Inkling pricing
$1.00 per 1M input tokens and $4.05 per 1M output tokens. In real work that is 0.56¢ per chat answer and 2.2¢ to summarize a 20-page PDF.
What Inkling costs per task
Token counts estimated from a measured model of the same lab (Mistral Large 4), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.56¢$5.55 / 1,000 | 38 in · 508 out · 854 reasoning | 231 of 336 | estimated |
| Reply to a customer email | 1.5¢$14.53 / 1,000 | 246 in · 582 out · 2,946 reasoning | 313 of 336 | estimated |
| Write a 1,500-word blog post | 3.1¢$31.28 / 1,000 | 53 in · 2,005 out · 5,705 reasoning | 273 of 336 | estimated |
| Write 10 product descriptions | 1.3¢$12.65 / 1,000 | 276 in · 825 out · 2,230 reasoning | 234 of 336 | estimated |
| Translate 1,000 words | 5.0¢$50.30 / 1,000 | 1,311 in · 1,279 out · 10,816 reasoning | 294 of 336 | estimated |
| Proofread one page (500 words) | 1.7¢$17.38 / 1,000 | 710 in · 835 out · 3,281 reasoning | 293 of 336 | estimated |
| Summarize a 20-page PDF | 2.2¢$21.76 / 1,000 | 12,996 in · 146 out · 2,019 reasoning | 251 of 336 | estimated |
| Extract data from an invoice | 1.1¢$11.01 / 1,000 | 363 in · 846 out · 1,784 reasoning | 282 of 336 | estimated |
| Analyze a 200-row spreadsheet | 4.7¢$47.46 / 1,000 | 4,639 in · 4,398 out · 6,174 reasoning | 237 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 1.7¢$16.56 / 1,000 | 3,665 in · 204 out · 2,981 reasoning | 276 of 336 | estimated |
| Classify 100 support tickets | 3.1¢$31.10 / 1,000 | 1,238 in · 808 out · 6,565 reasoning | 293 of 336 | estimated |
| Review 500 lines of code | 4.1¢$41.26 / 1,000 | 4,526 in · 1,549 out · 7,522 reasoning | 243 of 336 | estimated |
| Write a SQL query | 1.3¢$12.85 / 1,000 | 117 in · 496 out · 2,647 reasoning | 289 of 336 | estimated |
| Run a 50-step coding agent | $1.05$1,045 / 1,000 | 2,239,737 in · 15,014 out · 132,350 reasoning | 239 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Inkling through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 DeepInfrafp8 | $0.95 / $4.05 | $0.16 | 524K | 100% |
 Togetherunknown | $1.00 / $4.05 | $0.17 | 524K | 100% |
Price history
First seen in our price history on Jul 20, 2026 at $1.00 input / $4.05 output. Since then the output price moved from $4.05 to $4.05 per 1M tokens (4 changes).
FAQ
How much does Inkling cost?
Inkling costs $1.00 per 1 million input tokens and $4.05 per 1 million output tokens, with cached input at $0.17 (list price on Oct 18, 2026). In practice one chat answer costs about 0.56¢ and summarizing a 20-page PDF about 2.2¢.
Where is Inkling cheapest?
Among 2 providers we track, the lowest list price today is at DeepInfra: $0.95 input and $4.05 output per 1M tokens.
Does Inkling charge for reasoning tokens?
Yes. Reasoning (thinking) tokens are billed as output tokens. That is why the cost per task can be much higher than the visible answer suggests - our task costs include them.
Is the Inkling cost per task measured or estimated?
Estimated: Inkling was not run directly. Tokens come from Mistral Large 4 and are rescaled by the tokenizer of Thinkingmachines. Real usage can differ.