# Nvidia API prices

Nvidia lists 57 model(s) in the Sovyron catalog. Every price is Nvidia's own, in USD per 1M tokens.
Prices as of 2026-10-04.

| Model | Input $/1M | Output $/1M | Cache read $/1M | Context | Released |
| --- | --- | --- | --- | --- | --- |
| DeepSeek V4.1 Flash | free | free | — | 1.0M | Sep 10, 2026 |
| GLM-5.3-Flash | free | free | — | 1.0M | Aug 26, 2026 |
| GLM-5.3 | free | free | — | 1.0M | Aug 14, 2026 |
| Nemotron 3.5 Lightning 30B A3B | free | free | — | 262k | Aug 11, 2026 |
| Muse Glimmer 30B | free | free | — | 131k | Aug 10, 2026 |
| Kimi K3 | free | free | — | 1.0M | Jul 16, 2026 |
| Laguna XS 2.1 | free | free | — | 262k | Jul 2, 2026 |
| DiffusionGemma 26B A4B IT | free | free | — | 250k | Jun 9, 2026 |
| Nemotron 3 Ultra 550B A55B | $0.5 | $2.5 | $0.15 | 1.0M | Jun 4, 2026 |
| Nemotron 3.5 Content Safety | free | free | — | 128k | Jun 4, 2026 |
| Nemotron 3 Nano Omni | free | free | — | 256k | Apr 28, 2026 |
| Active Speaker Detection | free | free | — | — | Apr 16, 2026 |
| synthetic-video-detector | free | free | — | — | Apr 16, 2026 |
| Gemma 4 31B IT | free | free | — | 256k | Apr 2, 2026 |
| llama-nemotron-rerank-vl-1b-v2 | free | free | — | 128k | Mar 31, 2026 |
| nemotron-voicechat | free | free | — | 128k | Mar 16, 2026 |
| Nemotron 3 Super | $0.2 | $0.8 | — | 262k | Mar 11, 2026 |
| cosmos-transfer2.5-2b | free | free | — | — | Feb 26, 2026 |
| llama-nemotron-embed-vl-1b-v2 | free | free | — | 33k | Feb 10, 2026 |
| FLUX.2 Klein 4B | free | free | — | 41k | Jan 14, 2026 |
| usdcode | free | free | — | 128k | Jan 1, 2026 |
| riva-translate-4b-instruct-v1_1 | free | free | — | 128k | Dec 12, 2025 |
| Cosmos Reason2 8B | free | free | — | 131k | Dec 1, 2025 |
| streampetr | free | free | — | 128k | Nov 13, 2025 |
| llama-3.1-nemotron-safety-guard-8b-v3 | free | free | — | 128k | Oct 28, 2025 |
| Magistral Small 2506 | free | free | — | 33k | Sep 25, 2025 |
| Mistral Medium 3 | free | free | — | 131k | Sep 25, 2025 |
| Qwen Image Edit | free | free | — | — | Aug 19, 2025 |
| FLUX.1-Kontext-dev | free | free | — | 41k | Aug 12, 2025 |
| Qwen Image | free | free | — | — | Aug 7, 2025 |
| GPT OSS 20B | free | free | — | 131k | Aug 5, 2025 |
| llama-3_2-nemoretriever-300m-embed-v1 | free | free | — | 33k | Jul 24, 2025 |
| cosmos-transfer1-7b | free | free | — | — | Jun 13, 2025 |
| magpie-tts-zeroshot | free | free | — | — | May 22, 2025 |
| Llama 3.1 Nemotron 70B Instruct | free | free | — | 128k | Apr 15, 2025 |
| Llama 3.1 Nemotron Ultra 253B | free | free | — | 128k | Apr 7, 2025 |
| Llama Guard 4 12B | free | free | — | 128k | Apr 5, 2025 |
| Mistral 7B Instruct v0.3 | free | free | — | 66k | Apr 1, 2025 |
| bevformer | free | free | — | 128k | Mar 18, 2025 |
| cosmos-predict1-5b | free | free | — | — | Mar 18, 2025 |
| sparsedrive | free | free | — | 128k | Mar 18, 2025 |
| nv-embedcode-7b-v1 | free | free | — | 33k | Mar 17, 2025 |
| Gemma 3 12B IT | free | free | — | 131k | Mar 12, 2025 |
| Gemma 3 4B IT | free | free | — | 131k | Mar 12, 2025 |
| studiovoice | free | free | — | 128k | Oct 3, 2024 |
| Llama 3.2 90B Vision Instruct | free | free | — | 128k | Sep 25, 2024 |
| Llama 3.2 11B Vision Instruct | free | free | — | 128k | Sep 18, 2024 |
| esm2-650m | free | free | — | 128k | Aug 29, 2024 |
| FLUX.1-dev | free | free | — | 4k | Aug 1, 2024 |
| FLUX.1-schnell | free | free | — | 77 | Aug 1, 2024 |
| usdvalidate | free | free | — | — | Jul 24, 2024 |
| nv-embed-v1 | free | free | — | 33k | Jun 7, 2024 |
| paligemma | free | free | — | 128k | May 14, 2024 |
| rerank-qa-mistral-4b | free | free | — | 128k | Mar 17, 2024 |
| esmfold | free | free | — | 128k | Mar 15, 2024 |
| BGE M3 | free | free | — | 8k | Jan 30, 2024 |
| Whisper Large v3 | free | free | — | — | Sep 1, 2023 |

HTML page: https://sovyron.com/providers/nvidia/
Full dataset: https://sovyron.com/data/catalog.json
