Mixtral 8x7B (fw)

Name: Mixtral 8x7B (fw)
Brand: Fireworks AI
Price: 0.200000 USD

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 Kicked off the open-weights MoE wave; now superseded by 8x22B and Llama 3.x.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 32,000-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

unchanged since 3 May

default reference rate · how it is calculated →

CONTEXT

32,000

tokens

What it is 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 · 131,000 ctx

in $3.000/Mout $3.000/M

DeepSeek-R1 (fw)

Reasoning · 64,000 ctx

in $3.000/Mout $8.000/M

Qwen2.5-72B (fw)

Balanced · 32,000 ctx

in $0.900/Mout $0.900/M

Llama 3.1 8B (fw)

Nano · 131,000 ctx

in $0.100/Mout $0.100/M

Yi-34B (fw)

Open · 4,000 ctx

in $0.900/Mout $0.900/M

Phind-CodeLlama-34B (fw)

Code · 16,000 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 32,000 tokens of context in a single request.

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.

Terms used on this page

Full glossary →

Token Input tokens Output tokens Price per million tokens Context window Prompt caching Batch API Blended cost