Mistral

Mixtral 8x7B Instruct

AI model by Mistral. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.45
Output$0.70
Blended (3:1)$0.51

Source: Artificial Analysis

Performance

Output Speed
Time to First Token

Median values from Artificial Analysis

Benchmarks

Editorial Analysis

Profile. Mixtral 8x7B Instruct is a budget-tier option from Mistral at $0.70/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.

Cost model. For a workload of 1M input tokens + 100K output tokens, Mixtral 8x7B Instruct costs $0.52 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.

Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.

Compare with similar models

ModelInputOutputSpeed
Mixtral 8x7B InstructCurrent
$0.45$0.70
Hermes 3 - Llama-3.1 70B
$0.70$0.7034 tok/s
Qwen3 VL 8B Instruct
$0.18$0.70107 tok/s
Celeris-1
$0.20$0.701484 tok/s
Qwen3 8B (Non-reasoning)
$0.18$0.7039 tok/s
Llama 3.3 Instruct 70B
$0.66$0.7284 tok/s

Example Costs

Single Request
$0.0008
1.0K in / 500 out
1K Requests/day
$0.8000
1.0M in / 500.0K out
10K Requests/day
$8.00
10.0M in / 5.0M out