Home › Compare › Mistral Small vs Mistral Nemo

Mistral Small vs Mistral Nemo

A straight cost comparison of Mistral Small (Mistral AI) and Mistral Nemo (Mistral AI), per 1,000,000 tokens, verified November 2026.

Rate-by-rate comparison

For per-token metrics, the lower number wins. For context window and batch support, the higher or broader option wins. A dash means the provider does not publish that rate: a missing cache-write fee means writes are not billed per token, while a missing cached-input rate means cache hits bill at the full input rate.

Blended cost: 1M input + 250K output

Ten workloads, two bills

The same two models, priced across ten workloads that differ only in their input:output ratio. Nothing else changes — no retries, no system prompt, no middleware.

Mistral Small wins 9 of 10, Mistral Nemo wins 1 of 10. The winner is set by the token mix, not by the headline rate.

Where the two bills cross over

The two models split the token mix. Mistral Small is cheaper per input token ($0.10 vs $0.15 per million), while Mistral Nemo is cheaper per output token ($0.15 vs $0.30). The bills cross at 0.33 output tokens per input token.

Below that ratio — classification, extraction, retrieval, summarisation — Mistral Small wins. Above it — translation, long-form generation, agent loops that write more than they read — Mistral Nemo wins. Most production workloads sit between 0.10 and 1.00 output tokens per input token, which is why Mistral Small is the cheaper answer on a real invoice even when the sticker rate says otherwise.

Cost at four scales

The same support-chat workload (4K input, 600 output per request) at four monthly volumes.

What caching does to each bill

Caching only helps the part of the prompt that repeats. This is the support-chat workload (1,000 requests, 4,000 input tokens each) with an increasing share of that prompt served from a warm cache, written once on the first request.

Both models publish a cached-read rate, so the discount is comparable: Mistral Small reads cache at $0.01 per million, Mistral Nemo at $0.015.

Which one should you pick?

Mistral Small wins on classification, data extraction, support chat, code review, summarisation, agent loop, long-document qa, cached rag, nightly batch, while Mistral Nemo wins on translation.

Beyond price, the two differ on input rate ($0.10 vs $0.15); output rate ($0.30 vs $0.15); cached-input rate ($0.01 vs $0.015); context window (32,000 vs 128,000).

Batch mode is available on Mistral Small and Mistral Nemo, which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.

FAQ

Is Mistral Small cheaper than Mistral Nemo?

On a blended 1M-input-plus-250K-output workload, Mistral Small is cheaper by 7% ($0.175 vs $0.188). The gap changes for cache-heavy prompts and for batch jobs, as the workload table shows.

Which handles longer prompts, Mistral Small or Mistral Nemo?

Mistral Small has the larger context window (128,000 vs 32,000 tokens). Neither model publishes a long-context surcharge.

Do both models support prompt caching?

Mistral Small bills cached reads at $0.01 per 1M; Mistral Nemo at $0.015.

Related comparisons

• Mistral Large vs Mistral Nemo
• GPT-6 Luna vs Mistral Small
• GPT-6 Sol vs Mistral Nemo
• All Mistral AI pricing
• All Mistral AI pricing

Run your own token volumes