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
DeepInfraus · fp4$0.40$1.76$0.088.94s40 tps100%
Basetenus · fp4$0.60$2.40$0.120.32s118 tps100%
Basetenfp4$0.60$2.40$0.120.31s108 tps100%
Venicefp8$0.63$3.13$0.191.55s81 tps100%
DeepInfraus · fp4$0.50$2.20$0.101.44s85 tps99.95%

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.

0.0s5.0s10.0s15.0s20.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Venice DeepInfra (us) Baseten Baseten (us) DeepInfra (us)
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Venice DeepInfra (us) Baseten Baseten (us) DeepInfra (us)

Uptime

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

Last 3 daysAvailability 99.94%
Oct 16, 10:00 AMNow
Availability over the last 24 hoursAvailability 99.95%
100% 98% 97% 95%
Oct 18, 10:20 AMNow

Apps

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

Hermes AgentPersonal Agent · 31.1% of tokens7.8BClaude CodeCli Agent · 26% of tokens6.5BPortkey AIProgramming App · 16.1% of tokens4.0BNous Research APIGeneral Chat · 13.6% of tokens3.4Buse.ai clone13.2% of tokens3.3B

Activity

126.3B tokens processed market-wide in the last month.

02.0B4.0B6.0B8.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
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 http://192.168.1.55/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