11,852 prices on 5,032 listings · last collected 14 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
Showing 1201–1300 of 1,867
“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 tokens70
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterNot disclosed | NVIDIA: Nemotron 3 Ultravia KT | $2.2/M out | completion: 0.0000022 / token (endpoint kt) | |
| OpenRouterOfficial | OpenAI: o3 Mini (batch) | $2.2/M out | completion: 0.0000022 / token (endpoint openai) | |
| APIMartNot disclosed | gemini-3-flash-preview | $2.4/M out | Input $0.4 / Output $2.4 · Per 1M tokens | |
| APIMartNot disclosed | gemini-3-flash-preview-nothinking | $2.4/M out | Input $0.4 / Output $2.4 · Per 1M tokens | |
| APIMartNot disclosed | gemini-3-flash-preview-thinking | $2.4/M out | Input $0.4 / Output $2.4 · Per 1M tokens | |
| RunwareNot disclosed | MiniMax M3> 512K context | $2.4/M out | $0.0000024 / outputToken · > 512K context | |
| OpenRouterThird-party | Moondream: Moondream 3 Preview | $2.5/M out | completion: 0.0000025 / token (endpoint primeintellect/fp8) | |
| OpenRouterOfficial | Qwen: Qwen3 Coder FlashPrompt > 128K | $2.6/M out | completion: 0.0000026 / token (>128000; endpoint alibaba) | |
| APIMartNot disclosed | MiniMax-H3-Context-IR | $2.629/M out | 26.2865 ~$2.6287Claims official price $3.286/M outMember tiers: platinum $2.497 · diamond $2.366 | |
| 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 | |
| AibermNot disclosed | Gemini 3 Pro Preview | $2.76/M out | model_ratio 1 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $12/M out | |
| AibermNot disclosed | Gemini 3 Pro Preview Thinking | $2.76/M out | model_ratio 1 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $12/M out | |
| AibermNot disclosed | Gemini 3 Pro | $2.76/M out | model_ratio 1 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $12/M out | |
| AibermNot disclosed | Gemini 3 Pro Mcpmark | $2.76/M out | model_ratio 1 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $12/M out | |
| OpenRouterOfficial | Google: Gemini 3 Flash Previewvia Google AI Studio | $3/M out | completion: 0.000003 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3 Flash PreviewReasoningvia Google AI Studio | $3/M out | internal_reasoning: 0.000003 / token (endpoint google-ai-studio) | |
| ReplicateOfficial partner | google/gemini-3-flash | $3/M out | $3 per million output tokens | |
| RunwareNot disclosed | Gemini 3 Flash | $3/M out | $0.000003 / outputToken | |
| 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. | |
| FalPlatform-hosted | Moondream3 Preview [Segment] | $3.5/M out | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| KIENot disclosed | Gemini 3 Pro | $3.5/M out | 700 credits per million tokens ($3.5)Claims official or Fal price $12/M out | |
| OpenRouterThird-party | Qwen: Qwen3 235B A22B Thinking 2507 | $3.5/M out | completion: 0.0000035 / token (endpoint venice/fp8) | |
| APIMartNot disclosed | o3-mini | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-2025-01-31 | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-2025-01-31-high | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-2025-01-31-low | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-2025-01-31-medium | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-high | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-low | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMartNot disclosed | o3-mini-medium | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| OpenRouterOfficial | MiniMax: MiniMax H3 Image | $3.8/M out | output_image: 0.0000038 USD / token | |
| RunwareNot disclosed | MiniMax H3 ImageImage output | $3.8/M out | $0.0000038 / outputToken · Image output | |
| OpenRouterOfficial | OpenAI: o3 (batch) | $4/M out | completion: 0.000004 / token (endpoint openai) | |
| AibermNot disclosed | Kimi K3 | $5.29/M out | model_ratio 2.3 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $15/M out | |
| APIMartNot disclosed | o3 | $6.4/M out | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMartNot disclosed | o3-2025-04-16 | $6.4/M out | Input $1.6 / Output $6.4 · Per 1M tokens | |
| OpenRouterOfficial | MiniMax: MiniMax H3 Image Highspeed | $7.6/M out | output_image: 0.0000076 USD / token | |
| RunwareNot disclosed | MiniMax H3 Image HighspeedImage output | $7.6/M out | $0.0000076 / outputToken · Image output | |
| APIMartNot disclosed | gpt-4-32k | $8/M out | Input $2 / Output $8 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4-32k-0613 | $8/M out | Input $2 / Output $8 · Per 1M tokens | |
| OpenRouterOfficial | OpenAI: o3 | $8/M out | completion: 0.000008 / token (endpoint openai) | |
| APIMartNot disclosed | gemini-3-pro-preview | $9.6/M out | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMartNot disclosed | gemini-3-pro-preview-thinking | $9.6/M out | Input $1.6 / Output $9.6 · Per 1M tokens | |
| RunwareNot disclosed | Gemini 4 ArgonThrough Nov 30 · 2026 | $10/M out | $0.00001 / outputToken · Through Nov 30, 2026 | |
| OpenRouterNot disclosed | MoonshotAI: Kimi K3via Relace · fp4 | $11.006/M out | completion: 0.0000110055 / token (endpoint relace/fp4) | |
| OpenRouterThird-party | MoonshotAI: Kimi K3 (batch) | $11.4/M out | completion: 0.0000114 / token (endpoint deepinfra/bf16) | |
| APIMartNot disclosed | kimi-k3 | $12/M out | Input $2.4 / Output $12 · Per 1M tokens | |
| KIENot disclosed | Kimi K3 | $12/M out | 2400 credits per million tokens ($12.00)Claims official or Fal price $15/M out | |
| OpenRouterOfficial | Google: Nano Banana Pro (Gemini 3 Pro Image)Text | $12/M out | completion: 0.000012 / token | |
| OpenRouterOfficial | Google: Nano Banana Pro (Gemini 3 Pro Image)Reasoning | $12/M out | internal_reasoning: 0.000012 / token | |
| OpenRouterOfficial | Google: Nano Banana Pro (Gemini 3 Pro Image Preview)Text | $12/M out | completion: 0.000012 / token | |
| OpenRouterOfficial | Google: Nano Banana Pro (Gemini 3 Pro Image Preview)Reasoning | $12/M out | internal_reasoning: 0.000012 / token | |
| ReplicateOfficial partner | google/gemini-3-pro≤ 200 · 000 | $12/M out | $0.012 per thousand output tokens (input token ≤ 200,000) | |
| RunwareNot disclosed | Kimi K3 | $15/M out | $0.000015 / outputToken | |
| ReplicateOfficial partner | google/gemini-3-pro> 200 · 000 | $18/M out | $0.018 per thousand output tokens (input token > 200,000) | |
| APIMartNot disclosed | o3-deep-research | $32/M out | Input $8 / Output $32 · Per 1M tokens | |
| APIMartNot disclosed | o3-deep-research-2025-06-26 | $32/M out | Input $8 / Output $32 · Per 1M tokens | |
| OpenRouterOfficial | Google: Nano Banana Pro (Gemini 3 Pro Image Preview)via Google AI Studio · global/flex | $60/M out | output_image: 0.00006 USD / token | |
| APIMartNot disclosed | o3-pro | $64/M out | Input $16 / Output $64 · Per 1M tokens | |
| APIMartNot disclosed | o3-pro-2025-06-10 | $64/M out | Input $16 / Output $64 · Per 1M tokens | |
| OpenRouterOfficial | OpenAI: o3 Pro | $80/M out | completion: 0.00008 / token (endpoint openai) | |
| OpenRouterOfficial | Google: Nano Banana Pro (Gemini 3 Pro Image)via Google AI Studio | $120/M out | output_image: 0.00012 USD / token | |
| OpenRouterOfficial | Google: Nano Banana Pro (Gemini 3 Pro Image)via Google Vertex | $120/M out | output_image: 0.00012 USD / token | |
| OpenRouterOfficial | Google: Nano Banana Pro (Gemini 3 Pro Image) | $120/M out | image_output: 0.00012 / token | |
| OpenRouterOfficial | Google: Nano Banana Pro (Gemini 3 Pro Image Preview)via Google AI Studio · global | $120/M out | output_image: 0.00012 USD / token | |
| OpenRouterOfficial | Google: Nano Banana Pro (Gemini 3 Pro Image Preview) | $120/M out | image_output: 0.00012 / token |
Per million tokens4
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| FalPlatform-hosted | Nemotron 3 Nano Omni | $6/M tokCheapest | $0.006 / 1000 tokens | |
| FalPlatform-hosted | Nemotron 3 Nano Omni | $6/M tokCheapest | $0.006 / 1000 tokens | |
| FalPlatform-hosted | Nemotron 3 Nano Omni | $10/M tok | $0.01 / 1000 tokens | |
| FalPlatform-hosted | Nemotron 3 Nano Omni | $10/M tok | $0.01 / 1000 tokens |
Per million cached input tokens (read)26
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterOfficial | Mistral: Ministral 3 3B 2512via Mistral · zdr | $0.01/M cache readCheapest | input_cache_read: 0.00000001 / token (endpoint mistral/zdr) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3 Nano 30B A3B | $0.012/M cache read | input_cache_read: 0.000000012 / token (endpoint nebius/fp8) | |
| RunwareNot disclosed | Gemma 4 31BPer 1M | $0.012/M cache read | $1.2e-8 / cachedInputToken | |
| OpenRouterOfficial | Mistral: Ministral 3 8B 2512via Mistral · zdr | $0.015/M cache read | input_cache_read: 0.000000015 / token (endpoint mistral/zdr) | |
| OpenRouterOfficial | Mistral: Ministral 3 14B 2512via Mistral · zdr | $0.02/M cache read | input_cache_read: 0.00000002 / token (endpoint mistral/zdr) | |
| OpenRouterThird-party | Tencent: Hy3off-peak 1600–0000 UTC · via Tencent · fp8 | $0.021/M cache read | input_cache_read: 0.000000020625 / token (utc_start 1600, utc_end 0; endpoint tencent/fp8) | |
| OpenRouterThird-party | Meta: Muse Glimmer 30B (batch) | $0.032/M cache read | input_cache_read: 0.000000032 / token (endpoint deepinfra/bf16) | |
| OpenRouterThird-party | Tencent: Hy3peak 0000–1600 UTC · via Tencent · fp8 | $0.033/M cache read | input_cache_read: 0.000000033 / token (utc_start 0, utc_end 1600; endpoint tencent/fp8) | |
| OpenRouterOfficial | Qwen: Qwen3 Coder Flash | $0.039/M cache read | input_cache_read: 0.000000039 / token (endpoint alibaba) | |
| OpenRouterThird-party | Meta: Muse Glimmer 30B | $0.04/M cache read | input_cache_read: 0.00000004 / token (endpoint deepinfra/bf16) | |
| OpenRouterOfficial | Mistral: Mistral Medium 3via Mistral · zdr | $0.04/M cache read | input_cache_read: 0.00000004 / token (endpoint mistral/zdr) | |
| OpenRouterThird-party | MiniMax: MiniMax M3 (batch) | $0.045/M cache read | input_cache_read: 0.0000000448 / token (endpoint deepinfra/fp8) | |
| RunwareNot disclosed | Shieldstral 1.0 3BPer 1M | $0.045/M cache read | $4.5e-8 / cachedInputToken | |
| OpenRouterOfficial | Google: Gemini 3 Flash Previewvia Google AI Studio | $0.05/M cache read | input_cache_read: 0.00000005 / token (endpoint google-ai-studio) | |
| OpenRouterThird-party | Google: Gemma 3 12Bvia NextBit · int4 | $0.05/M cache read | input_cache_read: 0.00000005 / token (endpoint nextbit/int4) | |
| OpenRouterThird-party | MiniMax: MiniMax M3via CoreWeave · fp4 | $0.05/M cache read | input_cache_read: 0.00000005 / token (endpoint coreweave/fp4) | |
| OpenRouterOfficial | Mistral: Mistral Large 3 2512via Mistral · zdr | $0.05/M cache read | input_cache_read: 0.00000005 / token (endpoint mistral/zdr) | |
| OpenRouterNot disclosed | Motif Technologies: Motif 3 | $0.06/M cache read | input_cache_read: 0.00000006 / token (endpoint kt) | |
| OpenRouterThird-party | Tencent: Hy3 preview | $0.06/M cache read | input_cache_read: 0.00000006 / token (endpoint gmicloud/bf16) | |
| RunwareNot disclosed | MiniMax M3≤ 512K context | $0.06/M cache read | $6e-8 / cachedInputToken · ≤ 512K context | |
| OpenRouterOfficial | Qwen: Qwen3 Coder FlashPrompt > 32K | $0.065/M cache read | input_cache_read: 0.000000065 / token (>32000; endpoint alibaba) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder Next | $0.07/M cache read | input_cache_read: 0.00000007 / token (endpoint parasail/bf16) | |
| AibermNot disclosed | o3 Mini | $0.076/M cache read | model_ratio 0.55 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| OpenRouterOfficial | Google: Gemini 3 Flash Previewvia Google AI Studio | $0.1/M cache read | input_audio_cache: 0.0000001 / token (endpoint google-ai-studio) | |
| OpenRouterNot disclosed | Google: Gemma 4 31Bvia KT | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint kt) | |
| OpenRouterNot disclosed | NVIDIA: Nemotron 3 Ultravia KT | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint kt) |
