Skip to content

Commit c8aa264

Browse files
models-bot[bot]Truefoundry Models Bot
andauthored
feat(deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B): add new models [bot] (#1277)
* feat(deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B): add new models [bot] * feat(deepinfra): update model YAMLs [bot] --------- Co-authored-by: Truefoundry Models Bot <truefoundry-models-bot@users.noreply.github.com>
1 parent a62126b commit c8aa264

1 file changed

Lines changed: 25 additions & 0 deletions

File tree

Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
costs:
2+
- cache_read_input_token_cost: 1.5e-7
3+
input_cost_per_token: 5e-7
4+
output_cost_per_token: 2.5e-6
5+
region: "*"
6+
features:
7+
- prompt_caching
8+
- function_calling
9+
- json_output
10+
limits:
11+
context_window: 262144
12+
max_tokens: 262144
13+
modalities:
14+
input:
15+
- text
16+
output:
17+
- text
18+
mode: chat
19+
model: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
20+
sources:
21+
- https://deepinfra.com/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
22+
status: active
23+
supportedModes:
24+
- chat
25+
thinking: true

0 commit comments

Comments
 (0)