Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Model comparison · Updated 2 Nov 2026

Llama 4 Maverick vs Mistral Small 4

Mistral Small 4 is about 1.3× cheaper on input ($0.15 against $0.19 per 1M tokens) and on output. Llama 4 Maverick has the larger context window (524K against 262K tokens). For a support chatbot at 10,000 chats a day, the standard-tier bill is about $143 a month for Llama 4 Maverick and $122 for Mistral Small 4.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “Llama 4 Maverick vs Mistral Small 4”. Retrieved 2 Nov 2026. https://modelsatlas.com/compare/meta/llama-4-maverick/vs/mistralai/mistral-small

Model A

Llama 4 Maverick

by Meta · weights not marked open · GRIDC4

Input / 1M
$0.19
observed We measured
Source
Our catalogue
Retrieved
10 Oct 2026
Output / 1M$0.65
Context524K
vs

Model B

Mistral Small 4

by Mistral AI · weights not marked open · GRIDC4

Input / 1M
$0.15
observed We measured
Source
Our catalogue
Retrieved
17 Aug 2026
Output / 1M$0.60
Context262K

Key numbers

Standard tier · highlighted = better

Llama 4 Maverick
Mistral Small 4
Input / 1M tokens
$0.19
$0.15
Output / 1M tokens
$0.65
$0.60
Batch input / output
Not listed
Not listed
Context window
524,288
262,144
Input types
Not disclosed
Not disclosed
Weights
Not marked open
Not marked open
Tiers listed
standard
standard
Prices checked
2026-11-02
2026-10-10

What it costs for real workloads

Monthly, standard tier, 30 days

Support chatbot10k chats/day · 1.5k in, 300 out
$143/mo
$122/mo
RAG over documents2k queries/day · 12k in, 500 out
$155/mo
$126/mo
Coding agent300 tasks/day · 60k in, 8k out
$148/mo
$124/mo

Llama 4 Maverick   Mistral Small 4 · Derived from the standard-tier prices above, input and output tokens per request as stated, 30 days. Excludes caching discounts and batch. Try your own numbers.

On the atlas

Price band (A–H) × context band (1–6)

Same square. Llama 4 Maverick and Mistral Small 4 share C4.

Same square as Llama 4 Maverick: Qwen3 30B A3B Instruct 2507 ($0.10), Qwen3.6 35B A3B ($0.10), Qwen3 Coder Next ($0.12). Open C4

AFreeB<$0.10C$0.10–0.30D$0.30–1E$1–3F$3–10G$10–30H$30+1<32K232–128K3128–256K4256K–1M51M6>1MINPUT PRICE PER 1M TOKENS →CONTEXT WINDOW ↑ · position within a square follows the real valueGemma 4 31B · C4Ministral 3 14B 2512 · C4Qwen3.5-9B · C4Qwen3 VL 235B A22B Instruct · C4Ministral 3 8B 2512 · C4Qwen3 Coder 30B A3B Instruct · C4Qwen3 VL 30B A3B Instruct · C4Qwen3.5-35B-A3B · C4Qwen3 Coder Next · C4Llama 4 MaverickLlama 4 MaverickMistral Small 4Mistral Small 4
Llama 4 MaverickMistral Small 4Nearest neighboursOpen weights
View the map as a table (1 squares)
SquarePrice bandContext bandModels
GRIDC4$0.10–0.30256K–1MLlama 4 Maverick, Mistral Small 4, Gemma 4 31B, Ministral 3 14B 2512, Qwen3.5-9B, Qwen3 VL 235B A22B Instruct, Ministral 3 8B 2512, Qwen3 Coder 30B A3B Instruct, Qwen3 VL 30B A3B Instruct, Qwen3.5-35B-A3B, Qwen3 Coder Next

Capabilities side by side

Only what our records list

Llama 4 Maverick
Mistral Small 4
Vision input
Not disclosed
Not disclosed
Audio input
Not disclosed
Not disclosed
Open weights
Not marked open
Not marked open
Batch tier
Not listed
Not listed
Free tier
Not listed
Not listed
Thinking tier
Not listed
Not listed

Neither record lists input types, so we do not claim any.

Which should you choose?

Editorial

Choose Llama 4 Maverick if…

  • your prompts are long: it takes 524,288 tokens against 262,144

Choose Mistral Small 4 if…

  • you pay by the token: it costs $0.15 per 1M input against $0.19
  • output dominates your bill: $0.60 per 1M output against $0.65

Each reason is a fact from the tables above. Picking between them is our judgement, and we do not benchmark quality: price and context are what we can measure, so test both on your own prompts before you commit.

Questions

Is Llama 4 Maverick better than Mistral Small 4?
We do not benchmark quality, so we cannot say. On the recorded numbers: Mistral Small 4 is about 1.3× cheaper on input ($0.15 against $0.19 per 1M tokens) and on output. Llama 4 Maverick has the larger context window (524K against 262K tokens). For a support chatbot at 10,000 chats a day, the standard-tier bill is about $143 a month for Llama 4 Maverick and $122 for Mistral Small 4. Which is better for you depends on your task; test both on your own prompts.
Which is cheaper, Llama 4 Maverick or Mistral Small 4?
Mistral Small 4: $0.15 against $0.19 per 1M input tokens, and $0.60 against $0.65 per 1M output, on standard pricing.
How much does each cost per 1M tokens?
Llama 4 Maverick: $0.19 input and $0.65 output. Mistral Small 4: $0.15 input and $0.60 output. Standard tier, USD.
Which has the larger context window?
Llama 4 Maverick, with 524,288 tokens. Mistral Small 4 has 262,144 tokens.
Do both offer batch pricing?
Neither lists a batch tier in our catalogue.
Can both read images or audio?
Input types recorded for Llama 4 Maverick: none recorded. For Mistral Small 4: none recorded. Where a record lists none we say so rather than guess; check each vendor's documentation before relying on a capability.
Is either model open-weight?
Llama 4 Maverick: not marked open-weight in our records. Mistral Small 4: not marked open-weight in our records.
What would each cost for a support chatbot?
At 10,000 chats a day, 1,500 input and 300 output tokens each, 30 days, standard tier: about $143 a month for Llama 4 Maverick and $122 for Mistral Small 4. This is our calculation from the listed prices, not a quote.

About the two models

Llama 4 Maverick

By Meta. $0.19 input and $0.65 output per 1M tokens, 524K context, atlas square C4. Tiers listed: standard.

Full specs & pricing →

Mistral Small 4

By Mistral AI. $0.15 input and $0.60 output per 1M tokens, 262K context, atlas square C4. Tiers listed: standard.

Full specs & pricing →

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.