8,429 prices on 4,154 listings · last collected 6 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.
Model
Gemini 
Claude 
Qwen 
DeepSeek 
GLM 
Mistral 
Kimi 
Llama 
MiniMax 
Hunyuan 
Nemotron 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 1201–1300 of 2,608
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | AionLabs: Aion 3.5 Mini | $1.4/M out | completion: 0.0000014 / token | |
| OpenRouter | Z.ai: GLM 5.3 | $1.4/M out | completion: 0.0000014 / token | |
| OpenRouter | Z.ai: GLM Latest | $1.4/M out | completion: 0.0000014 / token | |
| kie.ai | Claude-Haiku-4-5 | $1.425/M out | 285 credits per million tokens ($1.425)Claims fal charges $5/M out | |
| APIMart | glm-4.6 | $1.44/M out | Input $0.36 / Output $1.44 · Per 1M tokens | |
| APIMart | glm-5.1 | $1.44/M out | Input $0.8 / Output $1.44 · Per 1M tokens | |
| Replicate | deepseek-ai/deepseek-v3 | $1.45/M out | $1.45 per million output tokens | |
| kie.ai | gpt-6-1-terra | $1.5/M out | 300 credits per million tokens ($1.5)Claims fal charges $5/M out | |
| OpenRouter | Cohere: Command A+ | $1.5/M out | completion: 0.0000015 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview (batch) | $1.5/M out | completion: 0.0000015 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview (batch)Reasoning | $1.5/M out | internal_reasoning: 0.0000015 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite | $1.5/M out | completion: 0.0000015 / token | |
| OpenRouter | Google: Gemini 3.1 Flash LiteReasoning | $1.5/M out | internal_reasoning: 0.0000015 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite Preview | $1.5/M out | completion: 0.0000015 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite PreviewReasoning | $1.5/M out | internal_reasoning: 0.0000015 / token | |
| OpenRouter | Mistral: Mistral Large 3 2512 | $1.5/M out | completion: 0.0000015 / token | |
| OpenRouter | Perceptron: Perceptron Mk1 | $1.5/M out | completion: 0.0000015 / token | |
| OpenRouter | Perceptron: Perceptron Mk1.5 | $1.5/M out | completion: 0.0000015 / token | |
| APIMart | deepseek-v4-pro | $1.5429/M out | Input $0.5143 / Output $1.5429 · Per 1M tokens | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-02-15 | $1.56/M out | completion: 0.00000156 / token | |
| APIMart | gpt-3.5-turbo-instruct | $1.596/M out | Input $1.2 / Output $1.596 · Per 1M tokens | |
| APIMart | davinci-002 | $1.6/M out | Input $1.6 / Output $1.6 · Per 1M tokens | |
| APIMart | gpt-3.5-turbo-1106 | $1.6/M out | Input $0.8 / Output $1.6 · Per 1M tokens | |
| APIMart | gpt-5-mini | $1.6/M out | Input $0.2 / Output $1.6 · Per 1M tokens | |
| APIMart | gpt-5-mini-2025-08-07 | $1.6/M out | Input $0.2 / Output $1.6 · Per 1M tokens | |
| APIMart | gpt-5.1-codex-mini | $1.6/M out | Input $0.2 / Output $1.6 · Per 1M tokens | |
| APIMart | grok-build-0.1 | $1.6/M out | Input $0.8 / Output $1.6 · Per 1M tokens | |
| OpenRouter | AionLabs: Aion-2.0 | $1.6/M out | completion: 0.0000016 / token | |
| OpenRouter | AionLabs: Aion-RP 1.0 (8B) | $1.6/M out | completion: 0.0000016 / token | |
| OpenRouter | OpenAI: GPT-4.1 Mini | $1.6/M out | completion: 0.0000016 / token | |
| Replicate | openai/gpt-4.1-mini | $1.6/M out | $1.60 per million output tokens | |
| OpenRouter | Qwen: Qwen3 Coder FlashPrompt > 32K | $1.625/M out | completion: 0.000001625 / token (>32000) | |
| APIMart | glm-4.7 | $1.68/M out | Input $0.4 / Output $1.68 · Per 1M tokens | |
| APIMart | kimi-k2-instruct | $1.68/M out | Input $0.4 / Output $1.68 · Per 1M tokens | |
| APIMart | kimi-k2-thinking | $1.68/M out | Input $0.4 / Output $1.68 · Per 1M tokens | |
| APIMart | deepseek-r1 | $1.792/M out | Input $0.448 / Output $1.792 · Per 1M tokens | |
| APIMart | deepseek-r1-250528 | $1.792/M out | Input $0.448 / Output $1.792 · Per 1M tokens | |
| OpenRouter | OpenAI: GPT-5.6 LunaPrompt > 272K | $1.8/M out | completion: 0.0000018 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna ProPrompt > 272K | $1.8/M out | completion: 0.0000018 / token (>272000) | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-04-20 | $1.8/M out | completion: 0.0000018 / token | |
| OpenRouter | Xiaomi: MiMo-V2.5-Pro | $1.8/M out | completion: 0.0000018 / token | |
| OpenRouter | Z.ai: GLM 4.5V | $1.8/M out | completion: 0.0000018 / token | |
| OpenRouter | Google: Gemini 3.6 Flash (batch) | $1.875/M out | completion: 0.000001875 / token | |
| OpenRouter | Google: Gemini 3.6 Flash (batch)Reasoning | $1.875/M out | internal_reasoning: 0.000001875 / token | |
| OpenRouter | Google: Gemini 3.7 Flash (batch) | $1.875/M out | completion: 0.000001875 / token | |
| OpenRouter | Google: Gemini 3.7 Flash (batch)Reasoning | $1.875/M out | internal_reasoning: 0.000001875 / token | |
| OpenRouter | Google: Gemini 3.8 Flash (batch) | $1.875/M out | completion: 0.000001875 / token | |
| OpenRouter | Google: Gemini 3.8 Flash (batch)Reasoning | $1.875/M out | internal_reasoning: 0.000001875 / token | |
| OpenRouter | Qwen: Qwen3.8 27B | $1.875/M out | completion: 0.000001875 / token | |
| OpenRouter | Morph: Morph V3 Large | $1.9/M out | completion: 0.0000019 / token | |
| OpenRouter | Qwen: Qwen3 VL 235B A22B Instruct | $1.9/M out | completion: 0.0000019 / token | |
| APIMart | gpt-4o-mini-realtime-preview | $1.92/M out | Input $0.48 / Output $1.92 · Per 1M tokens | |
| APIMart | gpt-4o-mini-realtime-preview-2024-12-17 | $1.92/M out | Input $0.48 / Output $1.92 · Per 1M tokens | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-02-15Prompt > 256K | $1.95/M out | completion: 0.00000195 / token (>256000) | |
| OpenRouter | Qwen: Qwen3.6 Plus | $1.95/M out | completion: 0.00000195 / token | |
| APIMart | gemini-3.5-flash-lite | $1.9992/M out | Input $0.24 / Output $1.9992 · Per 1M tokens | |
| APIMart | grok-4.20-0309-non-reasoning | $2/M out | Input $1 / Output $2 · Per 1M tokens | |
| APIMart | grok-4.20-0309-reasoning | $2/M out | Input $1 / Output $2 · Per 1M tokens | |
| APIMart | grok-4.20-multi-agent-0309 | $2/M out | Input $1 / Output $2 · Per 1M tokens | |
| APIMart | grok-4.3 | $2/M out | Input $1 / Output $2 · Per 1M tokens | |
| OpenRouter | ByteDance Seed: Seed 1.6 | $2/M out | completion: 0.000002 / token | |
| OpenRouter | ByteDance Seed: Seed-2.0-Lite | $2/M out | completion: 0.000002 / token | |
| OpenRouter | Mistral: Devstral 2 2512 | $2/M out | completion: 0.000002 / token | |
| OpenRouter | Mistral: Mistral Medium 3 | $2/M out | completion: 0.000002 / token | |
| OpenRouter | Mistral: Mistral Medium 3.1 | $2/M out | completion: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-3.5 Turbo (older v0613) | $2/M out | completion: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-5 Mini | $2/M out | completion: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-5.1-Codex-Mini | $2/M out | completion: 0.000002 / token | |
| OpenRouter | Qwen: Qwen3.8 27B (batch) | $2/M out | completion: 0.000002 / token | |
| OpenRouter | SpaceXAI: Grok 4.3 (batch) | $2/M out | completion: 0.000002 / token | |
| OpenRouter | SpaceXAI: Grok Build 0.1 | $2/M out | completion: 0.000002 / token | |
| OpenRouter | Xiaomi: MiMo-V2.5 | $2/M out | completion: 0.000002 / token | |
| OpenRouter | Z.ai: GLM 4.6 | $2/M out | completion: 0.000002 / token | |
| Replicate | openai/gpt-5-mini | $2/M out | $2 per million output tokens | |
| Replicate | openai/gpt-5-structuredgpt-5-mini | $2/M out | $2 per million output tokens (gpt-5-mini) | |
| Replicate | deepseek-ai/deepseek-v3.1 | $2.016/M out | $2.016 per million output tokens | |
| OpenRouter | Qwen: Qwen3.5-122B-A10B | $2.08/M out | completion: 0.00000208 / token | |
| OpenRouter | Mistral: Mistral Large 4 | $2.1/M out | completion: 0.0000021 / token | |
| OpenRouter | DeepSeek: R1 0528 | $2.15/M out | completion: 0.00000215 / token | |
| fal | Isaac 0.1 | $2.17/M out | $0.26 per 1M input tokens, $2.17 per 1M output tokens | |
| fal | Isaac 0.1 [OpenAI Compatible Endpoint] | $2.17/M out | $0.26 per 1M input tokens, $2.17 per 1M output tokens | |
| Replicate | perceptron-ai-inc/isaac-0.1 | $2.17/M out | $2.17 per million output tokens | |
| OpenRouter | MiniMax: MiniMax M1 | $2.2/M out | completion: 0.0000022 / token | |
| OpenRouter | OpenAI: o3 Mini (batch) | $2.2/M out | completion: 0.0000022 / token | |
| OpenRouter | OpenAI: o4 Mini (batch) | $2.2/M out | completion: 0.0000022 / token | |
| OpenRouter | Z.ai: GLM 4.5 | $2.2/M out | completion: 0.0000022 / token | |
| OpenRouter | Z.ai: GLM 4.7 | $2.2/M out | completion: 0.0000022 / token | |
| OpenRouter | OpenAI: GPT-5.4 Mini (batch) | $2.25/M out | completion: 0.00000225 / token | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-04-20Prompt > 256K | $2.25/M out | completion: 0.00000225 / token (>256000) | |
| OpenRouter | MoonshotAI: Kimi K2 0711 | $2.3/M out | completion: 0.0000023 / token | |
| OpenRouter | Qwen: Qwen-PlusPrompt > 256K | $2.34/M out | completion: 0.00000234 / token (>256000) | |
| APIMart | gemini-3-flash-preview | $2.4/M out | Input $0.4 / Output $2.4 · Per 1M tokens | |
| APIMart | gemini-3-flash-preview-nothinking | $2.4/M out | Input $0.4 / Output $2.4 · Per 1M tokens | |
| APIMart | gemini-3-flash-preview-thinking | $2.4/M out | Input $0.4 / Output $2.4 · Per 1M tokens | |
| APIMart | gpt-3.5-turbo-0613 | $2.4/M out | Input $1.2 / Output $2.4 · Per 1M tokens | |
| APIMart | qwen-turbo | $2.4/M out | Input $0.24 / Output $2.4 · Per 1M tokens | |
| kie.ai | grok-4-5 | $2.4/M out | 480 credits per million tokens ($2.40)Claims fal charges $6/M out | |
| kie.ai | grok-4-6 | $2.4/M out | 480 credits per million tokens ($2.40)Claims fal charges $6/M out | |
| kie.ai | grok-4-7 | $2.4/M out | 480 credits per million tokens ($2.40)Claims fal charges $6/M out | |
| OpenRouter | NVIDIA: Nemotron 3 Ultra | $2.4/M out | completion: 0.0000024 / token |
