Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All Groq models
Groq
GroqEfficient

Mixtral 8x7B (Groq)

Fast MoE

The original Mixtral MoE from late 2023. Kicked off the open-weights MoE wave; now superseded by 8x22B and Llama 3.x.

Mixtral 8x7B (Groq) is a efficient AI model from Groq. It costs $0.240 per million input tokens and $0.240 per million output tokens (blended $0.240/M), with a 32K-token context window.

Profile inherited from upstream Mixtral 8x7B ↗ — this is a hosted variant of the same open-weights model.

Released Dec 2023Modalities textOfficial model page ↗Provider pricing ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.240/M
per million input tokens
OUTPUT
$0.240/M
per million output tokens
BLENDED 70/30
$0.240/M
default reference rate · how it's calculated →
CONTEXT
32K
32,000 tokens
What it's good at
  • Open weights
  • 32K context
  • Wide ecosystem
Typical use cases
  • Legacy Mixtral 8x7B deployments
  • Fine-tune base
Benchmarks
vs. best public score
Scores inherited from Mixtral 8x7B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU71%
Multitask academic knowledge across 57 subjects.
MATH28%
High-school competition math problems.
HumanEval40%
Python function synthesis from docstrings.
LMArena Elo1124 Elo
Crowd-sourced head-to-head preference Elo rating.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources — treat as directional rather than authoritative.
More from Groq
See all 11 →
Llama 3.3 70B (Groq)
Ultra-Fast · 128K ctx
in $0.590/Mout $0.790/M
Llama 3.1 405B (Groq)
Fast Large · 128K ctx
in $2.990/Mout $2.990/M
Llama 3.1 70B (Groq)
Fast · 128K ctx
in $0.590/Mout $0.790/M
Llama 3.1 8B (Groq)
Fast Nano · 128K ctx
in $0.050/Mout $0.080/M
Llama 3.2 11B Vision (Groq)
Fast Vision · 128K ctx
in $0.180/Mout $0.180/M
Llama 3.2 3B (Groq)
Fast Micro · 128K ctx
in $0.060/Mout $0.060/M
Frequently asked questions

How much does Mixtral 8x7B (Groq) cost?

Mixtral 8x7B (Groq) costs $0.240 per million input tokens and $0.240 per million output tokens, for a blended reference rate of $0.240 per million tokens.

What is Mixtral 8x7B (Groq)'s context window?

Mixtral 8x7B (Groq) supports up to 32K tokens of context (32,000 tokens).

What is Mixtral 8x7B (Groq) best for?

Mixtral 8x7B (Groq) is well suited to Open weights, 32K context and Wide ecosystem.

Who makes Mixtral 8x7B (Groq)?

Mixtral 8x7B (Groq) is developed and served by Groq. It was released in Dec 2023.