API cost decision in 10 seconds

NewMistral Medium 3.5 vs Mistral Small 4

Pick Mistral Small 4 when budget is the priority.

Page updated: 2026-05-26T10:03:26Z Data confirmed: 2026-05-26T13:08:02Z Prices normalized to USD per 1M tokens Sample workload: 1M input + 500K output

Budget verdict

Pick Mistral Small 4 when budget is the priority.

On the standard 1M input plus 500K output workload, Mistral Small 4 is estimated at $0.45 vs $5.25 for Mistral Medium 3.5, saving $4.8 (91.4% lower).

Cost-first pickMistral Small 4

Context-first pickBoth models

Sample savings$4.891.4%

10x traffic gap$48

The reported context window is tied, so cost and provider fit carry more weight. At 10x that traffic, the same price gap is about $48. Use the calculator below to replace the sample workload with your own token volume.

Cost sensitivity

Workload Sensitivity

Same prices, different token mixes.

Mistral Small 4 stays cheaper across input-heavy, balanced, and output-heavy sample workloads.

Workload shape	Token mix	Better pick	Mistral Medium 3.5	Mistral Small 4
Input-heavy / RAG	5M input + 500K output	Mistral Small 4	$11.25	$1.05
Balanced workload	1M input + 1M output	Mistral Small 4	$9	$0.75
Output-heavy chatbot	1M input + 5M output	Mistral Small 4	$39	$3.15

Cheaper input Mistral Small 4 $1.5 vs $0.15 / 1M

Mistral Small 4 is $1.35 cheaper per 1M input tokens (90% lower; 10x difference).

Cheaper output Mistral Small 4 $7.5 vs $0.6 / 1M

Mistral Small 4 is $6.9 cheaper per 1M output tokens (92% lower; 12.5x difference).

Larger context Tie 262.14K vs 262.14K

Both models report the same context window at 262.14K tokens.

Sample workload Mistral Small 4 $5.25 vs $0.45

Mistral Small 4 is $4.8 cheaper on the standard workload (91.4% lower).

Estimate your workload cost

Your Workload Cost

Prices are normalized to USD per 1M tokens.

Monthly input tokens Monthly output tokens

Mistral Medium 3.5 Calculating… Estimated API cost

Mistral Small 4 Calculating… Estimated API cost

Cheaper for this workload Calculating… Difference: calculating…

This estimate uses normalized public API pricing per 1M tokens. It is a planning aid, not a billing quote. Verify provider pricing, limits, and terms before production use.

Quick Decision

Verdict

Mistral Small 4 has the lower input price; Mistral Small 4 has the lower output price; both models report the same context window. For the 1M input plus 500K output sample, Mistral Small 4 is cheaper for the standard workload.

For a 1M input token plus 500K output token workload, the estimated API cost is $5.25 for Mistral Medium 3.5 and $0.45 for Mistral Small 4.

Best Fit

Choose Mistral Medium 3.5 when its provider, model quality, latency, or availability is more important than the numeric price/context winner.

Choose Mistral Small 4 when you care most about lower input-token price, and lower output-token price.

Decision Notes

On the standard 1M input plus 500K output workload, Mistral Small 4 is estimated at $0.45 vs $5.25 for Mistral Medium 3.5, saving $4.8 (91.4% lower).
Mistral Small 4 is $4.8 cheaper on the standard workload (91.4% lower).
Mistral Small 4 is $1.35 cheaper per 1M input tokens (90% lower; 10x difference).
Mistral Small 4 is $6.9 cheaper per 1M output tokens (92% lower; 12.5x difference).
Both models report the same context window at 262.14K tokens.

Head-to-Head Specs

Feature	NewMistral Medium 3.5 (Mistral)	Mistral Small 4 (Mistral)
Input Price prompt tokens per 1M	$1.5	$0.15
Completion Price per 1M tokens	$7.5	$0.6
Sample Workload Cost 1M input + 500K output	$5.25	$0.45
Context Window	262.14K	262.14K
Release Date	2026-04-30	2026-03-16

Use-Case Decision Matrix

Use case	Better pick	Why
Budget-constrained production	Mistral Small 4	On the standard 1M input plus 500K output workload, Mistral Small 4 is estimated at $0.45 vs $5.25 for Mistral Medium 3.5, saving $4.8 (91.4% lower).
High-volume input processing	Mistral Small 4	Lower prompt-token price matters most when prompts, retrieved passages, or documents dominate the bill.
Long responses and chatbots	Mistral Small 4	Lower output-token price matters most when assistants generate many completion tokens.
RAG or long-document work	Tie	A larger context window leaves more room for retrieved passages, conversation history, or source files.

Related Alternatives

Same-provider lower-cost swaps

Mistral Nemo can replace Mistral Medium 3.5 when lower sample workload cost matters most: $0.04.
Mistral Small 3 can replace Mistral Medium 3.5 when lower sample workload cost matters most: $0.09.
Ministral 3 3B 2512 can replace Mistral Medium 3.5 when lower sample workload cost matters most: $0.15.
Mistral Small 3.2 24B can replace Mistral Medium 3.5 when lower sample workload cost matters most: $0.17.

Larger context near this budget

Llama 4 Scout offers 10M context with $0.23 sample workload cost.
Grok 4.20 Multi-Agent offers 2M context with $5 sample workload cost.
Grok 4.20 offers 2M context with $2.5 sample workload cost.
Owl Alpha offers 1.05M context with $0 sample workload cost.

Popular competitors

DeepSeek V4 Flash · DeepSeek · #1
Hy3 preview · Tencent · #2
Claude Opus 4.7 · Anthropic · #3
Claude Sonnet 4.6 · Anthropic · #4

Cheaper alternatives

Review low-cost models sorted by a standard 1M input plus 500K output workload.

Open cheapest models

Larger context alternatives

Find models with larger context windows for RAG, long documents, and codebase review.

Open largest context models

Provider catalogs

Compare models within provider hubs before choosing a final API vendor.

Open provider hubs

Mistral catalog

Review all tracked Mistral models before deciding whether this matchup is the right shortlist.

Open Mistral models

Mistral Medium 3.5

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

Mistral Small 4

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...