11,195 prices on 4,854 listings · last collected 4 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.
Platform
Gemini 
Qwen 
Mistral 
Kimi 
MiniMax 
Nemotron 
DeepSeek 
Hunyuan 
Llama Showing 1–100 of 120
“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 tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterThird-party | Dots Studio: Dots3-Note Preview (free) | $0/M inCheapest | prompt: 0 / token (endpoint atlas-cloud/fp8) | |
| OpenRouterOfficial | Google: Gemma 4 31B (free) | $0/M inCheapest | prompt: 0 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | NVIDIA: Nemotron 3 Nano Omni (free) | $0/M inCheapest | prompt: 0 / token (endpoint nvidia) | |
| OpenRouterOfficial | NVIDIA: Nemotron 3 Ultra (free) | $0/M inCheapest | prompt: 0 / token (endpoint nvidia) | |
| APIMartNot disclosed | text-embedding-3-small | $0.016/M in | Input $0.016 / Output $0.016 · Per 1M tokens | |
| OpenRouterThird-party | Sao10K: Llama 3 8B Lunarisvia Parasail · bf16 | $0.04/M in | prompt: 0.00000004 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Mistral: Mistral Small 3 | $0.05/M in | prompt: 0.00000005 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3 Nano 30B A3B | $0.06/M in | prompt: 0.00000006 / token (endpoint nebius/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder 30B A3B Instructvia SiliconFlow · fp8 | $0.07/M in | prompt: 0.00000007 / token (endpoint siliconflow/fp8) | |
| OpenRouterOfficial | Tencent: Hy-MT2-30B-A3B | $0.074/M in | prompt: 0.000000074 / token (endpoint tencent/fp8) | |
| OpenRouterThird-party | Google: Gemma 3 12Bvia NextBit · int4 | $0.075/M in | prompt: 0.000000075 / token (endpoint nextbit/int4) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3 Supervia DeepInfra · bf16 | $0.075/M in | prompt: 0.000000075 / token (endpoint deepinfra/bf16) | |
| OpenRouterThird-party | Google: Gemma 3 27Bvia DeepInfra · fp8 | $0.08/M in | prompt: 0.00000008 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 32Bvia DeepInfra · fp8 | $0.08/M in | prompt: 0.00000008 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Tencent: Hy3off-peak 1600–0000 UTC · via Tencent · fp8 | $0.083/M in | prompt: 0.0000000825 / token (utc_start 1600, utc_end 0; endpoint tencent/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 235B A22B Instruct 2507via DeepInfra · fp8 | $0.09/M in | prompt: 0.00000009 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 30B A3B Instruct 2507via DekaLLM | $0.09/M in | prompt: 0.00000009 / token (endpoint dekallm) | |
| OpenRouterThird-party | Qwen: Qwen3 Next 80B A3B Instructvia DeepInfra · fp8 | $0.09/M in | prompt: 0.00000009 / token (endpoint deepinfra/fp8) | |
| RunwareNot disclosed | Shieldstral 1.0 3B | $0.09/M in | $9e-8 / inputToken | |
| OpenRouterNot disclosed | Google: Gemma 4 31Bvia KT | $0.1/M in | prompt: 0.0000001 / token (endpoint kt) | |
| OpenRouterOfficial | Mistral: Ministral 3 3B 2512via Mistral · zdr | $0.1/M in | prompt: 0.0000001 / token (endpoint mistral/zdr) | |
| OpenRouterThird-party | Qwen: Qwen3 14Bvia NextBit · int4 | $0.1/M in | prompt: 0.0000001 / token (endpoint nextbit/int4) | |
| OpenRouterOfficial | Reka Flash 3 | $0.1/M in | prompt: 0.0000001 / token (endpoint reka) | |
| AibermNot disclosed | Gemini 3 Flash | $0.101/M in | model_ratio 0.22 × $2/M · group default ×0.23Claims official price $0.5/M in | |
| RunwareNot disclosed | Gemma 4 31B | $0.102/M in | $1.02e-7 / inputToken | |
| APIMartNot disclosed | text-embedding-3-large | $0.104/M in | Input $0.104 / Output $0.104 · Per 1M tokens | |
| OpenRouterThird-party | Qwen: Qwen3 30B A3B | $0.12/M in | prompt: 0.00000012 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder Next | $0.12/M in | prompt: 0.00000012 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Tencent: Hy3peak 0000–1600 UTC · via Tencent · fp8 | $0.132/M in | prompt: 0.000000132 / token (utc_start 0, utc_end 1600; endpoint tencent/fp8) | |
| OpenRouterOfficial | Mistral: Ministral 3 8B 2512via Mistral · zdr | $0.15/M in | prompt: 0.00000015 / token (endpoint mistral/zdr) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 30B A3B Instructvia DeepInfra · fp8 | $0.15/M in | prompt: 0.00000015 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Tencent: Hy3 preview | $0.18/M in | prompt: 0.00000018 / token (endpoint gmicloud/bf16) | |
| OpenRouterNot disclosed | MoonshotAI: Kimi K3via Relace · fp4 | $0.182/M in | prompt: 0.0000001824 / token (endpoint relace/fp4) | |
| OpenRouterOfficial | Qwen: Qwen3 Coder Flash | $0.195/M in | prompt: 0.000000195 / token (endpoint alibaba) | |
| OpenRouterOfficial | Mistral: Ministral 3 14B 2512via Mistral · zdr | $0.2/M in | prompt: 0.0000002 / token (endpoint mistral/zdr) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 235B A22B Instructvia DeepInfra · fp8 | $0.2/M in | prompt: 0.0000002 / token (endpoint deepinfra/fp8) | |
| APIMartNot disclosed | deepseek-v3-0324 | $0.206/M in | Input $0.2056 / Output $0.8224 · Per 1M tokens | |
| OpenRouterThird-party | MiniMax: MiniMax M3 (batch) | $0.224/M in | prompt: 0.000000224 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | MiniMax: MiniMax M3via CoreWeave · fp4 | $0.23/M in | prompt: 0.00000023 / token (endpoint coreweave/fp4) | |
| APIMartNot disclosed | minimax-m3 | $0.24/M in | Input $0.24 / Output $0.96 · Per 1M tokens | |
| OpenRouterThird-party | Meta: Muse Glimmer 30B (batch) | $0.24/M in | prompt: 0.00000024 / token (endpoint deepinfra/bf16) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3 0324via SiliconFlow · fp8 | $0.25/M in | prompt: 0.00000025 / token (endpoint siliconflow/fp8) | |
| OpenRouterOfficial | Google: Gemini 3 Flash Preview (batch)Image input | $0.25/M in | image: 0.00000025 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3 Flash Preview (batch) | $0.25/M in | prompt: 0.00000025 / token (endpoint google-vertex/global) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 8B Instruct | $0.25/M in | prompt: 0.00000025 / token (endpoint parasail/bf16) | |
| AibermNot disclosed | o3 Mini | $0.253/M in | model_ratio 0.55 × $2/M · group default ×0.23Claims official price $1.1/M in | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3via StreamLake | $0.257/M in | prompt: 0.0000002574 / token (endpoint streamlake) | |
| ReplicatePlatform-hosted | qwen/qwen3-235b-a22b-instruct-2507 | $0.264/M in | $0.264 per million input tokens | |
| OpenRouterThird-party | Qwen: Qwen3 VL 30B A3B Thinking | $0.29/M in | prompt: 0.00000029 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | Meta: Muse Glimmer 30B | $0.3/M in | prompt: 0.0000003 / token (endpoint deepinfra/bf16) | |
| OpenRouterThird-party | Moondream: Moondream 3 Preview | $0.3/M in | prompt: 0.0000003 / token (endpoint primeintellect/fp8) | |
| OpenRouterNot disclosed | Motif Technologies: Motif 3 | $0.3/M in | prompt: 0.0000003 / token (endpoint kt) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder 480B A35BTurbovia DeepInfra | $0.3/M in | prompt: 0.0000003 / token (endpoint deepinfra/turbo) | |
| RunwareNot disclosed | MiniMax M3≤ 512K context | $0.3/M in | $3e-7 / inputToken · ≤ 512K context | |
| OpenRouterOfficial | Qwen: Qwen3 Coder FlashPrompt > 32K | $0.325/M in | prompt: 0.000000325 / token (>32000; endpoint alibaba) | |
| APIMartNot disclosed | gemini-3-flash-preview | $0.4/M in | Input $0.4 / Output $2.4 · Per 1M tokens | |
| APIMartNot disclosed | gemini-3-flash-preview-nothinking | $0.4/M in | Input $0.4 / Output $2.4 · Per 1M tokens | |
| APIMartNot disclosed | gemini-3-flash-preview-thinking | $0.4/M in | Input $0.4 / Output $2.4 · Per 1M 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. | |
| OpenRouterOfficial | Mistral: Mistral Medium 3via Mistral · zdr | $0.4/M in | prompt: 0.0000004 / token (endpoint mistral/zdr) | |
| OpenRouterOfficial | Morph: Morph V3 Fast (batch) | $0.4/M in | prompt: 0.0000004 / token | |
| OpenRouterOfficial | Morph: Morph V3 Large (batch) | $0.45/M in | prompt: 0.00000045 / token (endpoint morph/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 235B A22B Thinking 2507 | $0.45/M in | prompt: 0.00000045 / token (endpoint venice/fp8) | |
| AibermNot disclosed | Gemini 3 Pro Preview | $0.46/M in | model_ratio 1 × $2/M · group default ×0.23Claims official price $2/M in | |
| AibermNot disclosed | Gemini 3 Pro Preview Thinking | $0.46/M in | model_ratio 1 × $2/M · group default ×0.23Claims official price $2/M in | |
| AibermNot disclosed | Gemini 3 Pro | $0.46/M in | model_ratio 1 × $2/M · group default ×0.23Claims official price $2/M in | |
| AibermNot disclosed | Gemini 3 Pro Mcpmark | $0.46/M in | model_ratio 1 × $2/M · group default ×0.23Claims official price $2/M in | |
| KIENot disclosed | Gemini 3 Pro | $0.5/M in | 100 credits per million tokens ($0.50)Claims official or Fal price $2/M in | |
| OpenRouterOfficial | Google: Gemini 3 Flash PreviewImage inputvia Google AI Studio | $0.5/M in | image: 0.0000005 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3 Flash Previewvia Google AI Studio | $0.5/M in | prompt: 0.0000005 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3 Flash Preview (batch)Audio input | $0.5/M in | audio: 0.0000005 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Mistral: Mistral Large 3 2512via Mistral · zdr | $0.5/M in | prompt: 0.0000005 / token (endpoint mistral/zdr) | |
| OpenRouterNot disclosed | NVIDIA: Nemotron 3 Ultravia KT | $0.5/M in | prompt: 0.0000005 / token (endpoint kt) | |
| ReplicateOfficial partner | google/gemini-3-flash | $0.5/M in | $0.50 per million input tokens | |
| RunwareNot disclosed | Gemini 3 Flashtext | $0.5/M in | $5e-7 / inputToken · text, image, video | |
| OpenRouterOfficial | Qwen: Qwen3 Coder FlashPrompt > 128K | $0.52/M in | prompt: 0.00000052 / token (>128000; endpoint alibaba) | |
| OpenRouterOfficial | OpenAI: o3 Mini (batch) | $0.55/M in | prompt: 0.00000055 / token (endpoint openai) | |
| OpenRouterThird-party | TheDrummer: Skyfall 36B V2 | $0.55/M in | prompt: 0.00000055 / token (endpoint parasail/fp8) | |
| RunwareNot disclosed | MiniMax M3> 512K context | $0.6/M in | $6e-7 / inputToken · > 512K context | |
| 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 | |
| OpenRouterThird-party | Qwen2.5 Coder 32B Instruct | $0.66/M in | prompt: 0.00000066 / token (endpoint cloudflare) | |
| OpenRouterOfficial | Morph: Morph V3 Fast | $0.8/M in | prompt: 0.0000008 / token (endpoint morph/fp8) | |
| OpenRouterOfficial | Relace: Relace Apply 3 | $0.85/M in | prompt: 0.00000085 / token (endpoint relace/fp8) | |
| APIMartNot disclosed | o3-mini | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-2025-01-31 | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-2025-01-31-high | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-2025-01-31-low | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-2025-01-31-medium | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-high | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-low | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-medium | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| OpenRouterOfficial | Morph: Morph V3 Large | $0.9/M in | prompt: 0.0000009 / token (endpoint morph/fp8) | |
| OpenRouterOfficial | Google: Gemini 3 Flash PreviewAudio inputvia Google AI Studio | $1/M in | audio: 0.000001 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | OpenAI: o3 (batch) | $1/M in | prompt: 0.000001 / token (endpoint openai) | |
| RunwareNot disclosed | Gemini 3 Flash | $1/M in | $0.000001 / inputToken · audio | |
| AibermNot disclosed | Kimi K3 | $1.058/M in | model_ratio 2.3 × $2/M · group default ×0.23Claims official price $3/M in |
