RETIRED JUN 30 2026LEAN 4CODE AGENTMISTRAL LABS
Leanstral API Pricing
Leanstral was retired by Mistral on June 30, 2026 - the labs-leanstral-2603 model id no longer answers. It was a free API row ($0 per million tokens in and out); the page is kept for the record. Checked against Mistral's deprecated and retired models table.
Input - per 1M tokens
Free/M
Source mistral.ai free
Output - per 1M tokens
Free/M
Context 128K free
Cached input
Not published
Cache vendor row not listed
Effective - agentic blend
Free/M
92/8 split - no cache
§ 01 / TERMINAL
Leanstral API cost calculator.
Live calculator pre-loaded with Leanstral rates. Tweak spend, output mix, or cache assumptions to compare it with sibling models.
$ /mo
Workload split
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Leanstral cost on real workloads.
CODE
Proof or code iteration
$0/task
CHATBOT
Developer assistant
$0/turn
RAG
Docs lookup
$0/query
BULK
Static checks
$0/item
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 365
Words 59
Tokens (estimated) 72 tokens
Cost as input · uncached $0 USD
Cost as output · uncached $0 USD
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Leanstral Current | Free | Free | Free agentic 92/8 | documented elsewhere | Lean 4 formal proofs |
| Mistral Large 3 | $0.50 cache $0.05 | $1.50 | $0.241 paid | documented elsewhere — not on pricing page | Mistral production workloads |
| Mistral Small 4 | $0.15 cache $0.015 | $0.60 | $0.0842 paid | 256K | Low-cost reasoning and coding |
| Mistral Medium 3.5 | $1.50 cache $0.15 | $7.50 | $0.962 paid | documented elsewhere — not on pricing page | Frontier agentic and coding work |
| Ministral 3 14B | $0.20 cache $0.02 | $0.20 | $0.0642 paid | 128K | Mistral production workloads |
| Ministral 3 3B | $0.10 cache $0.01 | $0.10 | $0.0321 paid | 128K | Mistral production workloads |
| DeepSeek V4.1 Flash | $0.30 cache $0.006 | $1.20 | $0.15 paid | 1M | Budget coding and bulk reasoning |
Leanstral API pricing FAQ.
Practical pricing questions, separated from calculator assumptions.
Q · 01 Can I still call Leanstral? +
No. Mistral retired
labs-leanstral-2603 on June 30, 2026, and requests to it now fail. Mistral named Leanstral 1.5 (labs-leanstral-1-5) as its successor, also free in public preview - and retired that model too, on September 30, 2026, with no replacement. The rates on this page are the last ones Mistral listed for the old id.Q · 02 What is Leanstral priced at? +
Leanstral is shown at
$0/M input and $0/M output. The page stores USD per-million-token baseline pricing from mistral.ai.Q · 03 Does this page include higher context pricing tiers? +
This page uses the public API baseline for the model row. If Mistral publishes separate long-context tiers later, the snapshot entry should be re-verified and updated.
Q · 04 Is prompt caching priced separately? +
No separate cache-read price is published for this row, so the calculator treats cached input as
$0/M.Q · 05 How is the effective price calculated? +
AI//COST uses the same 92/8 agentic blend everywhere. For Leanstral, that gives
$0/M with only documented cache discounts included.Q · 06 Is there a batch discount? +
Mistral pricing does not list a separate per-model batch discount in this row.
Q · 07 Are regional prices different? +
Mistral's public pricing page lets you view USD and EUR. AI//COST stores the USD baseline and handles currency variants in calculator URLs.