MistralDeprecated
mistral-nemo-instruct-2407
A 12B parameter, instruct-tuned language model by Mistral AI and NVIDIA, designed for advanced instruction following, multi-turn conversations, and generating text and code across multiple languages.
Context
131,072
Max output
128,000
Input / 1M
$0.02
Output / 1M
$0.03
Providers
7
01Profile
Profile
Released
2024-08-07
Last updated
2024-11-20
Knowledge cutoff
—
Weights
Closed
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
Yes
Structured output
Yes
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 7 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2024-08-07
2026-09-02ContextcortecsMax output131,072→ 128,000
2026-08-19ContextpioneerContext window131,072→ new
2026-08-05Addedcortecsoffering→ new
2026-07-11ContextpioneerMax output16,384→ 128,000
2026-07-11ContextpioneerMax output128,000→ new
2026-06-30ContextpioneerMax output131,072→ 16,384
2026-06-27Removedchutesofferingremoved→ new
2026-06-08Addedpioneeroffering→ new
2026-05-22Removedscalewayofferingremoved→ new
2026-05-07Addeddigitaloceanoffering→ new
2026-02-18Price cutmeganovainput / 1M$0.14→ $0.02
2026-02-18Price cutmeganovaoutput / 1M$0.14→ $0.04