LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Mixtral 8x22B Instruct

mistral·mistral/mixtral-8x22b-instruct·GA·Open weights·mistral series
Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·NanoGPTGateway
$2.00 / $6.00
Blended $3.00 · 1.1× spread
Context
65,536
Output limit
52,428
Knowledge cutoff
2024-01-31
Released / updated
2024-04-17 / 2024-04-17
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextPDF

Mixtral 8x22B Instruct by mistral is offered by 5 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is NanoGPT at $2.00 / $6.00 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

The context window is 65,536 tokens, with an output limit of 52,428 tokens. It supports tool use and structured output. Accepted input modalities are Text and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-01-31.

Available at 5 providers5 with public prices

  • ProviderInput / Output
  • NanoGPTGateway
    mistralai/mixtral-8x22b-instruct-v0.1
    $2.00 / $6.00
    Cache read $0.20Context 65,536Output limit 52,428
  • OpenRouterGateway
    $2.00 / $6.00
    Cache read $0.20Context 65,536Output limit 52,428
  • Kilo GatewayGateway
    $2.00 / $6.00
    Cache read $0.20Context 65,536Output limit 52,428
  • AI/ML APIGateway
    $2.12 / $6.35
    Cache read $0.21Context 65,536Output limit 52,428
  • Prime InferenceGateway
    $2.20 / $6.60
    Context 65,536Output limit 52,428
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPT
mistralai/mixtral-8x22b-instruct-v0.1
Gateway$2.00$6.00$0.20—65,53652,428
OpenRouterGateway$2.00$6.00$0.20—65,53652,428
Kilo GatewayGateway$2.00$6.00$0.20—65,53652,428
AI/ML APIGateway$2.12$6.35$0.21—65,53652,428
Prime InferenceGateway$2.20$6.60——65,53652,428

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1NanoGPT$484.00
2OpenRouter$484.00
3Kilo Gateway$484.00
4AI/ML API$512.07
5Prime Inference$770.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $3.00

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

Voxtral Mini Transcribe 3same series—Voxtral Small Transcribe 3same series—Voxtral TTS 3same series—Mistral Small (latest)same lab$0.15 / $0.60Pixtral Large (25.02)same lab—
Data partly from models.dev (MIT)