NVIDIA NIM pricing · auto-updated daily

NVIDIA NIM API pricing — June 12, 2026

All 103 NVIDIA NIM text models with token prices ($ per 1M), context window and max output, refreshed daily from the official pricing source. Bring your NVIDIA NIM key to flo2 and you pay these exact prices — zero markup — with fallback, racing and per-request cost accounting on top.

Pricing
Preview
per-GPU in production
Models
103
in this table
ModelIn $/MCached inOut $/MReasoning
01-ai/yi-largeFree preview—Free preview—
abacusai/dracarys-llama-3.1-70b-instructFree preview—Free preview—
ai21labs/jamba-1.5-large-instructFree preview—Free preview—
aisingapore/sea-lion-7b-instructFree preview—Free preview—
baai/bge-m3Free preview—Free preview—
bigcode/starcoder2-15bFree preview—Free preview—
bytedance/seed-oss-36b-instructFree preview—Free preview—
databricks/dbrx-instructFree preview—Free preview—
deepseek-ai/deepseek-coder-6.7b-instructFree preview—Free preview—
deepseek-ai/deepseek-v4-flashFree preview—Free preview—
deepseek-ai/deepseek-v4-proFree preview—Free preview—
google/codegemma-1.1-7bFree preview—Free preview—
google/codegemma-7bFree preview—Free preview—
google/deplotFree preview—Free preview—
google/diffusiongemma-26b-a4b-itFree preview—Free preview—
google/gemma-2-2b-itFree preview—Free preview—
google/gemma-2bFree preview—Free preview—
google/gemma-3-12b-itFree preview—Free preview—
google/gemma-3-4b-itFree preview—Free preview—
google/gemma-3n-e2b-itFree preview—Free preview—
google/gemma-3n-e4b-itFree preview—Free preview—
google/gemma-4-31b-itFree preview—Free preview—
google/recurrentgemma-2bFree preview—Free preview—
ibm/granite-3.0-3b-a800m-instructFree preview—Free preview—
ibm/granite-3.0-8b-instructFree preview—Free preview—
ibm/granite-34b-code-instructFree preview—Free preview—
ibm/granite-8b-code-instructFree preview—Free preview—
meta/codellama-70bFree preview—Free preview—
meta/llama-3.1-70b-instructFree preview—Free preview—
meta/llama-3.1-8b-instructFree preview—Free preview—
meta/llama-3.2-11b-vision-instructFree preview—Free preview—
meta/llama-3.2-1b-instructFree preview—Free preview—
meta/llama-3.2-3b-instructFree preview—Free preview—
meta/llama-3.2-90b-vision-instructFree preview—Free preview—
meta/llama-3.3-70b-instructFree preview—Free preview—
meta/llama-4-maverick-17b-128e-instructFree preview—Free preview—
meta/llama-guard-4-12bFree preview—Free preview—
meta/llama2-70bFree preview—Free preview—
microsoft/kosmos-2Free preview—Free preview—
microsoft/phi-3-vision-128k-instructFree preview—Free preview—
microsoft/phi-3.5-moe-instructFree preview—Free preview—
microsoft/phi-4-mini-instructFree preview—Free preview—
microsoft/phi-4-multimodal-instructFree preview—Free preview—
minimaxai/minimax-m2.7Free preview—Free preview—
mistralai/codestral-22b-instruct-v0.1Free preview—Free preview—
mistralai/ministral-14b-instruct-2512Free preview—Free preview—
mistralai/mistral-7b-instruct-v0.3Free preview—Free preview—
mistralai/mistral-largeFree preview—Free preview—
mistralai/mistral-large-2-instructFree preview—Free preview—
mistralai/mistral-large-3-675b-instruct-2512Free preview—Free preview—
mistralai/mistral-medium-3.5-128bFree preview—Free preview—
mistralai/mistral-nemotronFree preview—Free preview—
mistralai/mistral-small-4-119b-2603Free preview—Free preview—
mistralai/mixtral-8x22b-v0.1Free preview—Free preview—
mistralai/mixtral-8x7b-instruct-v0.1Free preview—Free preview—
moonshotai/kimi-k2.6Free preview—Free preview—
nv-mistralai/mistral-nemo-12b-instructFree preview—Free preview—
nvidia/ai-synthetic-video-detectorFree preview—Free preview—
nvidia/gliner-piiFree preview—Free preview—
nvidia/ising-calibration-1-35b-a3bFree preview—Free preview—
nvidia/llama-3.1-nemoguard-8b-content-safetyFree preview—Free preview—
nvidia/llama-3.1-nemoguard-8b-topic-controlFree preview—Free preview—
nvidia/llama-3.1-nemotron-51b-instructFree preview—Free preview—
nvidia/llama-3.1-nemotron-70b-instructFree preview—Free preview—
nvidia/llama-3.1-nemotron-nano-8b-v1Free preview—Free preview—
nvidia/llama-3.1-nemotron-nano-vl-8b-v1Free preview—Free preview—
nvidia/llama-3.1-nemotron-safety-guard-8b-v3Free preview—Free preview—
nvidia/llama-3.1-nemotron-ultra-253b-v1Free preview—Free preview—
nvidia/llama-3.3-nemotron-super-49b-v1Free preview—Free preview—
nvidia/llama-3.3-nemotron-super-49b-v1.5Free preview—Free preview—
nvidia/llama3-chatqa-1.5-70bFree preview—Free preview—
nvidia/mistral-nemo-minitron-8b-8k-instructFree preview—Free preview—
nvidia/nemotron-3-content-safetyFree preview—Free preview—
nvidia/nemotron-3-nano-30b-a3bFree preview—Free preview—
nvidia/nemotron-3-nano-omni-30b-a3b-reasoningFree preview—Free preview—
nvidia/nemotron-3-super-120b-a12bFree preview—Free preview—
nvidia/nemotron-3-ultra-550b-a55bFree preview—Free preview—
nvidia/nemotron-3.5-content-safetyFree preview—Free preview—
nvidia/nemotron-4-340b-instructFree preview—Free preview—
nvidia/nemotron-4-340b-rewardFree preview—Free preview—
nvidia/nemotron-content-safety-reasoning-4bFree preview—Free preview—
nvidia/nemotron-mini-4b-instructFree preview—Free preview—
nvidia/nemotron-nano-12b-v2-vlFree preview—Free preview—
nvidia/nemotron-nano-3-30b-a3bFree preview—Free preview—
nvidia/nemotron-parseFree preview—Free preview—
nvidia/neva-22bFree preview—Free preview—
nvidia/nvidia-nemotron-nano-9b-v2Free preview—Free preview—
openai/gpt-oss-120bFree preview—Free preview—
openai/gpt-oss-20bFree preview—Free preview—
qwen/qwen3-next-80b-a3b-instructFree preview—Free preview—
qwen/qwen3.5-122b-a10bFree preview—Free preview—
qwen/qwen3.5-397b-a17bFree preview—Free preview—
sarvamai/sarvam-mFree preview—Free preview—
stepfun-ai/step-3.5-flashFree preview—Free preview—
stepfun-ai/step-3.7-flashFree preview—Free preview—
stockmark/stockmark-2-100b-instructFree preview—Free preview—
upstage/solar-10.7b-instructFree preview—Free preview—
writer/palmyra-creative-122bFree preview—Free preview—
writer/palmyra-fin-70b-32kFree preview—Free preview—
writer/palmyra-med-70bFree preview—Free preview—
writer/palmyra-med-70b-32kFree preview—Free preview—
z-ai/glm-5.1Free preview—Free preview—
zyphra/zamba2-7b-instructFree preview—Free preview—

Prices in USD per 1,000,000 tokens, fetched 2026-06-12 from the official NVIDIA NIM pricing source. preview/free tier (build.nvidia.com); production NIM priced per-GPU. Verify before large commitments. Click any column header to sort.

More providers: OpenAI · Anthropic · Google Gemini · xAI Grok · Groq · Cerebras · Mistral · DeepInfra · OpenRouter · or the full cross-provider comparison.

Use NVIDIA NIM through one key — zero markup.
flo2 routes every call to the cheapest, fastest model that clears your bar, with fallback, racing and true cost accounting. Free during Beta.
Get your flo2 key →
© 2026 flo2.com — the zero-markup LLM gateway & router. blog · all providers · flow → to