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 Fireworks AI models
Fireworks AI
Fireworks AIEfficient

Mixtral 8x7B (fw)

Serverless

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 Kicked off the open-weights MoE wave; now superseded by 8x22B and Llama 3.x.

Mixtral 8x7B (fw) is a efficient AI model from Fireworks AI. It costs $0.200 per million input tokens and $0.200 per million output tokens (blended $0.200/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
$0.200/M
per million input tokens
OUTPUT
$0.200/M
per million output tokens
BLENDED 70/30
$0.200/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 Fireworks AI
See all 7 →
Llama 3.1 405B (fw)
Serverless · 131K ctx
in $3.000/Mout $3.000/M
DeepSeek-R1 (fw)
Reasoning · 64K ctx
in $3.000/Mout $8.000/M
Qwen2.5-72B (fw)
Balanced · 32K ctx
in $0.900/Mout $0.900/M
Llama 3.1 8B (fw)
Nano · 131K ctx
in $0.100/Mout $0.100/M
Yi-34B (fw)
Open · 4K ctx
in $0.900/Mout $0.900/M
Phind-CodeLlama-34B (fw)
Code · 16K ctx
in $0.800/Mout $0.800/M
Frequently asked questions

How much does Mixtral 8x7B (fw) cost?

Mixtral 8x7B (fw) costs $0.200 per million input tokens and $0.200 per million output tokens, for a blended reference rate of $0.200 per million tokens.

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

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

What is Mixtral 8x7B (fw) best for?

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

Who makes Mixtral 8x7B (fw)?

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