Start free trial

NVIDIA: Nemotron 3 Ultra (free)

nvidia/nemotron-3-ultra-550b-a55b-free
CompareAPITry this model

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Modalities
In / out per 1MFree / Free
Context1M
ReleasedJun 4, 2026

Providers

5 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Basetenus · fp4$0.60$2.40$0.120.27s115 tps100%
DeepInfraus · fp4$0.50$2.20$0.101.23s39 tps100%
Basetenfp4$0.60$2.40$0.120.23s120 tps100%
DeepInfraus · fp4$0.40$1.76$0.08——100%
Venicefp8$0.63$3.13$0.191.09s46 tps99.83%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Nemotron 3 Ultra (free) in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Nemotron 3 Ultra (free) costs pay-as-you-go elsewhere, not what you pay here.

Input
Free
per 1M tokens
Output
Free
per 1M tokens
Cache read
—
not published
Included in every pass
Nemotron 3 Ultra (free) is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s2.5s5.0s7.5s10.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AMNov 1, 4 PM
DeepInfra (us) Venice DeepInfra (us) Baseten Baseten (us)
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AMNov 1, 4 PM
DeepInfra (us) Venice DeepInfra (us) Baseten Baseten (us)

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.99%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.99%
100% 98% 97% 95%
Oct 31, 6:10 PMNow

Apps

Tools that most often run Nemotron 3 Ultra (free), by tokens this week.

Hermes AgentPersonal Agent · 28.2% of tokens8.0BOpenClawPersonal Agent · 22.9% of tokens6.5Buse.ai clone22% of tokens6.2Bcyber-train nexus eval14.9% of tokens4.2BPortkey AIProgramming App · 12% of tokens3.4B

Activity

159.0B tokens processed market-wide in the last month.

02.5B5.0B7.5B10.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens

FAQ

Which model id do I use for Nemotron 3 Ultra (free)?
nvidia/nemotron-3-ultra-550b-a55b:free. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Nemotron 3 Ultra (free) hold?
1,000,000 tokens per request, of which up to 65,536 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Nemotron 3 Ultra (free) cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at Free per 1M input tokens and Free per 1M output tokens.
Who built Nemotron 3 Ultra (free)?
NVIDIA, in the Nemotron family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion