Weaver (alpha) pricing
$0.40 per 1M input tokens and $0.75 per 1M output tokens. In real work that is 0.12¢ per chat answer and 0.72¢ to summarize a 20-page PDF.
What Weaver (alpha) 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 | 0.12¢$1.23 / 1,000 | 88 in · 689 out · 909 reasoning | 119 of 336 | estimated |
| Reply to a customer email | 0.06¢$0.64 / 1,000 | 326 in · 98 out · 587 reasoning | 126 of 336 | estimated |
| Write a 1,500-word blog post | ≥1.2¢$12.04 / 1,000 | 104 in · 0 out · 16,000 reasoning | 198 of 336 | estimated |
| Write 10 product descriptions | ≥1.2¢$12.14 / 1,000 | 345 in · 0 out · 16,000 reasoning | 224 of 336 | estimated |
| Translate 1,000 words | 0.15¢$1.53 / 1,000 | 1,386 in · 1,166 out · 136 reasoning | 85 of 336 | estimated |
| Proofread one page (500 words) | 0.17¢$1.68 / 1,000 | 777 in · 671 out · 1,159 reasoning | 137 of 336 | estimated |
| Summarize a 20-page PDF | 0.72¢$7.23 / 1,000 | 13,119 in · 501 out · 2,141 reasoning | 160 of 336 | estimated |
| Extract data from an invoice | 0.18¢$1.83 / 1,000 | 501 in · 561 out · 1,617 reasoning | 148 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥1.5¢$14.54 / 1,000 | 6,357 in · 0 out · 16,000 reasoning | 129 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.37¢$3.66 / 1,000 | 3,751 in · 974 out · 1,912 reasoning | 143 of 336 | estimated |
| Classify 100 support tickets | 0.69¢$6.89 / 1,000 | 1,463 in · 534 out · 7,879 reasoning | 171 of 336 | estimated |
| Review 500 lines of code | ≥1.4¢$13.95 / 1,000 | 4,874 in · 0 out · 16,000 reasoning | 178 of 336 | estimated |
| Write a SQL query | 0.20¢$2.04 / 1,000 | 177 in · 405 out · 2,225 reasoning | 160 of 336 | estimated |
| Run a 50-step coding agent | 98¢$976 / 1,000 | 2,259,875 in · 15,150 out · 80,850 reasoning | 234 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Weaver (alpha) through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| M Mancer 2fp8 | $0.40 / $0.75 | - | 8K |
Price history
First seen in our price history on Mar 26, 2024 at $3.38 input / $3.38 output. Since then the output price moved from $3.38 to $0.75 per 1M tokens (9 changes).
FAQ
How much does Weaver (alpha) cost?
Weaver (alpha) costs $0.40 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 0.12¢ and summarizing a 20-page PDF about 0.72¢.
Where is Weaver (alpha) cheapest?
Among 1 providers we track, the lowest list price today is at Mancer 2: $0.40 input and $0.75 output per 1M tokens.
Is the Weaver (alpha) cost per task measured or estimated?
Estimated: Weaver (alpha) was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Mancer. Real usage can differ.