Mistralopen weightsMixtral 8x22B Instruct pricing
$2.00 per 1M input tokens and $6.00 per 1M output tokens. In real work that is 0.83¢ per chat answer and 4.0¢ to summarize a 20-page PDF.
What Mixtral 8x22B Instruct 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 | 0.83¢$8.34 / 1,000 | 40 in · 523 out · 854 reasoning | 261 of 336 | estimated |
| Reply to a customer email | 2.2¢$21.78 / 1,000 | 254 in · 599 out · 2,946 reasoning | 324 of 336 | estimated |
| Write a 1,500-word blog post | 4.7¢$46.72 / 1,000 | 55 in · 2,064 out · 5,705 reasoning | 292 of 336 | estimated |
| Write 10 product descriptions | 1.9¢$19.04 / 1,000 | 285 in · 849 out · 2,230 reasoning | 266 of 336 | estimated |
| Translate 1,000 words | 7.5¢$75.50 / 1,000 | 1,349 in · 1,317 out · 10,816 reasoning | 306 of 336 | estimated |
| Proofread one page (500 words) | 2.6¢$26.31 / 1,000 | 731 in · 860 out · 3,281 reasoning | 302 of 336 | estimated |
| Summarize a 20-page PDF | 4.0¢$39.77 / 1,000 | 13,373 in · 151 out · 2,019 reasoning | 284 of 336 | estimated |
| Extract data from an invoice | 1.7¢$16.68 / 1,000 | 374 in · 871 out · 1,784 reasoning | 298 of 336 | estimated |
| Analyze a 200-row spreadsheet | 7.4¢$73.75 / 1,000 | 4,774 in · 4,526 out · 6,174 reasoning | 260 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 2.7¢$26.69 / 1,000 | 3,772 in · 210 out · 2,981 reasoning | 294 of 336 | estimated |
| Classify 100 support tickets | 4.7¢$46.93 / 1,000 | 1,274 in · 832 out · 6,565 reasoning | 308 of 336 | estimated |
| Review 500 lines of code | 6.4¢$64.01 / 1,000 | 4,658 in · 1,594 out · 7,522 reasoning | 267 of 336 | estimated |
| Write a SQL query | 1.9¢$19.19 / 1,000 | 121 in · 511 out · 2,647 reasoning | 299 of 336 | estimated |
| Run a 50-step coding agent | $1.50$1,499 / 1,000 | 2,304,625 in · 15,450 out · 132,350 reasoning | 261 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Mixtral 8x22B Instruct through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
Mistralunknown | $2.00 / $6.00 | $0.20 | 65K | |
Mistralunknown | $2.00 / $6.00 | $0.20 | 65K | |
Mistralunknown | $2.20 / $6.60 | $0.22 | 65K |
Price history
First seen in our price history on Apr 18, 2024 at $0.65 input / $0.65 output. Since then the output price moved from $0.65 to $6.00 per 1M tokens (4 changes).
FAQ
How much does Mixtral 8x22B Instruct cost?
Mixtral 8x22B Instruct costs $2.00 per 1 million input tokens and $6.00 per 1 million output tokens, with cached input at $0.20 (list price on Oct 18, 2026). In practice one chat answer costs about 0.83¢ and summarizing a 20-page PDF about 4.0¢.
Where is Mixtral 8x22B Instruct cheapest?
Among 3 providers we track, the lowest list price today is at Mistral: $2.00 input and $6.00 output per 1M tokens.
Is the Mixtral 8x22B Instruct cost per task measured or estimated?
Estimated: Mixtral 8x22B Instruct was not run directly. Tokens come from Mistral Large 4 and are rescaled by the tokenizer of Mistral. Real usage can differ.