Free models, shared capacity
These cost nothing, which is exactly why they run out: the capacity is shared across everyone and each account has a daily cap. Use them to prove an idea works. Once something ships and people depend on it, move to a paid model — the switch is one string in your code.
12 models in this category · prices in toman per 1M tokens
| Model | Capabilities | Context | Input / 1M | Output / 1M | ≈ 1,000 words |
|---|---|---|---|---|---|
 Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b:free | Free · shared capacityTool callingReasoning | 1,000,000 | 0 | 0 | 0 |
Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning:free | Free · shared capacityTool callingReasoning | 1,000,000 | 0 | 0 | 0 |
Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl:free | Free · shared capacityImage inputTool callingReasoningJSON output | 1,000,000 | 0 | 0 | 0 |
Dots3-Note Previewdots-studio/dots-3-note-preview:free | Free · shared capacityImage inputTool callingReasoningJSON output | 512,000 | 0 | 0 | 0 |
 Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-it:free | Free · shared capacityImage inputTool callingReasoningJSON output | 262,144 | 0 | 0 | 0 |
Gemma 4 31Bgoogle/gemma-4-31b-it:free | Free · shared capacityImage inputTool callingReasoningJSON output | 262,144 | 0 | 0 | 0 |
Flintrecursive/flint-v1.0:free | Free · shared capacityTool callingReasoningJSON output | 262,144 | 0 | 0 | 0 |
Xing4.0 29B A4Bxingchen-agi/xing4.0-29b-a4b:free | Free · shared capacityTool callingReasoningJSON output | 262,144 | 0 | 0 | 0 |
 North Mini Codecohere/north-mini-code:free | Free · shared capacityTool callingReasoning | 256,000 | 0 | 0 | 0 |
Nemotron 3 Nano Omninvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Free · shared capacityImage inputTool callingReasoningAudio input | 256,000 | 0 | 0 | 0 |
Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety:free | Free · shared capacityImage inputReasoning | 128,000 | 0 | 0 | 0 |
LFM2.5-2.6Bliquid/lfm-2.5-2.6b:free | Free · shared capacityTool callingReasoningJSON output | 65,536 | 0 | 0 | 0 |
Other categories
Models that hold up in a real codebaseCheap models for high-volume workModels that read imagesReasoning models, and what they costLong-context models for documents and codebasesModels that call your tools reliablyModels that return imagesEmbedding models for semantic searchBatch variants (cheaper, slower)