All times Eastern (ET)Provider pages checked daily at

Migrating from open-mixtral-8x7b to open-mixtral-8x22b

What changes when you move from open-mixtral-8x7b to open-mixtral-8x22b: context window 32,000 → 64,000 tokens.

Status
Retired
Shutdown
Mar 30, 2025
Time left
—
Status
Retired
Shutdown
Mar 30, 2025
Time left
—

open-mixtral-8x22b is itself retired. Its replacement is mistral-small-2603.

Prices

USD per 1M tokens, standard tier

Neither model has published per-token prices.

Limits

Tokens
Limitopen-mixtral-8x7bopen-mixtral-8x22bChange
Context window32,000 tokensin place when tracking began (October 6, 2026) · source64,000 tokensin place when tracking began (October 6, 2026) · source+100%
Max output tokensNot publishedNot published—

Benchmarks

Same benchmark, source and setting on both sides
Benchmarkopen-mixtral-8x7bopen-mixtral-8x22bChange
Arena TextArena. Ranges don't overlap.1197 ±41230 ±5+33
Arena Text: CodingArena. Ranges don't overlap.1240 ±81278 ±9+38
GPQA DiamondEpoch AI.30.6%34.1%+3.5 pts
MATH Level 5Epoch AI.9.3%24.2%+14.9 pts

A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Arena (arena.ai), CC BY 4.0; Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features and parameters

Compare models

No feature is published for both models, so none can be compared.

Not published for open-mixtral-8x7b: Structured outputs, Function calling, Prompt caching, Batch API, Image input, PDF input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Max output tokens.

Not published for open-mixtral-8x22b: Structured outputs, Function calling, Prompt caching, Batch API, Image input, PDF input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Max output tokens.

No aliases point at either model.

Checklist

  1. Change the model string from open-mixtral-8x7b to open-mixtral-8x22b.

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: open-mixtral-8x7b, open-mixtral-8x22b.