Compositev12
← All models Model directory

AI model

Mistral: Mistral Nemo

mistralai/mistral-nemo

Mistral: Mistral Nemo is a 131,072-token model served on Composite at $0.0207 per million tokens in and $0.0270 per million tokens out. Ranked #28 of 196 models by traffic on Composite over the last 30 days, taking 0.57% of tokens and 0.88% of requests (this model and its routing variants). Measured on Composite, 100.0% of its last 20 requests on Composite succeeded, the typical first token arrives in 1786 ms, output runs at about 55.9 tokens per second.

Try in Playground

Community rating

— No community ratings yet.

Sign in to rate this model. Ratings come from accounts that have run requests through Composite.

Specifications

Specifications and pricing as served by Composite
Model IDmistralai/mistral-nemo
Providercv11
Context window131,072 tokens
Acceptstext
Returnstext
Input price$0.0207 per million tokens
Output price$0.0270 per million tokens
Prompt cachingSupported — cached input is billed at the provider's cache rate, on credits and plans alike
ModeratedNo
Cost on a monthly planAbout 0.1 plan credits per typical call (8k in, 1k out)
Routing endpoints10 (base plus 9 routing variants)

Traffic rank on Composite

#28 of 196

0.57% of tokens and 0.88% of requests over 30 days, including routing variants.

Success rate

100.0%

Across the last 20 requests Composite served for this model.

Time to first token

1786 ms

Median across the same sample.

Output speed

55.9 tok/s

Median generation rate after the first token.

Routing variants

The same model behind 9 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.

RouteModel IDProviderPrice
Normal mistralai/mistral-nemo-normal cv11 $0.0363 per million tokens input · $0.0375 per million tokens output
Normal + cheapThink mistralai/mistral-nemo-normal:cheapThink cv11 $0.0363 per million tokens input · $0.0375 per million tokens output
Cheapest provider mistralai/mistral-nemo:cheapest-provider Io Net $0.0207 per million tokens input · $0.0270 per million tokens output
Cheapest provider + cheapThink mistralai/mistral-nemo:cheapest-provider:cheapThink Io Net $0.0207 per million tokens input · $0.0270 per million tokens output
cheapThink mistralai/mistral-nemo:cheapThink cv11 $0.0207 per million tokens input · $0.0270 per million tokens output
Fast mistralai/mistral-nemo:fast Io Net $0.0207 per million tokens input · $0.0270 per million tokens output
Fast + cheapThink mistralai/mistral-nemo:fast:cheapThink Io Net $0.0207 per million tokens input · $0.0270 per million tokens output
Quality mistralai/mistral-nemo:quality Io Net $0.0207 per million tokens input · $0.0270 per million tokens output
Quality + cheapThink mistralai/mistral-nemo:quality:cheapThink Io Net $0.0207 per million tokens input · $0.0270 per million tokens output

Pricing

$0.0207 per million tokens input · $0.0270 per million tokens output

Credits pay the provider’s price plus 25%; cache hits cost less.

On a monthly plan, a typical call (8k tokens in, 1k out) uses about 0.1 plan credits, at the provider's own price.

Provider

cv11

Roleplay fit

Mistral models are compact and fast, a good fit when reply speed matters more than maximum context length.

Context behavior

With a 131,072-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.

Cost for regular use

It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.

From the provider

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

Supplied by cv11, not written by Composite.