Last verified
ARCHIVE PRICERETIRED MOE64K CONTEXTOPEN WEIGHTS

Mixtral 8x22B API Pricing

Mixtral 8x22B is retired; this archive preserves its listed API price while pointing new work to mistral-small-4. Baseline token rates are $2/M input and $6/M output; no separate prompt-cache price is published for this row. Pulled from official Mistral sources and the project pricing snapshot.

Archived Input - per 1M tokens
$2.00/M
Source Mistral retired archive
Archived Output - per 1M tokens
$6.00/M
Context 64K retired archive
Cache N/A
$2.00/M
Cache no separate SKU not listed
Effective - agentic blend
$2.32/M
92/8 split - no cache
§ 01 / TERMINAL

Mixtral 8x22B API cost calculator.

Archive calculator pre-loaded with Mixtral 8x22B rates. Tweak spend, output mix, or cache assumptions to compare this row against current Mistral replacements.

$ /mo
Workload split
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Mixtral 8x22B cost on real workloads.

CHATBOT

Support assistant

$0.007/turn
2,000 in - 500 out~14,285 units/$100
CODING AGENT

Repo task iteration

$0.130/task
50,000 in - 5,000 out~769 units/$100
LONG DOC

Contract review

$0.372/doc
180,000 in - 2,000 out~268 units/$100
RAG

Knowledge base answer

$0.022/query
8,000 in - 1,000 out~4,545 units/$100
§ 03 / TOKENIZER

Mixtral 8x22B token counter and cost.

What's a token →
Calibrated · measured on the vendor's tokenizer · 2026-06-10 Auto-counts as you type

Counts use a chars-per-token calibration measured on the vendor's own published tokenizer (mistralai/Mistral-Nemo-Instruct-2407, 2026-06-10). English prose is typically within a few percent; code and non-Latin scripts tokenize heavier. For billing-exact counts use the vendor's count-tokens API.

Characters 394
Words 63
Tokens (estimated) 77 tokens
Cost as input · uncached $0.00015 USD
Cost as output · uncached $0.00046 USD
§ 04 / SHELF

Mixtral 8x22B vs similar models.

All models →
Model Input /M Output /M Effective blended Context Best for
Mixtral 8x22B Current $2.00 $6.00 $2.32 agentic 92/8 64K General Mistral workloads
Mistral Large 3 $0.50 cache $0.05 $1.50 $0.241 −9.6× documented elsewhere — not on pricing page Frontier multimodal work
Mistral Medium 3.5 $1.50 cache $0.15 $7.50 $0.962 −2.4× documented elsewhere — not on pricing page General Mistral workloads
Mistral Small 4 $0.15 cache $0.015 $0.60 $0.0842 −28× 256K Low-cost chat and support
Codestral $0.30 cache $0.03 $0.90 $0.144 −16× documented elsewhere — not on pricing page Code generation and agents
Devstral 2 $0.40 $2.00 $0.528 retired documented elsewhere — not on pricing page Code generation and agents
Magistral Medium $2.00 $5.00 $2.24 retired documented elsewhere — not on pricing page Transparent reasoning
DeepSeek V4.1 Flash $0.30 cache $0.006 $1.20 $0.15 −15× 1M Budget coding and bulk reasoning

Mixtral 8x22B API pricing FAQ.

Practical pricing questions, with archived prices separated from current availability.

Q · 01 What is Mixtral 8x22B priced at? +
Mixtral 8x22B is shown here at $2/M input and $6/M output. For retired or deprecated rows, the price is preserved as an archive baseline.
Q · 02 Is Mixtral 8x22B still available? +
Mixtral 8x22B is retired in the current Mistral docs. Use mistral-small-4 for new production traffic when available.
Q · 03 Does Mistral list prompt caching for this model? +
No separate prompt-cache SKU is published for this row. The calculator therefore treats cache-hit input as the base input rate, $2/M, so the effective blend does not assume a hidden discount.
Q · 04 What does the effective price mean? +
The effective tile uses the site-wide agentic blend: 92% input tokens, 8% output tokens, and no cache discount unless a vendor lists one. For Mixtral 8x22B, that gives $2.32/M.
Q · 05 Where does the archive price come from? +
For active rows, the price comes from Mistral's current pricing or model card. For retired rows, AI//COST preserves the verified snapshot price and uses Mistral's current docs to verify deprecation, retirement, and replacement status.
Q · 06 Is there a batch discount? +
Mistral exposes batching in the API docs, but this archive row does not publish a separate per-model batch rate. The calculator keeps the baseline token prices visible and avoids inventing a discount.
Y
Reviewed by Yaroslav Vikhariev Founder · AI//COST · Prices checked by hand against docs.mistral.ai · Last verified May 18, 2026
Methodology Report a correction More by Y.V.