Free NVIDIA NIM API Key, Base URL & Rate Limits
API ProviderNVIDIA NIM (NVIDIA Inference Microservices) provides API access to 100+ open-weight models hosted on NVIDIA infrastructure.
OpenAI CompatibleFree TierStreamingFunction CallingVision
How to get a free NVIDIA NIM API key
- 1
- 2 Go to Settings → API Keys
- 3 Generate an API key
- 4 Browse available models 100+ open models. Nemotron Super 49B recommended.
- 5 Configure OpenAI client Base URL: https://integrate.api.nvidia.com/v1
Provider Snapshot
Provider Type API Provider
OpenAI Compatible Yes
Base URL https://integrate.api.nvidia.com/v1
Free Tier 80 free models online
Phone Required Yes
Streaming Yes
Function Calling Yes
Vision Yes
Last Updated 2026-08-06
Supported Models 80 models
View in directory →| Model ID | Developer | Context | Availability | Free Tier | Use cases |
|---|---|---|---|---|---|
| moonshotai/kimi-k3 Kimi K3 | Kimi | 1.0M | Online | Yes | chat |
| deepseek-ai/deepseek-v4-flash-0731 deepseek-ai/deepseek-v4-flash | DeepSeek | 1.0M | Online | Yes | chat |
| minimaxai/minimax-m3 minimaxai/minimax-m3 | MiniMax | 1.0M | Online | Yes | chat |
| deepseek-ai/deepseek-v4-pro-0813 deepseek-ai/deepseek-v4-pro | DeepSeek | 1.0M | Online | Yes | chat |
| moonshotai/kimi-k2.6 moonshotai/kimi-k2.6 | Kimi | 262K | Online | Yes | chat |
| nvidia/nemotron-3-ultra-550b-a55b Nemotron 3 Ultra 550B A55B | NVIDIA NIM | 1.0M | Online | Yes | chat |
| poolside/laguna-xs-2.1 poolside/laguna-xs-2.1 | NVIDIA NIM | 262K | Online | Yes | chat |
| google/gemma-4-31b-it Gemma 4 31B IT | NVIDIA NIM | 262K | Online | Yes | chat |
| 01-ai/yi-large 01-ai/yi-large | NVIDIA NIM | 131K | Online | Yes | chat |
| meta/codellama-70b meta/codellama-70b | NVIDIA NIM | 131K | Online | Yes | chatcoding |
| nvidia/llama3-chatqa-1.5-70b nvidia/llama3-chatqa-1.5-70b | NVIDIA NIM | 131K | Online | Yes | chat |
| writer/palmyra-fin-70b-32k writer/palmyra-fin-70b-32k | NVIDIA NIM | 131K | Online | Yes | chat |
| writer/palmyra-med-70b writer/palmyra-med-70b | NVIDIA NIM | 131K | Online | Yes | chat |
| writer/palmyra-med-70b-32k writer/palmyra-med-70b-32k | NVIDIA NIM | 131K | Online | Yes | chat |
| meta/muse-glimmer-30b Muse Glimmer 30B | NVIDIA NIM | 131K | Online | Yes | chat |
| nvidia/llama-3.1-nemotron-ultra-253b-v1 nvidia/llama-3.1-nemotron-ultra-253b-v1 | NVIDIA NIM | 131K | Online | Yes | chatreasoning |
| ibm/granite-34b-code-instruct ibm/granite-34b-code-instruct | NVIDIA NIM | 131K | Online | Yes | chatcoding |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA NIM | 256K | Online | Yes | chat |
| nvidia/nemotron-3-super-120b-a12b Nemotron 3 Super 120B A12B | NVIDIA NIM | 262K | Online | Yes | chat |
| bigcode/starcoder2-15b bigcode/starcoder2-15b | NVIDIA NIM | 131K | Online | Yes | chatcoding |
| google/deplot google/deplot | NVIDIA NIM | 131K | Online | Yes | chat |
| google/gemma-2b google/gemma-2b | NVIDIA NIM | 131K | Online | Yes | chat |
| google/recurrentgemma-2b google/recurrentgemma-2b | NVIDIA NIM | 131K | Online | Yes | chat |
| microsoft/kosmos-2 microsoft/kosmos-2 | NVIDIA NIM | 131K | Online | Yes | chat |
| microsoft/phi-3-vision-128k-instruct microsoft/phi-3-vision-128k-instruct | NVIDIA NIM | 131K | Online | Yes | chatvision |
| microsoft/phi-3.5-moe-instruct microsoft/phi-3.5-moe-instruct | NVIDIA NIM | 131K | Online | Yes | chat |
| mistralai/mixtral-8x22b-v0.1 mistralai/mixtral-8x22b-v0.1 | NVIDIA NIM | 131K | Online | Yes | chat |
| nvidia/llama-3.1-nemotron-51b-instruct nvidia/llama-3.1-nemotron-51b-instruct | NVIDIA NIM | 131K | Online | Yes | chatreasoning |
| nvidia/nemotron-4-340b-instruct nvidia/nemotron-4-340b-instruct | NVIDIA NIM | 131K | Online | Yes | chatreasoning |
| nvidia/nemotron-4-340b-reward nvidia/nemotron-4-340b-reward | NVIDIA NIM | 131K | Online | Yes | chatreasoning |
| nvidia/nemotron-parse nvidia/nemotron-parse | NVIDIA NIM | 131K | Online | Yes | chatreasoning |
| nvidia/neva-22b nvidia/neva-22b | NVIDIA NIM | 131K | Online | Yes | chat |
| nvidia/nvclip nvidia/nvclip | NVIDIA NIM | 131K | Online | Yes | chat |
| nvidia/riva-translate-4b-instruct nvidia/riva-translate-4b-instruct | NVIDIA NIM | 131K | Online | Yes | chat |
| nvidia/vila nvidia/vila | NVIDIA NIM | 131K | Online | Yes | chat |
| writer/palmyra-creative-122b writer/palmyra-creative-122b | NVIDIA NIM | 131K | Online | Yes | chat |
| adept/fuyu-8b adept/fuyu-8b | NVIDIA NIM | 131K | Online | Yes | chat |
| aisingapore/sea-lion-7b-instruct aisingapore/sea-lion-7b-instruct | NVIDIA NIM | 131K | Online | Yes | chat |
| deepseek-ai/deepseek-coder-6.7b-instruct deepseek-ai/deepseek-coder-6.7b-instruct | NVIDIA NIM | 131K | Online | Yes | chatcoding |
| google/codegemma-1.1-7b google/codegemma-1.1-7b | NVIDIA NIM | 131K | Online | Yes | chatcoding |
| google/codegemma-7b google/codegemma-7b | NVIDIA NIM | 131K | Online | Yes | chatcoding |
| ibm/granite-3.0-8b-instruct ibm/granite-3.0-8b-instruct | NVIDIA NIM | 131K | Online | Yes | chat |
| ibm/granite-8b-code-instruct ibm/granite-8b-code-instruct | NVIDIA NIM | 131K | Online | Yes | chatcoding |
| nv-mistralai/mistral-nemo-12b-instruct nv-mistralai/mistral-nemo-12b-instruct | NVIDIA NIM | 131K | Online | Yes | chat |
| nvidia/mistral-nemo-minitron-8b-8k-instruct nvidia/mistral-nemo-minitron-8b-8k-instruct | NVIDIA NIM | 131K | Online | Yes | chat |
| zyphra/zamba2-7b-instruct zyphra/zamba2-7b-instruct | NVIDIA NIM | 131K | Online | Yes | chat |
| mistralai/mistral-large mistralai/mistral-large-3-675b-instruct-2512 | NVIDIA NIM | 8K | Online | Yes | chat |
| nvidia/cosmos-reason2-8b nvidia/cosmos-reason2-8b | NVIDIA NIM | 131K | Online | Yes | chat |
| nvidia/nemotron-3.5-content-safety nvidia/nemotron-3.5-content-safety | NVIDIA NIM | 128K | Online | Yes | chatreasoning |
| mistralai/codestral-22b-instruct-v0.1 mistralai/codestral-22b-instruct-v0.1 | NVIDIA NIM | 131K | Online | Yes | chatcoding |
| openai/gpt-oss-120b GPT OSS 120B | NVIDIA NIM | 131K | Online | Yes | chat |
| mistralai/mistral-7b-instruct-v0.3 mistralai/mistral-7b-instruct-v0.3 | NVIDIA NIM | 131K | Online | Yes | chat |
| ibm/granite-3.0-3b-a800m-instruct ibm/granite-3.0-3b-a800m-instruct | NVIDIA NIM | 131K | Online | Yes | chat |
| nvidia/nemotron-nano-3-30b-a3b nvidia/nemotron-nano-3-30b-a3b | NVIDIA NIM | 131K | Online | Yes | chatreasoning |
| mistralai/mistral-large-2-instruct mistralai/mistral-large-2-instruct | Mistral | 131K | Online | Yes | chat |
| google/diffusiongemma-26b-a4b-it google/diffusiongemma-26b-a4b-it | NVIDIA NIM | 8K | Online | Yes | chat |
| meta/llama-3.2-90b-vision-instruct meta/llama-3.2-90b-vision-instruct | NVIDIA NIM | 8K | Online | Yes | chat |
| mistralai/mistral-nemotron mistralai/mistral-nemotron | NVIDIA NIM | 8K | Online | Yes | chat |
| nvidia/riva-translate-4b-instruct-v1.1 nvidia/riva-translate-4b-instruct-v1.1 | NVIDIA NIM | 8K | Online | Yes | chat |
| nvidia/ising-calibration-1.5-31b nvidia/ising-calibration-1.5-31b | NVIDIA NIM | 8K | Online | Yes | chat |
| nvidia/riva-translate-4b-instruct-v2 nvidia/riva-translate-4b-instruct-v2 | NVIDIA NIM | 8K | Online | Yes | chat |
| nvidia/nemotron-3.5-lightning-30b-a3b nvidia/nemotron-3.5-lightning-30b-a3b | NVIDIA NIM | 8K | Online | Yes | chat |
| nvidia/llama-3.1-nemotron-70b-instruct nvidia/llama-3.1-nemotron-70b-instruct | NVIDIA | 131K | Online | Yes | chatreasoning |
| meta/llama-3.2-11b-vision-instruct meta/llama-3.2-11b-vision-instruct | Meta | 131K | Online | Yes | chatvision |
| nvidia/nemotron-3-nano-30b-a3b Nemotron 3 Nano 30B A3B | NVIDIA NIM | 262K | Online | Yes | chat |
| nvidia/llama-nemotron-embed-vl-1b-v2 nvidia/llama-nemotron-embed-vl-1b-v2 | NVIDIA NIM | 131K | Online | Yes | chatreasoningembedding |
| ai21labs/jamba-1.5-large-instruct ai21labs/jamba-1.5-large-instruct | AI21 Labs | 131K | Online | Yes | chat |
| openai/gpt-oss-20b GPT OSS 20B | NVIDIA NIM | 131K | Online | Yes | chat |
| nvidia/embed-qa-4 nvidia/embed-qa-4 | NVIDIA NIM | 131K | Online | Yes | chatembedding |
| nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1 nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1 | NVIDIA NIM | 131K | Online | Yes | chatembedding |
| nvidia/llama-3.2-nv-embedqa-1b-v1 nvidia/llama-3.2-nv-embedqa-1b-v1 | NVIDIA NIM | 131K | Online | Yes | chatembedding |
| nvidia/nemotron-3-embed-1b nvidia/nemotron-3-embed-1b | NVIDIA NIM | 131K | Online | Yes | chatreasoningembedding |
| nvidia/nv-embedqa-mistral-7b-v2 nvidia/nv-embedqa-mistral-7b-v2 | NVIDIA NIM | 131K | Online | Yes | chatembedding |
| snowflake/arctic-embed-l snowflake/arctic-embed-l | NVIDIA NIM | 131K | Online | Yes | chatembedding |
| databricks/dbrx-instruct databricks/dbrx-instruct | Databricks | 131K | Online | Yes | chat |
| meta/llama2-70b meta/llama2-70b | Meta | 131K | Online | Yes | chat |
| meta/llama-guard-4-12b meta/llama-guard-4-12b | NVIDIA NIM | 1.0M | Online | Yes | chat |
| nvidia/llama-3.1-nemotron-safety-guard-8b-v3 Llama 3.1 Nemotron Safety Guard 8B v3 | NVIDIA NIM | 128K | Online | Yes | chat |
| nvidia/llama-3.1-nemoguard-8b-content-safety nvidia/llama-3.1-nemoguard-8b-content-safety | NVIDIA NIM | 8K | Online | Yes | chat |
| nvidia/llama-3.1-nemoguard-8b-topic-control nvidia/llama-3.1-nemoguard-8b-topic-control | NVIDIA NIM | 8K | Online | Yes | chat |
Developer Tools
Related Providers
View all →NVIDIA NIM FreeLLM Score free API access score
How we score → 87 /100
⭐ FreeLLM's Pick — Best for easy signup
Generosity Free limits and access terms
65 Access Signup and key availability
100 Model Breadth Free model coverage
95 Reliability Status and stability signals
60 Compatibility SDK and endpoint support
100 Quality Model capability signals
100 What is NVIDIA NIM?
100+ open models from NVIDIA — no credit card, 40 RPM.
NVIDIA NIM (NVIDIA Inference Microservices) provides API access to 100+ open-weight models hosted on NVIDIA infrastructure. The free tier is available to all NVIDIA Developer Program members (free sign-up) with a limit of ~40 requests/minute. Models include Llama, Mistral, DeepSeek-R1, Nemotron, and domain-specific variants. All endpoints are OpenAI-compatible.
- 100+ open models available
- No daily token cap
- ~40 RPM free tier
- No credit card required
API Compatibility: Live-tested OpenAI-compatible Chat Completions
NVIDIA NIM Free Tier Limits & Pricing
Credit Card Not required
Phone Verification Required
Free Tier 80 free models online
Context Range 8K – 1.0M
Total Models 80 listed
Rate Limits Up to 40 RPM
API Compatibility Live-tested OpenAI-compatible Chat Completions
NVIDIA NIM API Setup Tutorials
Claude Code Environment variables and base URL setup Codex OpenAI-compatible config for local coding Gemini CLI Provider-specific API key routing notes
NVIDIA NIM is fully compatible with popular AI coding assistants like Cursor, Claude Code, and more. To see step-by-step API configuration instructions for your favorite tool, please visit our Global Configuration Guide →
NVIDIA NIM Model Use Cases
What NVIDIA NIM's free models are best for, based on aggregated model capabilities:
NVIDIA NIM Limitations & Caveats
- ~40 RPM shared across all models, not per-model
- Some models require additional registration per model family
- Unavailable models listed in catalog but uncallable with standard key
NVIDIA NIM FAQ
Why can't I call certain models on NVIDIA NIM even though they're listed?
NVIDIA NIM's catalog includes all models, but some require additional per-model-family registration. If you get a 403 error, go to the model's page and click "Try API" to register for that specific model family.
Is the 40 RPM limit shared across all models?
Yes — NVIDIA NIM applies a global ~40 RPM limit to your API key, shared across all model calls. If you're using multiple models in parallel, the combined rate cannot exceed ~40 RPM.
Does NVIDIA NIM require phone verification?
Yes, NVIDIA Developer account signup requires phone number verification. This is a one-time step during account creation.