8,429 prices on 4,154 listings · last collected 4 h ago · 36 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on six 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.
Unit
All 2,608Per second of output 5Per image 32Per million input tokens 866Per million output tokens 859Per million tokens 5Per million cached input tokens (read) 425Per million cache-write tokens 188Per thousand characters 2Per second of compute time 12Per run (default parameters) 200Other units (see the platform’s wording) 14
Showing 201–300 of 866
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | Meta: Llama Guard 4 12B | $0.18/M in | prompt: 0.00000018 / token | |
| OpenRouter | Tencent: Hy3 preview | $0.18/M in | prompt: 0.00000018 / token | |
| Replicate | openai/gpt-oss-120b | $0.18/M in | $0.18 per million input tokens | |
| OpenRouter | Qwen: Qwen3.6 Flash | $0.1875/M in | prompt: 0.0000001875 / token | |
| OpenRouter | MoonshotAI: Kimi K3 | $0.192/M in | prompt: 0.000000192 / token | |
| OpenRouter | Qwen: Qwen3 Coder Flash | $0.195/M in | prompt: 0.000000195 / token | |
| APIMart | gemini-3.1-flash-lite-preview | $0.2/M in | Input $0.2 / Output $1.2 · Per 1M tokens | |
| APIMart | gpt-5-mini | $0.2/M in | Input $0.2 / Output $1.6 · Per 1M tokens | |
| APIMart | gpt-5-mini-2025-08-07 | $0.2/M in | Input $0.2 / Output $1.6 · Per 1M tokens | |
| APIMart | gpt-5.1-codex-mini | $0.2/M in | Input $0.2 / Output $1.6 · Per 1M tokens | |
| OpenRouter | ByteDance Seed: Seed-2.0-MiniPrompt > 128K | $0.2/M in | prompt: 0.0000002 / token (>128000) | |
| OpenRouter | Venice: Uncensored | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | Google: Gemma 4 31B | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | Mistral: Ministral 3 14B 2512 | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | Mistral: Saba | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | NVIDIA: Nemotron 3.5 Content Safety | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-4.1 Mini (batch) | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.4 Nano | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro (batch)Prompt > 272K | $0.2/M in | prompt: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna (batch)Prompt > 272K | $0.2/M in | prompt: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 LunaPrompt > 272K | $0.2/M in | prompt: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna ProPrompt > 272K | $0.2/M in | prompt: 0.0000002 / token (>272000) | |
| OpenRouter | Qwen: Qwen3.7 FlashPrompt > 256K | $0.2/M in | prompt: 0.0000002 / token (>256000) | |
| OpenRouter | Ricursive: Ripple 65B Preview | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | StepFun: Step 3.7 Flash | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT Luna LatestPrompt > 272K | $0.2/M in | prompt: 0.0000002 / token (>272000) | |
| Replicate | meta/llama-guard-4-12b | $0.2/M in | $0.20 per million input tokens | |
| APIMart | deepseek-v3-0324 | $0.2056/M in | Input $0.2056 / Output $0.8224 · Per 1M tokens | |
| APIMart | deepseek-v3.2 | $0.2056/M in | Input $0.2056 / Output $0.3084 · Per 1M tokens | |
| APIMart | deepseek-v3.2-exp | $0.2056/M in | Input $0.2056 / Output $0.3084 · Per 1M tokens | |
| OpenRouter | MiniMax: MiniMax M2.7 | $0.21/M in | prompt: 0.00000021 / token | |
| OpenRouter | Qwen: Qwen3 VL 235B A22B Instruct | $0.21/M in | prompt: 0.00000021 / token | |
| APIMart | minimax-m2.1 | $0.216/M in | Input $0.216 / Output $0.864 · Per 1M tokens | |
| OpenRouter | MiniMax: MiniMax M3 (batch) | $0.224/M in | prompt: 0.000000224 / token | |
| kie.ai | Gemini 3.6 Flash | $0.225/M in | 45 credits per million tokens ($0.225)Claims fal charges $0.75/M in | |
| kie.ai | Gemini 3.7 Flash | $0.225/M in | 45 credits per million tokens ($0.225)Claims fal charges $0.75/M in | |
| kie.ai | Gemini 3.8 Flash | $0.225/M in | 45 credits per million tokens ($0.225)Claims fal charges $0.75/M in | |
| APIMart | qwen3.6-plus | $0.2286/M in | Input $0.2286 / Output $1.3718 · Per 1M tokens | |
| APIMart | qwen3.7-plus | $0.2286/M in | Input $0.2286 / Output $0.9146 · Per 1M tokens | |
| OpenRouter | Qwen: Qwen3.7 Plus (batch) | $0.23/M in | prompt: 0.00000023 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Pro 0423 | $0.231246/M in | prompt: 0.000000231246 / token | |
| APIMart | gemini-3.5-flash-lite | $0.24/M in | Input $0.24 / Output $1.9992 · Per 1M tokens | |
| APIMart | minimax-m2.5 | $0.24/M in | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMart | minimax-m2.7 | $0.24/M in | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMart | minimax-m3 | $0.24/M in | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMart | qwen-turbo | $0.24/M in | Input $0.24 / Output $2.4 · Per 1M tokens | |
| OpenRouter | Meta: Muse Glimmer 30B (batch) | $0.24/M in | prompt: 0.00000024 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)Prompt > 100K | $0.25/M in | prompt: 0.00000025 / token (>100000) | |
| OpenRouter | ByteDance Seed: Seed 1.6 | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | ByteDance Seed: Seed-2.0-Lite | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | DeepSeek: DeepSeek V3.1 | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview (batch) | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite Preview | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite (batch)Audio input | $0.25/M in | audio: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-5 Mini | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-5.1-Codex-Mini | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | Qwen: Qwen3 VL 8B Instruct | $0.25/M in | prompt: 0.00000025 / token | |
| Replicate | meta/llama-4-maverick-instruct | $0.25/M in | $0.25 per million input tokens | |
| Replicate | openai/gpt-5-mini | $0.25/M in | $0.25 per million input tokens | |
| Replicate | openai/gpt-5-structuredgpt-5-mini | $0.25/M in | $0.25 per million input tokens (gpt-5-mini) | |
| fal | Isaac 0.1 | $0.26/M in | $0.26 per 1M input tokens, $2.17 per 1M output tokens | |
| fal | Isaac 0.1 [OpenAI Compatible Endpoint] | $0.26/M in | $0.26 per 1M input tokens, $2.17 per 1M output tokens | |
| OpenRouter | DeepSeek: DeepSeek V3.2 | $0.26/M in | prompt: 0.00000026 / token | |
| OpenRouter | Qwen: Qwen-Plus | $0.26/M in | prompt: 0.00000026 / token | |
| OpenRouter | Qwen: Qwen3.5-122B-A10B | $0.26/M in | prompt: 0.00000026 / token | |
| OpenRouter | Qwen: Qwen3.5-27B | $0.26/M in | prompt: 0.00000026 / token | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-02-15 | $0.26/M in | prompt: 0.00000026 / token | |
| Replicate | perceptron-ai-inc/isaac-0.1 | $0.26/M in | $0.26 per million input tokens | |
| Replicate | qwen/qwen3-235b-a22b-instruct-2507 | $0.264/M in | $0.264 per million input tokens | |
| OpenRouter | DeepSeek: DeepSeek V3.1 Terminus | $0.27/M in | prompt: 0.00000027 / token | |
| OpenRouter | DeepSeek: DeepSeek V3.2 Exp | $0.27/M in | prompt: 0.00000027 / token | |
| kie.ai | Claude-Haiku-4-5 | $0.275/M in | 55 credits per million tokens ($0.275)Claims fal charges $1/M in | |
| Replicate | qwen/qwen3-7-plus256000 | $0.276/M in | $0.276 per million input tokens (,256000) | |
| OpenRouter | DeepSeek: DeepSeek V3 0324 | $0.29/M in | prompt: 0.00000029 / token | |
| OpenRouter | Qwen: Qwen3 VL 30B A3B Thinking | $0.29/M in | prompt: 0.00000029 / token | |
| kie.ai | gpt-6-1-terra | $0.3/M in | 60 credits per million tokens ($0.3)Claims fal charges $1/M in | |
| OpenRouter | Amazon: Nova 2 Lite | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Cohere: Command A+ | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Google: Gemini 2.5 Flash | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Google: Gemini 2.5 Flash LiteAudio input | $0.3/M in | audio: 0.0000003 / token | |
| OpenRouter | Google: Gemini 3.5 Flash LiteAudio input | $0.3/M in | audio: 0.0000003 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Meituan: LongCat 2.0 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Meta: Muse Glimmer 30B | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | MiniMax: MiniMax M2.5 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | MiniMax: MiniMax M3 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Mistral: Codestral 2508 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Moondream: Moondream 3 Preview | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Moondream: Moondream 3.1 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Qwen: Qwen3 Coder 480B A35B | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-04-20 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Reflection: Beam 1.0 501B A23B | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | TheDrummer: Cydonia 24B V4.1 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Z.ai: GLM 4.6V | $0.3/M in | prompt: 0.0000003 / token | |
| Replicate | google/gemini-2.5-flash | $0.3/M in | $0.30 per million input tokens | |
| APIMart | babbage-002 | $0.32/M in | Input $0.32 / Output $0.32 · Per 1M tokens | |
| APIMart | gpt-4.1-mini | $0.32/M in | Input $0.32 / Output $1.28 · Per 1M tokens |
