NVIDIA NIM
Inference cloud
- Catalog status
- List checked 24m ago
- Last successful check
- 2026-11-20 (24m ago)
- Latest attempt
- 24m ago: succeeded
"List checked" means we fetched the provider's model list in the last 3 hours. That shows the list is reachable and current, not that inference works.
Free quota
Free
Free API access
- Kind
- Recurring
- Credit
- Not documented
- Tokens granted
- Not documented
- Expires after
- Not documented
- Renews every
- Not documented
- Card required
- No
- Phone required
- Not documented
- Trains on prompts
- Yes
- Commercial use
- No
- Eligibility
- NVIDIA Developer Program members of legal adult age
- Note
- NVIDIA states up to 40 RPM and 10,000 requests per day; limits may vary by model and traffic from other users. Trial access for prototyping, research, development and testing only, not production. Production use needs an NVIDIA AI Enterprise license. Do not submit confidential or sensitive data.
- Source
- Provider page, checked 2026-11-01
| Limits | Per minute | Per day | Per month |
|---|---|---|---|
| Requests | 40 | 10,000 | Not documented |
| Tokens | Not documented | Not documented | Not documented |
Models covered
z-ai/glm-5.3-flashnvidia/nemotron-3.5-super-vl-120b-a12bstepfun-ai/step-5-previewnvidia/nemotron-3-ultra-550b-a55bpoolside/laguna-xs-2.1meta/muse-glimmer-30bnvidia/nemotron-3-super-120b-a12bnvidia/nemotron-3-nano-omni-30b-a3b-reasoningnvidia/nemotron-3.5-lightning-30b-a3bdeepseek-ai/deepseek-v4.1-flashopenai/gpt-oss-20bgoogle/gemma-4-31b-itgoogle/diffusiongemma-26b-a4b-it
How to call it
- OpenAI-compatible
- Yes, Chat Completions at the base URL
- Base URL
https://integrate.api.nvidia.com/v1
curl "https://integrate.api.nvidia.com/v1/chat/completions" \
-H "Authorization: Bearer $NVIDIA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "bigcode/starcoder2-15b", "messages": [{"role": "user", "content": "Hello"}]}'
Models
| Model ID | Comparison key | Input $/1M | Output $/1M | Price checked |
|---|---|---|---|---|
bigcode/starcoder2-15b |
unknown | unknown | — | |
fastino/gliner2-pii |
unknown | unknown | — | |
google/gemma-3-12b-it |
google/gemma-3-12b-it |
$0 | $0 | models.dev, synced 13h ago |
google/gemma-3-4b-it |
google/gemma-3-4b-it |
$0 | $0 | models.dev, synced 13h ago |
google/gemma-4-31b-it |
google/gemma-4-31b-it |
$0 | $0 | models.dev, synced 13h ago |
meta/muse-glimmer-30b |
meta/muse-glimmer-30b |
$0 | $0 | models.dev, synced 13h ago |
minimaxai/minimax-m3.1-flash |
minimax/MiniMax-M3.1-Flash |
$0 | $0 | models.dev, synced 13h ago |
mistralai/mistral-large-4-1t-a52b |
unknown | unknown | — | |
moonshotai/kimi-k3.1-pro |
unknown | unknown | — | |
nvidia/ai-synthetic-video-detector |
unknown | unknown | — | |
nvidia/cosmos-reason2-8b |
$0 | $0 | models.dev, synced 13h ago | |
nvidia/embed-qa-4 |
unknown | unknown | — | |
nvidia/ising-calibration-1.5-31b |
unknown | unknown | — | |
nvidia/llama-3.1-nemoguard-8b-topic-control |
unknown | unknown | — | |
nvidia/llama-3.1-nemotron-safety-guard-8b-v3 |
nvidia/llama-3.1-nemotron-safety-guard-8b-v3 |
$0 | $0 | models.dev, synced 13h ago |
nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1 |
unknown | unknown | — | |
nvidia/llama-3.2-nv-embedqa-1b-v1 |
unknown | unknown | — | |
nvidia/nemotron-3-embed-1b |
unknown | unknown | — | |
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning |
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning |
$0 | $0 | models.dev, synced 13h ago |
nvidia/nemotron-3-ultra-550b-a55b |
nvidia/nemotron-3-ultra-550b-a55b |
$0 | $0 | models.dev, synced 13h ago |
nvidia/nemotron-3.5-bolt-e4b |
unknown | unknown | — | |
nvidia/nemotron-3.5-content-safety |
nvidia/nemotron-3.5-content-safety |
$0 | $0 | models.dev, synced 13h ago |
nvidia/nemotron-3.5-embed-1b |
unknown | unknown | — | |
nvidia/nemotron-3.5-embed-8b |
unknown | unknown | — | |
nvidia/nemotron-3.5-lightning-30b-a3b |
nvidia/nemotron-3.5-lightning |
$0 | $0 | models.dev, synced 13h ago |
nvidia/nemotron-3.5-super-vl-120b-a12b |
nvidia/nemotron-3.5-super-vl-120b-a12b |
$0 | $0 | models.dev, synced 13h ago |
nvidia/nv-embedqa-mistral-7b-v2 |
unknown | unknown | — | |
nvidia/nvclip |
unknown | unknown | — | |
nvidia/riva-translate-4b-instruct-v2 |
unknown | unknown | — | |
poolside/laguna-xs-2.1 |
poolside/laguna-xs-2.1 |
$0 | $0 | models.dev, synced 13h ago |
snowflake/arctic-embed-l |
unknown | unknown | — | |
stepfun-ai/step-5-preview |
stepfun/step-5-preview |
$0 | $0 | models.dev, synced 13h ago |
z-ai/glm-5.3-flash |
zhipuai/glm-5.3-flash |
$0 | $0 | models.dev, synced 13h ago |
Offers needing attention
These offers and free-tier model IDs are no longer in the active list.
deepseek-ai/deepseek-v4.1-flashgoogle/diffusiongemma-26b-a4b-itnvidia/nemotron-3-super-120b-a12bopenai/gpt-oss-20bz-ai/glm-5.3