Catalog Changes · 2026-10-14 00:06:06.820410
NVIDIA: Nemotron 3 Ultra (free) · 2026-10-14 00:06:06.820410 UTC
Current Model ListingKilo
1 Changed Fields
| Field / Array Position | Previous Value | Observed Value |
|---|---|---|
| Preferred Index | Not Reported | 2 |
NVIDIA: Nemotron 3 Ultra (free)
nvidia/nemotron-3-ultra-550b-a55b:free
Kilo Catalog ChangesLast Observed: 2026-10-15 06:04:22.899622 UTC
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).
- Context Tokens: 1000000
- Input Price (Native Units): 0
- Output Price (Native Units): 0
- Output Token Limit: 65536
- Find Similar · At Least This Context And The Same Reported Modality
Architecture And Modalities · 2
Architecture · Modality
API Details/architecture/modality text->text |
text->text |
|---|---|
Architecture · Tokenizer
API Details/architecture/tokenizer Other |
Other |
Catalog Identity And Metadata · 15
Context Tokens
API Details/context_length 1000000 |
1,000,000 |
|---|---|
Created
API Details/created 1780551208 |
2026-06-04 05:33:28 UTC |
Description
API Details/description NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). |
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba…NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). |
Expiration Date
API Details/expiration_date Explicit Null |
Explicit Null |
Id
API Details/id nvidia/nemotron-3-ultra-550b-a55b:free |
nvidia/nemotron-3-ultra-550b-a55b:free |
Is Free
API Details/isFree True |
True |
May Train On Your Prompts
API Details/mayTrainOnYourPrompts True |
True |
Name
API Details/name NVIDIA: Nemotron 3 Ultra (free) |
NVIDIA: Nemotron 3 Ultra (free) |
Opencode · Variants · High · Reasoning · Effort
API Details/opencode/variants/high/reasoning/effort high |
high |
Opencode · Variants · High · Reasoning · Enabled
API Details/opencode/variants/high/reasoning/enabled True |
True |
Opencode · Variants · Medium · Reasoning · Effort
API Details/opencode/variants/medium/reasoning/effort medium |
medium |
Opencode · Variants · Medium · Reasoning · Enabled
API Details/opencode/variants/medium/reasoning/enabled True |
True |
Opencode · Variants · None · Reasoning · Effort
API Details/opencode/variants/none/reasoning/effort none |
none |
Opencode · Variants · None · Reasoning · Enabled
API Details/opencode/variants/none/reasoning/enabled False |
False |
Preferred Index
API Details/preferredIndex 2 |
2 |
Request Limits · 1
Per Request Limits
API Details/per_request_limits Explicit Null |
Explicit Null |
|---|
Pricing · 3
Output Price · USD/Token
API Details/pricing/completion 0 |
0 |
|---|---|
Pricing · Discount
API Details/pricing/discount 0 |
0 |
Input Price · USD/Token
API Details/pricing/prompt 0 |
0 |
Provider Limits · 3
Top Provider · Context Length
API Details/top_provider/context_length 1000000 |
1,000,000 |
|---|---|
Top Provider · Is Moderated
API Details/top_provider/is_moderated False |
False |
Top Provider · Max Completion Tokens
API Details/top_provider/max_completion_tokens 65536 |
65,536 |
API Structure And Container Types
Architecture
API Details/architecture Object · See Fields |
Object · See Fields |
|---|---|
Architecture · Input Modalities
API Details/architecture/input_modalities Array · See Items |
Array · See Items |
Architecture · Output Modalities
API Details/architecture/output_modalities Array · See Items |
Array · See Items |
Opencode
API Details/opencode Object · See Fields |
Object · See Fields |
Opencode · Variants
API Details/opencode/variants Object · See Fields |
Object · See Fields |
Opencode · Variants · High
API Details/opencode/variants/high Object · See Fields |
Object · See Fields |
Opencode · Variants · High · Reasoning
API Details/opencode/variants/high/reasoning Object · See Fields |
Object · See Fields |
Opencode · Variants · Medium
API Details/opencode/variants/medium Object · See Fields |
Object · See Fields |
Opencode · Variants · Medium · Reasoning
API Details/opencode/variants/medium/reasoning Object · See Fields |
Object · See Fields |
Opencode · Variants · None
API Details/opencode/variants/none Object · See Fields |
Object · See Fields |
Opencode · Variants · None · Reasoning
API Details/opencode/variants/none/reasoning Object · See Fields |
Object · See Fields |
Pricing
API Details/pricing Object · See Fields |
Object · See Fields |
Supported Parameters
API Details/supported_parameters Array · See Items |
Array · See Items |
Top Provider
API Details/top_provider Object · See Fields |
Object · See Fields |
Architecture · Input Modalities
1 items · source order preserved
- text
API Details
| Item | /architecture/input_modalities/* |
|---|---|
| 1 | text |
Architecture · Output Modalities
1 items · source order preserved
- text
API Details
| Item | /architecture/output_modalities/* |
|---|---|
| 1 | text |
Supported Parameters
9 items · source order preserved
- include_reasoning
- max_tokens
- reasoning
- reasoning_effort
- seed
- temperature
- tool_choice
- tools
- top_p
API Details
| Item | /supported_parameters/* |
|---|---|
| 1 | include_reasoning |
| 2 | max_tokens |
| 3 | reasoning |
| 4 | reasoning_effort |
| 5 | seed |
| 6 | temperature |
| 7 | tool_choice |
| 8 | tools |
| 9 | top_p |