Mixtral 8x22B — pricing & specs
Mixtral 8x22B is a balanced model from Mistral, at capability tier 4 of 8. Live $/M-token pricing and specs from the Mintok catalog, as of 2026-08-09.
$/M-token pricing
as of 2026-08-09 · MistralWhat Mixtral 8x22B costs in practice
At $6/M output tokens, Mixtral 8x22B is the 7th-cheapest of 7 priced tier-4 models in the Mintok catalog — about 650% above the tier median of $0.80/M.
| Scenario | Est. cost |
|---|---|
| 1M input + 1M output tokens | $8.00 |
| A 10K-token request (8K in / 2K out) | $0.028 |
| 1,000 agent runs (~2K in / 500 out each) | $7.00 |
| 1M-token RAG chat session (900K cached in / 100K out) | $2.40 |
Estimated from list price (as of 2026-08-09) at the token mixes shown; your real cost depends on prompt/response length and cache hit-rate. Model your own volume →
Specifications
- Vendor
- Mistral
- Family
- Mixtral 8x
- Capability tier
- 4 / 8
- Size class
- BALANCED
- Category
- GENERAL
- Parameters
- 141B total · 2B active (MoE)
- Context window
- 65,536 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 cost per token?
Mixtral 8x22B costs $2 per million input tokens and $6 per million output tokens, via Mistral, as of 2026-08-09.
Is Mixtral 8x22B expensive?
At $6/M output tokens, Mixtral 8x22B is the 7th-cheapest of 7 priced tier-4 models in the Mintok catalog — about 650% above the tier median of $0.80/M.
What does a typical request with Mixtral 8x22B cost?
At list price, a 10K-token request (8K in / 2K out) with Mixtral 8x22B costs about $0.028, and 1,000 agent runs (~2K in / 500 out each) about $7.00.
What is Mixtral 8x22B's context window?
Mixtral 8x22B supports a 65,536-token context window.
What capability tier is Mixtral 8x22B?
Mixtral 8x22B sits at capability tier 4 of 8 on the Mintok scale (BALANCED size class).
Is Mixtral 8x22B open-source or proprietary?
Mixtral 8x22B is a proprietary model from Mistral, accessed via API.
Put Mixtral 8x22B 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.