Llama 3.3 Euryale 70B pricing
$0.65 per 1M input tokens and $0.75 per 1M output tokens. In real work that is 0.13¢ per chat answer and 1.1¢ to summarize a 20-page PDF.
What Llama 3.3 Euryale 70B 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 | 0.13¢$1.26 / 1,000 | 88 in · 689 out · 909 reasoning | 122 of 336 | estimated |
| Reply to a customer email | 0.07¢$0.73 / 1,000 | 326 in · 98 out · 587 reasoning | 136 of 336 | estimated |
| Write a 1,500-word blog post | ≥1.2¢$12.07 / 1,000 | 104 in · 0 out · 16,000 reasoning | 199 of 336 | estimated |
| Write 10 product descriptions | ≥1.2¢$12.22 / 1,000 | 345 in · 0 out · 16,000 reasoning | 225 of 336 | estimated |
| Translate 1,000 words | 0.19¢$1.88 / 1,000 | 1,386 in · 1,166 out · 136 reasoning | 98 of 336 | estimated |
| Proofread one page (500 words) | 0.19¢$1.88 / 1,000 | 777 in · 671 out · 1,159 reasoning | 145 of 336 | estimated |
| Summarize a 20-page PDF | 1.1¢$10.51 / 1,000 | 13,119 in · 501 out · 2,141 reasoning | 189 of 336 | estimated |
| Extract data from an invoice | 0.20¢$1.96 / 1,000 | 501 in · 561 out · 1,617 reasoning | 153 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥1.6¢$16.13 / 1,000 | 6,357 in · 0 out · 16,000 reasoning | 140 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.46¢$4.60 / 1,000 | 3,751 in · 974 out · 1,912 reasoning | 164 of 336 | estimated |
| Classify 100 support tickets | 0.73¢$7.26 / 1,000 | 1,463 in · 534 out · 7,879 reasoning | 178 of 336 | estimated |
| Review 500 lines of code | ≥1.5¢$15.17 / 1,000 | 4,874 in · 0 out · 16,000 reasoning | 183 of 336 | estimated |
| Write a SQL query | 0.21¢$2.09 / 1,000 | 177 in · 405 out · 2,225 reasoning | 162 of 336 | estimated |
| Run a 50-step coding agent | $1.54$1,541 / 1,000 | 2,259,875 in · 15,150 out · 80,850 reasoning | 267 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Llama 3.3 Euryale 70B through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| N NextBitbf16 | $0.65 / $0.75 | - | 131K | 100% |
Price history
First seen in our price history on Jan 17, 2025 at $0.70 input / $0.80 output. Since then the output price moved from $0.80 to $0.75 per 1M tokens (1 change).
FAQ
How much does Llama 3.3 Euryale 70B cost?
Llama 3.3 Euryale 70B costs $0.65 per 1 million input tokens and $0.75 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.13¢ and summarizing a 20-page PDF about 1.1¢.
Where is Llama 3.3 Euryale 70B cheapest?
Among 1 providers we track, the lowest list price today is at NextBit: $0.65 input and $0.75 output per 1M tokens.
Is the Llama 3.3 Euryale 70B cost per task measured or estimated?
Estimated: Llama 3.3 Euryale 70B was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Sao10K. Real usage can differ.