Mixtral 8x7B Instruct

Mixtral 8x7B Instruct is a text model from Perplexity with a context window of 4K tokens and max output of 4K tokens. Pricing starts at 0.07 per million input tokens and 0.28 per million output tokens (cheapest at Perplexity).

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Specifications

Model Keyperplexity/mixtral-8x7b-instruct
ProviderPerplexity
Provider IDperplexity
ModeText
Canonical Namemixtral-8x7b
Context Window4K tokens
Max Output4K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.0000700.070
Output Tokens0.0002800.280

Benchmarks

Intelligence Index7.7#223
MMLU-Pro0.4#185
GPQA0.3#207
HLE0.0#139
LiveCodeBench0.1#189
AIME0.0#127
Time to First Token0.00s#1
SciCode0.0#214
MATH-5000.3#134

Price Comparison by Provider

Compare prices for Mixtral 8x7B Instruct across different providers. The same model may be available through multiple providers at different price points.

Provider
Model Key
Input Price, $
Output Price, $
Snowflakesnowflake/mixtral-8x7bN/AN/A
Perplexityperplexity/mixtral-8x7b-instruct0.0700.280
Mistral AImistral/open-mixtral-8x7b0.7000.700
Fireworks AIfireworks_ai/accounts/fireworks/models/mixtral-8x7b0.5000.500

All Variants

All available versions, regions, and API endpoints for Mixtral 8x7B Instruct.

Model Key
Provider
Mode
Input Price, $
Output Price, $
Context
Max Output
Vision
Functions
fireworks_ai/accounts/fireworks/models/mixtral-8x7bFireworks AIText0.5000.50033K33Knono
fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instructFireworks AIText0.5000.50033K33Knono
fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hfFireworks AIText0.5000.50033K33Knono
mistral/open-mixtral-8x7bMistral AIText0.7000.70032K8Knoyes
perplexity/mixtral-8x7b-instructPerplexityText0.0700.2804K4Knono
snowflake/mixtral-8x7bSnowflakeTextN/AN/A32K8Knono