Is Mistral Large cheaper than Mistral Small?

On input tokens, Mistral Small is cheaper ($1.00 vs $4.00 per million). On output tokens, Mistral Small is cheaper. Total cost on a typical workload depends on your input:output ratio.

Which has the larger context window, Mistral Large or Mistral Small?

Mistral Small has a 128,000-token context window. Mistral Large fits 128,000 tokens.

How do I switch from Mistral Large to Mistral Small?

Update the model id in your API call: replace "mistral-large" with "mistral-small". Then verify cost impact on a sample of your real prompts using a token counter.

Mistral Large vs Mistral Small

Side-by-side comparison of Mistral Large (Mistral) and Mistral Small (Mistral). Exact API pricing per million tokens, context windows, output speed, and total cost on real-world prompts.

Specifications

Spec	Mistral Large	Mistral Small
Provider	Mistral	Mistral
Model id	mistral-large	mistral-small
Input price (per 1M tokens)	$4.00	$1.00
Output price (per 1M tokens)	$12.00	$3.00
Context window	128,000	128,000
Output speed (tokens/sec)	~55	~110

Cost on real prompts

Total cost = (input tokens × input price) + (output tokens × output price). Numbers below use the exact pricing tables published by each provider.

Scenario	Input	Output	Mistral Large	Mistral Small	Cheaper
Short question + answer	50	150	$0.002000	$0.0005	Mistral Small
Code review on one file	500	1,500	$0.020000	$0.005000	Mistral Small
Long document summary	5,000	500	$0.026000	$0.006500	Mistral Small
Heavy reasoning task	2,000	8,000	$0.104000	$0.026000	Mistral Small
Full codebase analysis	50,000	10,000	$0.320000	$0.080000	Mistral Small

Want the exact cost for your prompt instead of these examples? Open the cost calculator pre-loaded with both models →

When to pick which

Heuristics derived from the spec table above. Always validate on your own prompts before committing — these are starting points, not verdicts.

Pick Mistral Large for

No clear advantage on the data points we measure. Compare on your actual prompts.

Pick Mistral Small for

•output-heavy workloads — mistral-small is meaningfully cheaper per output token
•input-heavy workloads — mistral-small is cheaper per input token
•latency-sensitive UX — mistral-small streams faster (~110 vs ~55 tok/s)

Switching between them

For most use cases, switching providers means updating the model id and the request shape if the providers differ. Within the same provider, it's usually a single-line change.

From Mistral Large to Mistral Small

# Before
model = "mistral-large"

# After
model = "mistral-small"

If the providers differ (Mistral vs Mistral), you'll also need to swap the SDK / endpoint URL. Cross-provider migrations usually take 30 minutes to a few hours depending on how many features (streaming, function calling, tool use) you depend on.

Calculate cost on your own prompt

The examples above use generic input/output ratios. For an exact comparison, paste your real prompt into the calculator — it counts tokens with the right tokenizer for each model and shows side-by-side cost.

Open the calculator with both models →