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.
Showing 1–34 of 34
“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 output tokens34
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterThird-party | Dots Studio: Dots3-Note Preview (free) | $0/M outCheapest | completion: 0 / token (endpoint atlas-cloud/fp8) | |
| OpenRouterThird-party | Sao10K: Llama 3 8B Lunarisvia Parasail · bf16 | $0.05/M out | completion: 0.00000005 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Mistral: Mistral Small 3 | $0.08/M out | completion: 0.00000008 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Google: Gemma 3 12Bvia NextBit · int4 | $0.15/M out | completion: 0.00000015 / token (endpoint nextbit/int4) | |
| OpenRouterThird-party | Google: Gemma 3 27Bvia DeepInfra · fp8 | $0.16/M out | completion: 0.00000016 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 14Bvia NextBit · int4 | $0.22/M out | completion: 0.00000022 / token (endpoint nextbit/int4) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3 Nano 30B A3B | $0.24/M out | completion: 0.00000024 / token (endpoint nebius/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 32Bvia DeepInfra · fp8 | $0.28/M out | completion: 0.00000028 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder 30B A3B Instructvia SiliconFlow · fp8 | $0.28/M out | completion: 0.00000028 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 30B A3B Instruct 2507via DekaLLM | $0.3/M out | completion: 0.0000003 / token (endpoint dekallm) | |
| OpenRouterThird-party | Tencent: Hy3off-peak 1600–0000 UTC · via Tencent · fp8 | $0.33/M out | completion: 0.00000033 / token (utc_start 1600, utc_end 0; endpoint tencent/fp8) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3 Supervia DeepInfra · bf16 | $0.4/M out | completion: 0.0000004 / token (endpoint deepinfra/bf16) | |
| OpenRouterThird-party | Qwen: Qwen3 30B A3B | $0.5/M out | completion: 0.0000005 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Tencent: Hy3peak 0000–1600 UTC · via Tencent · fp8 | $0.528/M out | completion: 0.000000528 / token (utc_start 0, utc_end 1600; endpoint tencent/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 235B A22B Instruct 2507via DeepInfra · fp8 | $0.55/M out | completion: 0.00000055 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 30B A3B Instructvia DeepInfra · fp8 | $0.6/M out | completion: 0.0000006 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Tencent: Hy3 preview | $0.6/M out | completion: 0.0000006 / token (endpoint gmicloud/bf16) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 8B Instruct | $0.75/M out | completion: 0.00000075 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder Next | $0.8/M out | completion: 0.0000008 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | TheDrummer: Skyfall 36B V2 | $0.8/M out | completion: 0.0000008 / token (endpoint parasail/fp8) | |
| OpenRouterThird-party | MiniMax: MiniMax M3 (batch) | $0.88/M out | completion: 0.00000088 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 235B A22B Instructvia DeepInfra · fp8 | $0.88/M out | completion: 0.00000088 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Meta: Muse Glimmer 30B (batch) | $0.96/M out | completion: 0.00000096 / token (endpoint deepinfra/bf16) | |
| OpenRouterThird-party | MiniMax: MiniMax M3via CoreWeave · fp4 | $0.96/M out | completion: 0.00000096 / token (endpoint coreweave/fp4) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3 0324via SiliconFlow · fp8 | $1/M out | completion: 0.000001 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | Qwen2.5 Coder 32B Instruct | $1/M out | completion: 0.000001 / token (endpoint cloudflare) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder 480B A35BTurbovia DeepInfra | $1/M out | completion: 0.000001 / token (endpoint deepinfra/turbo) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 30B A3B Thinking | $1/M out | completion: 0.000001 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3via StreamLake | $1.029/M out | completion: 0.0000010287 / token (endpoint streamlake) | |
| OpenRouterThird-party | Qwen: Qwen3 Next 80B A3B Instructvia DeepInfra · fp8 | $1.1/M out | completion: 0.0000011 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Meta: Muse Glimmer 30B | $1.2/M out | completion: 0.0000012 / token (endpoint deepinfra/bf16) | |
| OpenRouterThird-party | Moondream: Moondream 3 Preview | $2.5/M out | completion: 0.0000025 / token (endpoint primeintellect/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 235B A22B Thinking 2507 | $3.5/M out | completion: 0.0000035 / token (endpoint venice/fp8) | |
| OpenRouterThird-party | MoonshotAI: Kimi K3 (batch) | $11.4/M out | completion: 0.0000114 / token (endpoint deepinfra/bf16) |
