Mixtral 8x22B (MoE) — pricing & specs
Mixtral 8x22B (MoE) is a balanced model from Mistral, at capability tier 4 of 8. Live $/M-token pricing and specs from the Mintok catalog.
$/M-token pricing
Open-weights model — no per-token list price. Size your self-host $/M-token →
Specifications
- Vendor
- Mistral
- Family
- Mixtral 8x
- Capability tier
- 4 / 8
- Size class
- BALANCED
- Category
- GENERAL
- Parameters
- 141B total · 2B active (MoE)
- Context window
- 64,000 tokens
- Licensing
- Proprietary
Carbon footprint (modeled)
Modeled decode on a reference NVIDIA Rubin Ultra VR300 at 50% MBU, batch 32, global-avg grid. Compare all models & grids →
Alternatives at tier 4
Same capability tier, sorted by output price — the cheaper-capable options.
- LLaMA 4 ScoutMeta$0.30/M out
- Qwen 2.5 72BAlibaba$0.40/M out
- GPT-4o miniOpenAI$0.60/M out
- LLaMA 4 MaverickMeta$0.80/M out
- Qwen 3 235B (MoE)Alibaba$1.82/M out
- Claude Haiku 3.5Anthropic$4/M out
FAQ
How much does Mixtral 8x22B (MoE) cost per token?
Mixtral 8x22B (MoE) is distributed as open weights — there is no per-token list price; you self-host it. Use the Mintok sizing report to estimate your $/M-token at your volume.
What is Mixtral 8x22B (MoE)'s context window?
Mixtral 8x22B (MoE) supports a 64,000-token context window.
What capability tier is Mixtral 8x22B (MoE)?
Mixtral 8x22B (MoE) sits at capability tier 4 of 8 on the Mintok scale (BALANCED size class).
Is Mixtral 8x22B (MoE) open-source or proprietary?
Mixtral 8x22B (MoE) is a proprietary model from Mistral, accessed via API.
Put Mixtral 8x22B (MoE) to work
Benchmark it on your prompts, or size a deployment and compare $/M-token against alternatives.
Pricing and specs are maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.