11,195 prices on 4,854 listings · last collected 5 h ago · 442 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on ten platforms, daily by default, and keeps the page it read. Nothing is typed in by hand. Search a model to see who charges least, per unit, right now.
Llama 
DeepSeek 
Qwen 
Nemotron Showing 1–19 of 19
“Cheapest” is the lowest exact price in this unit for your search. Rows can differ in resolution, length or quality — read the label, or add it to the search (e.g. “1080”).
Per million input tokens8
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| ReplicatePlatform-hosted | qwen/qwen3-235b-a22b-instruct-2507 | $0.264/M inCheapest | $0.264 per million input tokens | |
| FalPlatform-hosted | Moondream3 Preview [Caption] | $0.4/M in | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| FalPlatform-hosted | Moondream3 Preview [Detect] | $0.4/M in | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| FalPlatform-hosted | Moondream3 Preview [Point] | $0.4/M in | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| FalPlatform-hosted | Moondream 3 Preview [Query] | $0.4/M in | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| ReplicatePlatform-hosted | meta/meta-llama-3-70b | $0.65/M in | $0.65 per million input tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-70b-instruct | $0.65/M in | $0.65 per million input tokens | |
| ReplicatePlatform-hosted | deepseek-ai/deepseek-v3 | $1.45/M in | $1.45 per million input tokens |
Per million output tokens8
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| ReplicatePlatform-hosted | qwen/qwen3-235b-a22b-instruct-2507 | $1.06/M outCheapest | $1.06 per million output tokens | |
| ReplicatePlatform-hosted | deepseek-ai/deepseek-v3 | $1.45/M out | $1.45 per million output tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-70b | $2.75/M out | $2.75 per million output tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-70b-instruct | $2.75/M out | $2.75 per million output tokens | |
| FalPlatform-hosted | Moondream3 Preview [Caption] | $3.5/M out | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| FalPlatform-hosted | Moondream3 Preview [Detect] | $3.5/M out | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| FalPlatform-hosted | Moondream3 Preview [Point] | $3.5/M out | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| FalPlatform-hosted | Moondream 3 Preview [Query] | $3.5/M out | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. |
Per million tokens1
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| FalPlatform-hosted | Nemotron 3 Nano Omni | $10/M tokCheapest | $0.01 / 1000 tokens |
Per second of compute time1
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| FalPlatform-hosted | LLaVA v1.6 34B | $0.0013/compute sCheapest | $0.00125 / compute seconds |
Other units (see the platform’s wording)1
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| FalPlatform-hosted | Sam 3 | $0.005/unitCheapest | $0.005 / units |