LiteLLMModels

Cosmos3 Super Reasoner API Pricing

As of October 10, 2026, Cosmos3 Super Reasoner costs $0.10 per 1M input tokens and $0.30 per 1M output tokens on Nebius AI Studio. It has a 262,144-token context window and returns up to 262,144 tokens per response.

By NVIDIAModel ID nebius/nvidia/Cosmos3-Super-ReasonerPrices updated Checked
Input
$0.10 / 1M tokens
Output
$0.30 / 1M tokens
Context window
262,144 tokens
Max output
262,144 tokens
Providers
1
Added to LiteLLM
September 3, 2026

Cosmos3 Super Reasoner pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputContext
Nebius AI Studionebius/nvidia/Cosmos3-Super-Reasoner$0.10$0.30256K

What Cosmos3 Super Reasoner costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Nebius AI Studio$0.35

100 long-document requests with 100,000 input and 2,000 output tokens each

Nebius AI Studio$1.06

Cosmos3 Super Reasoner features

Use Cosmos3 Super Reasoner with LiteLLM

Call Cosmos3 Super Reasoner through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="nebius/nvidia/Cosmos3-Super-Reasoner",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: cosmos3-super-reasoner
    litellm_params:
      model: nebius/nvidia/Cosmos3-Super-Reasoner
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "cosmos3-super-reasoner",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Cosmos3 Super Reasoner FAQ

How much does Cosmos3 Super Reasoner cost?

Cosmos3 Super Reasoner costs $0.10 per 1M input tokens and $0.30 per 1M output tokens on Nebius AI Studio.

What is the context window of Cosmos3 Super Reasoner?

Cosmos3 Super Reasoner has a 262,144-token context window and returns up to 262,144 tokens per response.

Which providers offer Cosmos3 Super Reasoner?

Cosmos3 Super Reasoner is available from Nebius AI Studio through LiteLLM, using the model name nebius/nvidia/Cosmos3-Super-Reasoner.

How do I call Cosmos3 Super Reasoner with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="nebius/nvidia/Cosmos3-Super-Reasoner", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Cosmos3 Super Reasoner support?

Cosmos3 Super Reasoner supports function calling, image input and reasoning.

When did LiteLLM add Cosmos3 Super Reasoner?

Cosmos3 Super Reasoner was added to LiteLLM's model price file on September 3, 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Nebius AI Studio.

Provider pages: Nebius AI Studio.