinking 2507 Singapore (international) rate. | $0.23 | $2.30 | $0.23 | $2.30 | $2.53 |
Qwen (Alibaba) | Qwen3 235B A22B Instruct 2507 Singapore (international) rate. | $0.23 | $0.92 | $0.23 | $0.92 | $1.15 |
Qwen (Alibaba) | Qwen3 30B A3B Thinking 2507 Singapore (international) rate. | $0.20 | $2.40 | $0.20 | $2.40 | $2.60 |
Qwen (Alibaba) | Qwen3 30B A3B Instruct 2507 Singapore (international) rate. | $0.20 | $0.80 | $0.20 | $0.80 | $1.00 |
Qwen (Alibaba) | Qwen3 235B A22B Singapore (international) rate; thinking-mode output $8.40. | $0.70 | $2.80 | $0.70 | $2.80 | $3.50 |
Qwen (Alibaba) | Qwen3 32B Singapore (international) rate. | $0.16 | $0.64 | $0.16 | $0.64 | $0.80 |
Qwen (Alibaba) | Qwen3 30B A3B Singapore (international) rate; thinking-mode output $2.40. | $0.20 | $0.80 | $0.20 | $0.80 | $1.00 |
Qwen (Alibaba) | Qwen3 14B Singapore (international) rate; thinking-mode output $4.20. | $0.35 | $1.40 | $0.35 | $1.40 | $1.75 |
Qwen (Alibaba) | Qwen3 8B Singapore (international) rate; thinking-mode output $2.10. | $0.18 | $0.70 | $0.18 | $0.70 | $0.88 |
Qwen (Alibaba) | Qwen3 Coder Next Singapore (international) rate; tiered by prompt length, ≤32K shown; 32K–128K $0.50 in / $2.50 out; 128K–256K $0.80 in / $4.00 out. | $0.30 | $1.50 | $0.30 | $1.50 | $1.80 |
Qwen (Alibaba) | Qwen3 Coder 480B A35B Instruct Singapore (international) rate; tiered by prompt length, ≤32K shown; 32K–128K $2.70 in / $13.50 out; 128K–200K $4.50 in / $22.50 out. | $1.50 | $7.50 | $1.50 | $7.50 | $9.00 |
Qwen (Alibaba) | Qwen3 Coder 30B A3B Instruct Singapore (international) rate; tiered by prompt length, ≤32K shown; 32K–128K $0.75 in / $3.75 out; 128K–200K $1.20 in / $6.00 out. | $0.45 | $2.25 | $0.45 | $2.25 | $2.70 |
Groq | GPT OSS 120B | $0.15 | $0.60 | $0.15 | $0.60 | $0.75 |
Groq | GPT OSS 20B | $0.075 | $0.30 | $0.075 | $0.30 | $0.375 |
Groq | Qwen/Qwen3.8-27B Preview model | $0.80 | $4.00 | $0.80 | $4.00 | $4.80 |
AWS Bedrock | Claude Opus 4.7 (Anthropic) Global cross-region endpoint; regional endpoints cost 10% more | $5.00 | $25.00 | $5.00 | $25.00 | $30.00 |
AWS Bedrock | Claude Sonnet 5 (Anthropic) Global cross-region endpoint; regional endpoints cost 10% more | $2.00 | $10.00 | $2.00 | $10.00 | $12.00 |
AWS Bedrock | Claude Sonnet 4.6 (Anthropic) Global cross-region endpoint; regional endpoints cost 10% more | $3.00 | $15.00 | $3.00 | $15.00 | $18.00 |
AWS Bedrock | Claude Haiku 4.5 (Anthropic) Global cross-region endpoint; regional endpoints cost 10% more | $1.00 | $5.00 | $1.00 | $5.00 | $6.00 |
AWS Bedrock | Nova 2.0 Lite (Amazon) In-region rate. Global cross-region: $0.30 in / $2.50 out | $0.33 | $2.75 | $0.33 | $2.75 | $3.08 |
AWS Bedrock | Nova 2.0 Omni (Amazon) In-region rate. Global cross-region: $0.30 in / $2.50 out | $0.30 | $2.80 | $0.30 | $2.80 | $3.10 |
AWS Bedrock | Nova 2.0 Pro (Amazon) In-region rate. Global cross-region: $1.25 in / $10.00 out | $1.38 | $11.00 | $1.38 | $11.00 | $12.38 |
AWS Bedrock | Nova Lite (Amazon) | $0.06 | $0.24 | $0.06 | $0.24 | $0.30 |
AWS Bedrock | Nova Micro (Amazon) | $0.035 | $0.14 | $0.035 | $0.14 | $0.175 |
AWS Bedrock | Nova Premier (Amazon) | $2.50 | $12.50 | $2.50 | $12.50 | $15.00 |
AWS Bedrock | Nova Pro (Amazon) | $0.80 | $3.20 | $0.80 | $3.20 | $4.00 |
AWS Bedrock | DeepSeek R1 | $1.35 | $5.40 | $1.35 | $5.40 | $6.75 |
AWS Bedrock | DeepSeek V3.1 | $0.58 | $1.68 | $0.58 | $1.68 | $2.26 |
AWS Bedrock | DeepSeek V3.2 | $0.62 | $1.85 | $0.62 | $1.85 | $2.47 |
AWS Bedrock | Gemma 3 12B (Google) | $0.09 | $0.29 | $0.09 | $0.29 | $0.38 |
AWS Bedrock | Gemma 3 27B (Google) | $0.23 | $0.38 | $0.23 | $0.38 | $0.61 |
AWS Bedrock | Gemma 3 4B (Google) | $0.04 | $0.08 | $0.04 | $0.08 | $0.12 |
AWS Bedrock | Gemma 4 26B A4B (Google) | $0.13 | $0.40 | $0.13 | $0.40 | $0.53 |
AWS Bedrock | Gemma 4 31B (Google) | $0.14 | $0.40 | $0.14 | $0.40 | $0.54 |
AWS Bedrock | Gemma 4 E2B (Google) | $0.04 | $0.08 | $0.04 | $0.08 | $0.12 |
AWS Bedrock | Llama 3.1 70B (Meta) | $0.72 | $0.72 | $0.72 | $0.72 | $1.44 |
AWS Bedrock | Llama 3.1 8B (Meta) | $0.22 | $0.22 | $0.22 | $0.22 | $0.44 |
AWS Bedrock | Llama 3.2 11B (Meta) | $0.16 | $0.16 | $0.16 | $0.16 | $0.32 |
AWS Bedrock | Llama 3.2 1B (Meta) | $0.10 | $0.10 | $0.10 | $0.10 | $0.20 |
AWS Bedrock | Llama 3.2 3B (Meta) | $0.15 | $0.15 | $0.15 | $0.15 | $0.30 |
AWS Bedrock | Llama 3.2 90B (Meta) | $0.72 | $0.72 | $0.72 | $0.72 | $1.44 |
AWS Bedrock | Llama 3.3 70B (Meta) | $0.72 | $0.72 | $0.72 | $0.72 | $1.44 |
AWS Bedrock | Llama 4 Maverick 17B (Meta) | $0.24 | $0.97 | $0.24 | $0.97 | $1.21 |
AWS Bedrock | Llama 4 Scout 17B (Meta) | $0.17 | $0.66 | $0.17 | $0.66 | $0.83 |
AWS Bedrock | MiniMax M2 | $0.30 | $1.20 | $0.30 | $1.20 | $1.50 |
AWS Bedrock | MiniMax M2.1 | $0.30 | $1.20 | $0.30 | $1.20 | $1.50 |
AWS Bedrock | MiniMax M2.5 | $0.30 | $1.20 | $0.30 | $1.20 | $1.50 |
AWS Bedrock | Devstral 2 123B (Mistral AI) | $0.40 | $2.00 | $0.40 | $2.00 | $2.40 |
AWS Bedrock | Mistral Large 3 | $0.50 | $1.50 | $0.50 | $1.50 | $2.00 |
AWS Bedrock | Magistral Small 1.2 (Mistral AI) | $0.50 | $1.50 | $0.50 | $1.50 | $2.00 |
AWS Bedrock | Ministral 14B 3.0 (Mistral AI) | $0.20 | $0.20 | $0.20 | $0.20 | $0.40 |
AWS Bedrock | Ministral 3B 3.0 (Mistral AI) | $0.10 | $0.10 | $0.10 | $0.10 | $0.20 |
AWS Bedrock | Ministral 8B 3.0 (Mistral AI) | $0.15 | $0.15 | $0.15 | $0.15 | $0.30 |
AWS Bedrock | Pixtral Large 25.02 (Mistral AI) | $2.00 | $6.00 | $2.00 | $6.00 | $8.00 |
AWS Bedrock | Kimi K2 Thinking (Moonshot AI) | $0.60 | $2.50 | $0.60 | $2.50 | $3.10 |
AWS Bedrock | Kimi K2.5 (Moonshot AI) | $0.60 | $3.00 | $0.60 | $3.00 | $3.60 |
AWS Bedrock | NVIDIA Nemotron 3 Super 120B A12B | $0.15 | $0.65 | $0.15 | $0.65 | $0.80 |
AWS Bedrock | NVIDIA Nemotron Nano 2 | $0.06 | $0.23 | $0.06 | $0.23 | $0.29 |
AWS Bedrock | NVIDIA Nemotron Nano 2 VL | $0.20 | $0.60 | $0.20 | $0.60 | $0.80 |
AWS Bedrock | NVIDIA Nemotron Nano 3 30B | $0.06 | $0.24 | $0.06 | $0.24 | $0.30 |
AWS Bedrock | gpt-oss-120b (OpenAI) | $0.15 | $0.60 | $0.15 | $0.60 | $0.75 |
AWS Bedrock | gpt-oss-20b (OpenAI) | $0.07 | $0.30 | $0.07 | $0.30 | $0.37 |
AWS Bedrock | Qwen3 235B A22B 2507 | $0.22 | $0.88 | $0.22 | $0.88 | $1.10 |
AWS Bedrock | Qwen3 32B | $0.15 | $0.60 | $0.15 | $0.60 | $0.75 |
AWS Bedrock | Qwen3 Coder 30B A3B | $0.15 | $0.60 | $0.15 | $0.60 | $0.75 |
AWS Bedrock | Qwen3 Coder 480B A35B | $0.45 | $1.80 | $0.45 | $1.80 | $2.25 |
AWS Bedrock | Qwen3 Coder Next | $0.50 | $1.20 | $0.50 | $1.20 | $1.70 |
AWS Bedrock | Qwen3 Next 80B A3B | $0.14 | $1.20 | $0.14 | $1.20 | $1.34 |
AWS Bedrock | Qwen3 VL 235B A22B | $0.53 | $2.66 | $0.53 | $2.66 | $3.19 |
AWS Bedrock | Writer Palmyra Vision 7B | $0.15 | $0.60 | $0.15 | $0.60 | $0.75 |
AWS Bedrock | Grok 4.3 (xAI) | $1.25 | $2.50 | $1.25 | $2.50 | $3.75 |
AWS Bedrock | Grok 4.6 (xAI) In-region rate. Global cross-region: $2.00 in / $6.00 out | $2.20 | $6.60 | $2.20 | $6.60 | $8.80 |
AWS Bedrock | GLM 4.7 (Z.ai) | $0.60 | $2.20 | $0.60 | $2.20 | $2.80 |
AWS Bedrock | GLM 4.7 Flash (Z.ai) | $0.07 | $0.40 | $0.07 | $0.40 | $0.47 |
AWS Bedrock | GLM 5 (Z.ai) | $1.00 | $3.20 | $1.00 | $3.20 | $4.20 |
HOW TO USE THIS CALCULATOR
Estimate your LLM bill in three steps
1
Set token volume
Enter expected input/prompt tokens and output/completion tokens per month or use quick presets to model your workload scale.
2
Choose provider & mode
Filter by specific AI providers or toggle between Standard, Batch API, and Prompt Caching to evaluate discount structures.
3
Compare & decision
Review total calculated costs across 100+ AI models side-by-side to choose the optimal price-to-performance model for your product.
COST DRIVERS
What drives your LLM API bill
Input vs Output token ratio
Output tokens are priced 3x to 4x higher than input tokens across almost every provider. Minimizing verbose output instructions directly lowers costs.
Batch API & Prompt Caching
Batch API processing usually cuts the rate by half for non-realtime jobs (xAI discounts 20%), while Prompt Caching cuts input cost up to 75-90% for repeated system prompts.
Model class & parameter size
Flagship reasoning models cost significantly more per token than lightweight small language models (SLMs) like Gemini Flash, GPT-4o-mini, or Claude Haiku.
Hosting provider & tiering
API rates vary between direct providers (OpenAI, Anthropic) and hyperscaler deployments (AWS Bedrock, GCP Vertex AI), especially when enterprise commitments apply.
DATA SOURCES & METHODOLOGY
Where every price came from
OpenAI
Verified Checked October 14, 2026 Source page
Anthropic
Verified Checked September 10, 2026 Source page
Google Gemini
Verified Checked September 10, 2026 Source page
Grok (xAI)
Verified Checked October 14, 2026 Source page
Mistral AI
Verified Checked September 10, 2026 Source page
Cohere
Verified Checked October 14, 2026 Source page
DeepSeek
Verified Checked October 14, 2026 Source page
Qwen (Alibaba)
Verified Checked September 10, 2026 Source page
Groq
Verified Checked October 14, 2026 Source page
AWS Bedrock
Verified Checked September 1, 2026 Source page
FREQUENTLY ASKED QUESTIONS
LLM API pricing questions
How are LLM API costs calculated?
LLM API costs are calculated per million tokens. The total cost is (Input Tokens × Input Rate / 1,000,000) + (Output Tokens × Output Rate / 1,000,000). Output tokens are typically priced 3x to 4x higher than input tokens.
What is Batch API pricing and how much can I save?
How does Prompt Caching work for LLMs?
Why are output tokens more expensive than input tokens?
Are AWS Bedrock rates identical to direct provider rates?
How often are these LLM API rates updated?
Start with AWS 
Start with GCP 
Start with Azure