aiapicostcalcUnit economicsPricesBrandsCompareBenchmarksSkills & PluginsFind my modelGuidesChanges

Codestral 25.08 API pricing and cost calculator

Short answer: Codestral 25.08 costs $0.3 per 1M input tokens and $0.9 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 $0.00105, so 1,000 calls cost $1.05. Output is 3.0× 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$0.00105
Per 1,000 calls$1.05

$0.3 in · $0.9 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
GPT-4o mini (deprecated)$0.0006$0.6000
Mistral Small 4$0.0006$0.6000
GPT-5.6 Luna$0.0010$1.00
GPT-5.4 nano (deprecated, retires 2027-04-01)$0.00103$1.03
Codestral 25.08$0.00105$1.05
DeepSeek Flash (V4.1)$0.0012$1.20
Gemini 3.1 Flash-Lite$0.00125$1.25
GPT-5 mini (deprecated, retires 2026-12-11)$0.0015$1.50
Gemini 3.5 Flash-Lite$0.00185$1.85

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 IDcodestral-2508
Context window128K tokens
Inputstext

Every price tier

TierPrice per 1M tokens
Standard input$0.3
Cached input (cache read)–
Output (incl. reasoning tokens)$0.9
Batch API input / output$0.15 / $0.45 (50% off)

Source: Mistral pricing and the Codestral 25.08 model page, checked 2026-11-15.

API name codestral-2508; 128K context; code model; batch −50%

Worked examples

WorkloadPer callPer 1K callsPer 1K, Batch
Chat reply · 1K in / 500 out$0.00075$0.7500$0.3750
RAG answer · 10K in / 1K out$0.0039$3.90$1.95
RAG with 80% cached prefix$0.0039$3.90$1.95
Long document · 100K in / 2K out$0.0318$31.80$15.90
Whole-codebase prompt · 400K in / 4K outexceeds the 128K context window

When to pick it

Where it sits in the Mistral lineup

Among the 6 Mistral models we track, Codestral 25.08 ranks #5 from cheapest at a 10K-in / 1K-out workload ($3.90 per 1,000 calls). The next cheaper option is Ministral 3 14B at $2.20 (0.56× the cost, 256K context). Stepping up to Mistral Large 4 costs $9.10 (2.3×). The cheapest in the lineup, Ministral 3 3B, is 3.55× cheaper.

Performance benchmarks

Measured scores copied from the dated leaderboard pages linked in the table: SWE-bench Verified, LiveCodeBench, AIME. 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 SWE-bench Verified, Codestral 25.08 ranks #2 of the 3 Mistral models we track that publish this benchmark.

BenchmarkScoreRank in the Mistral lineupCost per quality pointSource, checked
SWE-bench Verified60.1%#2 of 3$0.00749 / pointtrustthebench.com ·
LiveCodeBench63.1%#2 of 3$0.00713 / pointtrustthebench.com ·
AIME71.5%#2 of 3$0.00629 / pointtrustthebench.com ·

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 Codestral 25.08 cost per 1M tokens?

$0.3 for input, $0.9 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 Codestral 25.08 API calls cost?

At 2,000 input and 500 output tokens per call, one call costs $0.00105 and 1,000 calls cost $1.05 at list price. Batch and caching are not included; both lower the total.

Is Codestral 25.08 expensive compared with other models?

On a 2,000-input / 500-output chat call it ranks #11 of 55 verified models by cost. The cheapest is Ministral 3 3B at $0.00025 per call.

Does Codestral 25.08 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 Codestral 25.08

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