Open-Weight AI Models
Open weights buy you three things a closed API cannot: the option to self-host, freedom from per-token pricing at scale, and no risk of the model being deprecated out from under you. The listed prices are what hosted providers charge to run these for you; the real economics show up only when you run them yourself. Good fit for high-volume, latency-sensitive, or data-residency-constrained workloads.
Showing top 25 of 305 matching models · last synced 17 hours ago
Top pick right now: Aya Vision 8B from Cohere. It is the lowest-priced open-weight option here at N/A/Mtok output, and you can self-host it to drop that cost further.
| # | Model | Provider | Input $/Mtok | Output $/Mtok | Context | Capabilities |
|---|---|---|---|---|---|---|
| 1 |
Aya Vision 8B
|
Cohere | N/A | N/A | 16,000 | vision, open |
| 2 |
Aya Expanse 8B
|
Cohere | N/A | N/A | 8,000 | open |
| 3 |
Aya Vision 32B
|
Cohere | N/A | N/A | 16,000 | vision, open |
| 4 |
Aya Expanse 32B
|
Cohere | N/A | N/A | 128,000 | open |
| 5 |
Whisper
|
Groq | N/A | N/A | N/A | open |
| 6 |
Whisper Large V3 Turbo
|
Groq | N/A | N/A | N/A | open |
| 7 |
Gemma 4 31B IT
|
N/A | N/A | 262,144 | vision, tools, reasoning, structured output, open | |
| 8 |
Gemma 4 26B A4B IT
|
N/A | N/A | 262,144 | vision, tools, reasoning, structured output, open | |
| 9 |
Gemma 4 E4B IT
|
N/A | N/A | 131,072 | vision, tools, reasoning, structured output, open | |
| 10 |
Gemma 4 E2B IT
|
N/A | N/A | 131,072 | vision, tools, reasoning, structured output, open | |
| 11 |
LFM2.5-1.2B-Instruct (free)
|
OpenRouter | Free | Free | 32,768 | structured output, open |
| 12 |
LFM2.5-1.2B-Thinking (free)
|
OpenRouter | Free | Free | 32,768 | tools, reasoning, structured output, open |
| 13 |
Trinity Large Preview
|
OpenRouter | Free | Free | 131,072 | tools, structured output, open |
| 14 |
Uncensored (free)
|
OpenRouter | Free | Free | 32,768 | structured output, open |
| 15 |
Seedream 4.5
|
OpenRouter | Free | Free | 4,096 | vision, open |
| 16 |
FLUX.2 Klein 4B
|
OpenRouter | Free | Free | 40,960 | vision, open |
| 17 |
Hermes 3 405B Instruct (free)
|
OpenRouter | Free | Free | 131,072 | open |
| 18 |
Llama 3.2 3B Instruct (free)
|
OpenRouter | Free | Free | 131,072 | open |
| 19 |
Llama 3.3 70B Instruct (free)
|
OpenRouter | Free | Free | 65,536 | tools, open |
| 20 |
Laguna M.1 (free)
|
OpenRouter | Free | Free | 262,144 | tools, reasoning, open |
| 21 |
Laguna XS.2 (free)
|
OpenRouter | Free | Free | 262,144 | tools, reasoning, open |
| 22 |
Nemotron 3 Nano Omni (free)
|
OpenRouter | Free | Free | 256,000 | vision, tools, reasoning, open |
| 23 |
Nemotron 3 Nano 30B A3B (free)
|
OpenRouter | Free | Free | 256,000 | tools, reasoning, open |
| 24 |
Nemotron Nano 9B V2 (free)
|
OpenRouter | Free | Free | 128,000 | tools, reasoning, structured output, open |
| 25 |
Nemotron 3 Super (free)
|
OpenRouter | Free | Free | 262,144 | tools, reasoning, structured output, open |
Browse other categories
Data synced daily from models.dev. Always verify pricing with the provider before deploying to production.