Metaopen weightsLlama Guard 4 12B pricing
$0.18 per 1M input tokens and $0.18 per 1M output tokens. In real work that is 0.03¢ per chat answer and 0.28¢ to summarize a 20-page PDF.
What Llama Guard 4 12B costs per task
Token counts estimated from a measured model of the same lab (Qwen3.8 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.03¢$0.30 / 1,000 | 87 in · 683 out · 909 reasoning | 29 of 336 | estimated |
| Reply to a customer email | 0.02¢$0.18 / 1,000 | 323 in · 97 out · 587 reasoning | 47 of 336 | estimated |
| Write a 1,500-word blog post | ≥0.29¢$2.90 / 1,000 | 103 in · 0 out · 16,000 reasoning | 89 of 336 | estimated |
| Write 10 product descriptions | ≥0.29¢$2.94 / 1,000 | 342 in · 0 out · 16,000 reasoning | 106 of 336 | estimated |
| Translate 1,000 words | 0.05¢$0.48 / 1,000 | 1,375 in · 1,156 out · 136 reasoning | 33 of 336 | estimated |
| Proofread one page (500 words) | 0.05¢$0.47 / 1,000 | 770 in · 665 out · 1,159 reasoning | 47 of 336 | estimated |
| Summarize a 20-page PDF | 0.28¢$2.82 / 1,000 | 13,015 in · 497 out · 2,141 reasoning | 84 of 336 | estimated |
| Extract data from an invoice | 0.05¢$0.48 / 1,000 | 497 in · 556 out · 1,617 reasoning | 48 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥0.40¢$4.02 / 1,000 | 6,306 in · 0 out · 16,000 reasoning | 53 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.12¢$1.19 / 1,000 | 3,721 in · 966 out · 1,912 reasoning | 72 of 336 | estimated |
| Classify 100 support tickets | 0.18¢$1.77 / 1,000 | 1,451 in · 529 out · 7,879 reasoning | 63 of 336 | estimated |
| Review 500 lines of code | ≥0.38¢$3.75 / 1,000 | 4,835 in · 0 out · 16,000 reasoning | 55 of 336 | estimated |
| Write a SQL query | 0.05¢$0.50 / 1,000 | 175 in · 401 out · 2,225 reasoning | 45 of 336 | estimated |
| Run a 50-step coding agent | 42¢$421 / 1,000 | 2,241,975 in · 15,030 out · 80,850 reasoning | 156 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Llama Guard 4 12B through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 DeepInfrabf16 | $0.14 / $0.14 | - | 163K | |
DeepInfrabf16 | $0.18 / $0.18 | - | 163K | 100% |
DeepInfrabf16 | $0.27 / $0.27 | - | 163K | 100% |
Price history
First seen in our price history on May 3, 2025 at $0.05 input / $0.05 output. Since then the output price moved from $0.05 to $0.18 per 1M tokens (1 change).
FAQ
How much does Llama Guard 4 12B cost?
Llama Guard 4 12B costs $0.18 per 1 million input tokens and $0.18 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.03¢ and summarizing a 20-page PDF about 0.28¢.
Where is Llama Guard 4 12B cheapest?
Among 3 providers we track, the lowest list price today is at DeepInfra: $0.14 input and $0.14 output per 1M tokens.
Is the Llama Guard 4 12B cost per task measured or estimated?
Estimated: Llama Guard 4 12B was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Meta. Real usage can differ.