Mixtral 8x22B Instruct API pricing
Mistral · Mid-range price tier · Apache 2.0 · released 2024-04. Prices in USD per 1 million tokens. Data snapshot: 2026-10-22.
Deprecated. The model maker has announced retirement of this model's API · shutdown 2025-03-30 · suggested replacement: Mistral Small 4. It still carries a price because hosts still serve it; treat it as a model to migrate off, not one to start on.
Mixtral 8x22B Instruct has held the same list price since 2026-10-18 and is the 66th cheapest of 113 models in the Mid-range price tier. Only one host, Mistral, sells it, so there is no second price to shop. Its maker has announced its retirement, so it is a model to migrate off rather than start on.
- Input: $2.00 per 1M tokens
- Output: $6.00 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.20 per 1M tokens
- Context window: 66K tokens
- Arena ELO: 1230 as of 2026-10-08
Market position
On blended price ($4.80 per 1M tokens at 30% input, 70% output) it is cheaper than 35% of models in the Mid-range price tier: 66th cheapest of 113, tied with 8 others. Across every price tier it is cheaper than 23% of priced text models in the catalogue: 230th cheapest of 308, tied with 8 others. Its Arena ELO of 1230 ranks 153rd of the 156 models that carry one, above 2% of them.
Licence, size and capabilities
Mixtral 8x22B Instruct is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token. Its published size is 141B parameters. Listed capabilities: Text, Agents. Filling its 66K context window once costs $0.132 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 1 host. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
Mistral is the only host with a published rate, $2.00 input / $6.00 output per 1M tokens, which is the price we quote.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| Mistral (model maker, price we quote) | $2.00 | $6.00 |
List prices as published on 2026-10-22, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Mistral publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $438 – $600 |
| Knowledge Q&A | 2,000 / 800 | $628 – $880 |
| Meeting Summary | 10,000 / 1,200 | $2.5K – $2.7K |
| Marketing Content | 2,500 / 1,800 | $1.5K – $1.6K |
| Coding Task | 3,000 / 2,000 | $1.5K – $1.8K |
| Invoice Processing | 1,500 / 600 | $579 – $660 |
| Call Summary | 2,000 / 700 | $784 – $820 |
| Agent Workflow | 6,000 / 3,000 | $2.2K – $3.0K |
Price history
Mixtral 8x22B Instruct entered our daily price archive on 2026-10-18; tracking began on 2026-08-15. It listed at $2.00 input / $6.00 output per 1M tokens that day. No list price change since 2026-10-18. Last checked against the 2026-10-22 snapshot.
Alternatives to Mixtral 8x22B Instruct
- Next cheaper model in the Mid-range price tier: Palmyra X5 (Writer) at $4.38 blended, 9% less.
- Next more expensive: GLM 5.2 (Zhipu) at $4.9102 blended, 2% more.
The nearest models in the Mid-range price tier on Arena ELO, each with its blended price and score difference against Mixtral 8x22B Instruct.
- Command R+ (08-2024) (Cohere): $2.50 in / $10.00 out per 1M, Arena ELO 1276 (61% more expensive, 46 ELO points higher)
- Mistral Large 2407 (Mistral): $2.00 in / $6.00 out per 1M, Arena ELO 1314 (same blended price, 84 ELO points higher)
- GPT-4o (OpenAI): $2.50 in / $10.00 out per 1M, Arena ELO 1336 (61% more expensive, 106 ELO points higher)
- o3 Mini (OpenAI): $1.10 in / $4.40 out per 1M, Arena ELO 1348 (29% cheaper, 118 ELO points higher)
- Highest Arena ELO within 20% of this price: Qwen3.8 Max (0902) (Alibaba), same blended price, 253 ELO points higher, out of 8 models in that price band.
Other models from Mistral
The 8 nearest to Mixtral 8x22B Instruct in price, of 19 other Mistral models in the catalogue. Prices per 1M tokens, input then output.
- Mistral Large 3 2512: $0.50 / $1.50
- Devstral 2 2512: $0.40 / $2.00
- Mistral Medium 3: $0.40 / $2.00
- Mistral Medium 3.1: $0.40 / $2.00
- Mistral Large 4: $1.36 / $4.18
- Mistral Large: $2.00 / $6.00
- Mistral Large 2407: $2.00 / $6.00
- Mistral Medium 3.5: $1.50 / $7.50
All 20 Mistral models and prices
Common questions about Mixtral 8x22B Instruct pricing
- How much does Mixtral 8x22B Instruct cost?
- Mixtral 8x22B Instruct costs $2.00 per 1M input tokens and $6.00 per 1M output tokens. That is the model maker's own rate (Mistral). Prices as listed on 2026-10-22.
- Which host is cheapest for Mixtral 8x22B Instruct?
- Mistral is the only host with a published rate, $2.00 input / $6.00 output per 1M tokens, which is the price we quote. Host rates as listed on 2026-10-22.
- Does Mixtral 8x22B Instruct offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.20 per 1M tokens, as listed on 2026-10-22. No batch pricing is published.
- What would Mixtral 8x22B Instruct cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $600 on Mixtral 8x22B Instruct at the list price quoted on 2026-10-22.
- Can Mixtral 8x22B Instruct be self-hosted?
- Yes. Mixtral 8x22B Instruct is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token.
- Has the price of Mixtral 8x22B Instruct changed?
- Mixtral 8x22B Instruct entered our daily price archive on 2026-10-18; tracking began on 2026-08-15. It listed at $2.00 input / $6.00 output per 1M tokens that day. No list price change since 2026-10-18. Last checked against the 2026-10-22 snapshot.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server