Metaopen weightsLlama 4 Maverick pricing
$0.19 per 1M input tokens and $0.65 per 1M output tokens. In real work that is 0.11¢ per chat answer and 0.42¢ to summarize a 20-page PDF.
What Llama 4 Maverick 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 | 0.11¢$1.06 / 1,000 | 87 in · 683 out · 909 reasoning | 105 of 336 | estimated |
| Reply to a customer email | 0.05¢$0.51 / 1,000 | 323 in · 97 out · 587 reasoning | 106 of 336 | estimated |
| Write a 1,500-word blog post | ≥1.0¢$10.46 / 1,000 | 103 in · 0 out · 16,000 reasoning | 189 of 336 | estimated |
| Write 10 product descriptions | ≥1.1¢$10.50 / 1,000 | 342 in · 0 out · 16,000 reasoning | 212 of 336 | estimated |
| Translate 1,000 words | 0.11¢$1.10 / 1,000 | 1,375 in · 1,156 out · 136 reasoning | 72 of 336 | estimated |
| Proofread one page (500 words) | 0.13¢$1.33 / 1,000 | 770 in · 665 out · 1,159 reasoning | 116 of 336 | estimated |
| Summarize a 20-page PDF | 0.42¢$4.16 / 1,000 | 13,015 in · 497 out · 2,141 reasoning | 113 of 336 | estimated |
| Extract data from an invoice | 0.15¢$1.51 / 1,000 | 497 in · 556 out · 1,617 reasoning | 134 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥1.2¢$11.62 / 1,000 | 6,306 in · 0 out · 16,000 reasoning | 116 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.26¢$2.58 / 1,000 | 3,721 in · 966 out · 1,912 reasoning | 114 of 336 | estimated |
| Classify 100 support tickets | 0.58¢$5.76 / 1,000 | 1,451 in · 529 out · 7,879 reasoning | 157 of 336 | estimated |
| Review 500 lines of code | ≥1.1¢$11.35 / 1,000 | 4,835 in · 0 out · 16,000 reasoning | 159 of 336 | estimated |
| Write a SQL query | 0.17¢$1.75 / 1,000 | 175 in · 401 out · 2,225 reasoning | 141 of 336 | estimated |
| Run a 50-step coding agent | 19¢$186 / 1,000 | 2,241,975 in · 15,030 out · 80,850 reasoning | 92 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Llama 4 Maverick through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| D DigitalOceanunknown | $0.19 / $0.65 | $0.05 | 128K | 100% |
 Novitafp8 | $0.27 / $0.85 | - | 1M | 100% |
 Parasailfp8 | $0.35 / $1.00 | $0.17 | 524K | 100% |
 Googleunknown | $0.35 / $1.15 | - | 524K |
Price history
First seen in our price history on Apr 10, 2025 at $0.19 input / $0.85 output. Since then the output price moved from $0.85 to $0.65 per 1M tokens (13 changes).
FAQ
How much does Llama 4 Maverick cost?
Llama 4 Maverick costs $0.19 per 1 million input tokens and $0.65 per 1 million output tokens, with cached input at $0.05 (list price on Oct 18, 2026). In practice one chat answer costs about 0.11¢ and summarizing a 20-page PDF about 0.42¢.
Where is Llama 4 Maverick cheapest?
Among 4 providers we track, the lowest list price today is at DigitalOcean: $0.19 input and $0.65 output per 1M tokens.
Is the Llama 4 Maverick cost per task measured or estimated?
Estimated: Llama 4 Maverick was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Meta. Real usage can differ.