Mistral Small 31 24b Instruct
NanoGPT
Mistral Small 31 24b Instruct by NanoGPT costs $0.10 per 1M input tokens and $0.30 per 1M output tokens, with a 128K-token context window.
Pricing
Input (per 1M tokens)
$0.10
Output (per 1M tokens)
$0.30
Cached input (per 1M)
—
Specifications
- Provider
- NanoGPT
- Context window
- 128K tokens
- Parameters
- —
- Released
- Apr 2025
- Open weights
- No
- Frontier model
- No
Benchmarks
- LMArena Vision Elo
- 1136.4
Compare Mistral Small 31 24b Instruct with…
Mistral Small 31 24b Instruct vs MiMo V2.5 Pro$0.87/1MMistral Small 31 24b Instruct vs Llama-xLAM-2 70B fc-r$2.50/1MMistral Small 31 24b Instruct vs MiniMax Latest$1.20/1MMistral Small 31 24b Instruct vs MiniMax M2.5$1.20/1MMistral Small 31 24b Instruct vs MiniMax M2.7 Turbo$2.40/1MMistral Small 31 24b Instruct vs MiniMax 01$1.12/1M
FAQ
How much does Mistral Small 31 24b Instruct cost?
Mistral Small 31 24b Instruct is priced at $0.10 per 1M input tokens and $0.30 per 1M output tokens. Output tokens cost more than input.
What is Mistral Small 31 24b Instruct's context window?
Mistral Small 31 24b Instruct supports a context window of 128K tokens — the maximum prompt plus response length it can handle in a single request.
Is Mistral Small 31 24b Instruct open weight?
No — Mistral Small 31 24b Instruct is a closed/proprietary model accessed via API.
Data as of 2026-06-28. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.