NVIDIA: Cosmos Reason2 8B
Cosmos Reason2 8B is a reasoning model from NVIDIA released on Dec 1, 2025. It reads text, images and video and writes text, with a 131K token context window and up to 16K tokens per reply.
Show moreShow less
It costs $0 per million input tokens and $0 per million output tokens.
It supports tool calling, and its weights are open, so you can host it yourself.
- Modalities
- In / out price
- $0 / $0 per 1M
- Context
- 131K
- Max output
- 16K
- Released
- Dec 1, 2025
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Cosmos Reason2 8B pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0 / 1M tokens | |
|---|---|---|
| Output | $0 / 1M tokens |
What Cosmos Reason2 8B costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Cosmos Reason2 8B through an OpenAI compatible API.
- Tools
tools - Reasoning
reasoning - Temperature
temperature
Alternatives to Cosmos Reason2 8B
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- 1.05M context
Reads text, images and video. Tool calling, reasoning.
by nvidiaOct 15, 2026$0/M input tokens$0/M output tokens
- 1.05M context
Reads text, images and video. Tool calling, reasoning. Served by 2 providers.
by moonshotaiSep 11, 2026$0/M input tokens$0/M output tokens2 providers
- 256K context
Reads text, images and video. Tool calling, reasoning.
by nvidiaApr 2, 2026$0/M input tokens$0/M output tokens
- 262K context
Reads text, images and video. Tool calling, reasoning. Served by 2 providers.
by qwenNov 1, 2025$0/M input tokens$0/M output tokens2 providers
- 1M context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 12 providers.
by qwenJul 15, 2026$0.03/M input tokens$0.13/M output tokens12 providers
- 128K context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 6 providers.
by z-aiDec 8, 2025$0.0218/M input tokens$0.2184/M output tokens6 providers
More from NVIDIA
- 1.05M context
Reads text, images and video. Tool calling, reasoning.
by nvidiaOct 15, 2026$0/M input tokens$0/M output tokens
- Index 12.9
Reads text. Tool calling, structured output, reasoning. Served by 3 providers.
by nvidiaAug 11, 2026262K context$0/M input tokens$0/M output tokens3 providers
- 262K context
Reads text. Tool calling, structured output, reasoning. Served by 9 providers.
by nvidiaAug 11, 2026$0.05/M input tokens$0.20/M output tokens9 providers
- Index 22.9
Reads text. Tool calling, structured output, reasoning. Served by 18 providers.
by nvidiaJun 4, 20261M context$0.50/M input tokens$2.50/M output tokens18 providers
- 128K context
Reads text and images. Reasoning. Served by 6 providers.
by nvidiaJun 4, 2026$0.05/M input tokens$0.15/M output tokens6 providers
- 256K context
Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 7 providers.
by nvidiaApr 28, 2026$0.10/M input tokens$0.25/M output tokens7 providers
Cosmos Reason2 8B questions
How much does the Cosmos Reason2 8B API cost?
$0 per million input tokens and $0 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Cosmos Reason2 8B?
131,072 tokens of input, and it can write up to 16,384 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Does Cosmos Reason2 8B support tool calling?
Yes. It accepts tool definitions, which is what an agent needs to call your APIs.
Is Cosmos Reason2 8B open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Cosmos Reason2 8B released?
Dec 1, 2025.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Cosmos Reason2 8B?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting