aiapicostcalcUnit economicsPricesBrandsCompareBenchmarksSkills & PluginsFind my modelGuidesChanges

Ministral 3 8B API pricing and cost calculator

Short answer: Ministral 3 8B costs $0.15 per 1M input tokens and $0.15 per 1M output tokens on Mistral's standard tier (checked 2026-11-15), with no cached-input rate listed. A 2,000-input / 500-output chat call costs $0.000375, so 1,000 calls cost $0.3750. Output is 1.0× the input price, which is why long answers dominate a bill.

Last verified 2026-11-18 · Sources: Mistral pricing page, checked 2026-11-15 · Report an error

By Shangyi Duan · Reviewed against Mistral pricing page

Source URL: https://docs.mistral.ai/inference/pricing · Verified: · Rate row: src/prices.json

1
2
Presets

Preset token counts are starting assumptions; replace them with your logged averages.

Cost per call$0.000375
Per 1,000 calls$0.3750

$0.15 in · $0.15 out per 1M

Nearest-priced models, this workload

Showing the 9 models closest in price; change any input to rank every model.

ModelPer callPer 1K calls
Ministral 3 3B$0.00025$0.2500
Ministral 3 8B$0.000375$0.3750
Gemini 2.5 Flash-Lite$0.0004$0.4000
GPT-6 Luna$0.00045$0.4500
Claude Haiku 5.5$0.00045$0.4500
Ministral 3 14B$0.0005$0.5000
GPT-4o mini (deprecated)$0.0006$0.6000
Mistral Small 4$0.0006$0.6000
GPT-5.6 Luna$0.0010$1.00

o4-mini is shut down; its last published list rate is kept for comparing old invoices, not as a model you can call today — the model page names its replacement.

At a glance

API model IDministral-8b-2512
Context window256K tokens
Inputstext, image

Every price tier

TierPrice per 1M tokens
Standard input$0.15
Cached input (cache read)–
Output (incl. reasoning tokens)$0.15
Batch API input / output$0.075 / $0.075 (50% off)

Source: Mistral pricing and the Ministral 3 8B model page, checked 2026-11-15.

API name ministral-8b-2512; 256K context; batch −50%

Worked examples

WorkloadPer callPer 1K callsPer 1K, Batch
Chat reply · 1K in / 500 out$0.000225$0.2250$0.1125
RAG answer · 10K in / 1K out$0.00165$1.65$0.8250
RAG with 80% cached prefix$0.00165$1.65$0.8250
Long document · 100K in / 2K out$0.0153$15.30$7.65
Whole-codebase prompt · 400K in / 4K outexceeds the 256K context window

When to pick it

Where it sits in the Mistral lineup

Among the 6 Mistral models we track, Ministral 3 8B ranks #2 from cheapest at a 10K-in / 1K-out workload ($1.65 per 1,000 calls). The next cheaper option is Ministral 3 3B at $1.10 (0.67× the cost, 256K context). Stepping up to Mistral Small 4 costs $2.10 (1.3×).

Performance benchmarks

Measured scores copied from the dated leaderboard pages linked in the table: GPQA Diamond, Humanity's Last Exam, MMMU-Pro. A benchmark this model does not publish is left out rather than estimated, and scores from different benchmarks are never mixed into one number.

On GPQA Diamond, Ministral 3 8B ranks #3 of the 4 Mistral models we track that publish this benchmark.

BenchmarkScoreRank in the Mistral lineupCost per quality pointSource, checked
GPQA Diamond47.1%#3 of 4$0.00318 / pointartificialanalysis.ai ·
Humanity's Last Exam4.3%#3 of 4$0.0349 / pointartificialanalysis.ai ·
MMMU-Pro46%#3 of 4$0.00326 / pointartificialanalysis.ai ·

GPQA/MMMU-Pro/HLE from Artificial Analysis entry 'Ministral 3 8B'.

Cost per quality point = blended standard price (3 input tokens : 1 output token per 1 million) ÷ the benchmark score: what one point of measured quality costs at list price, not a task cost. Ranks compare only models from the same provider on the same benchmark. All benchmarks ranked by price and performance · Best LLM for coding · Compare two models

Related

Ready to build? Create an API key in the official Mistral console.

Questions

How much does Ministral 3 8B cost per 1M tokens?

$0.15 for input, $0.15 for output and – for cached input on the standard tier. Source: the official Mistral pricing page, checked 2026-11-15.

How much do 1,000 Ministral 3 8B API calls cost?

At 2,000 input and 500 output tokens per call, one call costs $0.000375 and 1,000 calls cost $0.3750 at list price. Batch and caching are not included; both lower the total.

Is Ministral 3 8B expensive compared with other models?

On a 2,000-input / 500-output chat call it ranks #2 of 55 verified models by cost. The cheapest is Ministral 3 3B at $0.00025 per call.

Does Ministral 3 8B publish a cached-input rate or a batch discount?

Its official pricing page lists no cached-input rate on its official page, so cached tokens are billed at the normal input rate and a Batch API multiplier of 0.5, a 50% discount. Caching pays off when a system prompt or document prefix repeats across calls; batch applies only to asynchronous jobs nobody is waiting on. Both are priced on top of the standard rates above, never instead of them.

Next step → Estimate cost per user with Ministral 3 8B

Price data last checked 2026-11-18 against official sources · how we verify

Price-change alerts

One short email when a provider changes a price or a promo ends. No spam, unsubscribe any time.

Tools, skills & plugins that use this model

Matched to this model's profile: cheaper models are paired with workflow and agent tools, million-token-context models with frameworks and open-source projects, and reasoning models with coding agents. Each entry links to its token-cost page or official site, and the per-task price is calculated on this model from the tool data rather than copied from another model.

More paths from this model