8,429 prices on 4,154 listings · last collected 38 min 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 7,913Per second of output 1,911Per minute 34Per video 485Per image 1,521Per megapixel 308Per million input tokens 982Per million output tokens 977Per million tokens 48Per million cached input tokens (read) 458Per million cache-write tokens 191Per thousand characters 64Per second of compute time 93Per run (default parameters) 516Other units (see the platform’s wording) 325
Showing 6701–6800 of 7,913
Per million cached input tokens (read)24
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| fal | GPT Image 2.6 Sunburst Text to ImageText to imagetext | $1.25/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2 APIImage editingtext | $1.25/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| OpenRouter | OpenAI: GPT-4o | $1.25/M cache read | input_cache_read: 0.00000125 / token | |
| OpenRouter | OpenAI: GPT-4o (2024-08-06) | $1.25/M cache read | input_cache_read: 0.00000125 / token | |
| OpenRouter | OpenAI: GPT-4o (2024-11-20) | $1.25/M cache read | input_cache_read: 0.00000125 / token | |
| OpenRouter | OpenAI: GPT-5 Image | $1.25/M cache read | input_cache_read: 0.00000125 / token | |
| OpenRouter | Anthropic: Claude Opus 4.1 | $1.5/M cache read | input_cache_read: 0.0000015 / token | |
| kie.ai | gpt-image-2-6-flareText to imageImage editing | $1.8/M cache read | 360 credits per million tokens ($1.8)Claims fal charges $2/M cache read | |
| kie.ai | gpt-image-2-6-sunburstText to imageImage editing | $1.8/M cache read | 360 credits per million tokens ($1.8)Claims fal charges $2/M cache read | |
| fal | GPT Image 2 API | $2/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.5 Flare EditImage editing | $2/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.5 Flare Text to ImageText to image | $2/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.5 Sunburst Edit Image editing | $2/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.5 Sunburst Text to ImageText to image | $2/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.6 Flare EditImage editing | $2/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.6 Flare Text to ImageText to image | $2/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.6 Sunburst EditImage editing | $2/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.6 Sunburst Text to ImageText to image | $2/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2 APIImage editing | $2/M cache read | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| OpenRouter | OpenAI: GPT-5.4 Image 2 | $2/M cache read | input_cache_read: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-6 AstraPrompt > 272K | $2/M cache read | input_cache_read: 0.000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra ProPrompt > 272K | $2/M cache read | input_cache_read: 0.000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT Astra LatestPrompt > 272K | $2/M cache read | input_cache_read: 0.000002 / token (>272000) | |
| OpenRouter | Magnum v4 72B | $2.5/M cache read | input_cache_read: 0.0000025 / token |
Per million cache-write tokens76
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| kie.ai | gpt-6-luna | $0.0375/M cache writeCheapest | 7.5 credits per million tokens ($0.0375)Claims fal charges $0.125/M cache write | |
| OpenRouter | Qwen: Qwen3.7 Flash5-min cache | $0.038/M cache write | input_cache_write: 0.000000038 / token | |
| OpenRouter | Google: Gemini 3.6 Flash5-min cache | $0.0416667/M cache write | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.6 Flash (batch)5-min cache | $0.0416667/M cache write | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.7 Flash5-min cache | $0.0416667/M cache write | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.7 Flash (batch)5-min cache | $0.0416667/M cache write | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.8 Flash5-min cache | $0.0416667/M cache write | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.8 Flash (batch)5-min cache | $0.0416667/M cache write | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini Flash Latest5-min cache | $0.0416667/M cache write | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)5-min cache | $0.0625/M cache write | input_cache_write: 0.0000000625 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro (batch)5-min cache | $0.0625/M cache write | input_cache_write: 0.0000000625 / token | |
| OpenRouter | OpenAI: GPT-6 Luna (batch)5-min cache | $0.0625/M cache write | input_cache_write: 0.0000000625 / token | |
| kie.ai | gpt-5.6-luna | $0.07/M cache write | 14 credits per million tokens ($0.07)Claims fal charges $0.25/M cache write | |
| OpenRouter | Google: Gemini 2.5 Flash5-min cache | $0.0833333/M cache write | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Nano Banana (Gemini 2.5 Flash Image)5-min cache | $0.0833333/M cache write | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 2.5 Flash Lite5-min cache | $0.0833333/M cache write | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview5-min cache | $0.0833333/M cache write | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite5-min cache | $0.0833333/M cache write | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite Preview5-min cache | $0.0833333/M cache write | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 3.5 Flash5-min cache | $0.0833333/M cache write | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite5-min cache | $0.0833333/M cache write | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)1-h cache | $0.1/M cache write | input_cache_write_1h: 0.0000001 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.55-min cache | $0.125/M cache write | input_cache_write: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT-6 Luna5-min cache | $0.125/M cache write | input_cache_write: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro5-min cache | $0.125/M cache write | input_cache_write: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro (batch)5-min cachePrompt > 272K | $0.125/M cache write | input_cache_write: 0.000000125 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna (batch)5-min cachePrompt > 272K | $0.125/M cache write | input_cache_write: 0.000000125 / token (>272000) | |
| OpenRouter | Qwen: Qwen3.7 Flash5-min cachePrompt > 32K | $0.125/M cache write | input_cache_write: 0.000000125 / token (>32000) | |
| OpenRouter | Anthropic: Claude Haiku Latest5-min cache | $0.125/M cache write | input_cache_write: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT Luna Latest5-min cache | $0.125/M cache write | input_cache_write: 0.000000125 / token | |
| OpenRouter | Google: Gemini 4 Argon5-min cache | $0.1875/M cache write | input_cache_write: 0.0000001875 / token | |
| OpenRouter | Google: Gemini 4 Argon (batch)5-min cache | $0.1875/M cache write | input_cache_write: 0.0000001875 / token | |
| OpenRouter | Google: Gemini Pro Latest5-min cache | $0.1875/M cache write | input_cache_write: 0.0000001875 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.51-h cache | $0.2/M cache write | input_cache_write_1h: 0.0000002 / token | |
| OpenRouter | Anthropic: Claude Haiku Latest1-h cache | $0.2/M cache write | input_cache_write_1h: 0.0000002 / token | |
| OpenRouter | Qwen: Qwen3.6 Flash5-min cache | $0.234375/M cache write | input_cache_write: 0.000000234375 / token | |
| OpenRouter | Qwen: Qwen3 Coder Flash5-min cache | $0.24375/M cache write | input_cache_write: 0.00000024375 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna5-min cache | $0.25/M cache write | input_cache_write: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro5-min cache | $0.25/M cache write | input_cache_write: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-6 Luna5-min cachePrompt > 272K | $0.25/M cache write | input_cache_write: 0.00000025 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna Pro5-min cachePrompt > 272K | $0.25/M cache write | input_cache_write: 0.00000025 / token (>272000) | |
| OpenRouter | Qwen: Qwen3.7 Flash5-min cachePrompt > 256K | $0.25/M cache write | input_cache_write: 0.00000025 / token (>256000) | |
| OpenRouter | OpenAI: GPT Luna Latest5-min cachePrompt > 272K | $0.25/M cache write | input_cache_write: 0.00000025 / token (>272000) | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)5-min cachePrompt > 100K | $0.3125/M cache write | input_cache_write: 0.0000003125 / token (>100000) | |
| OpenRouter | Qwen: Qwen-Plus5-min cache | $0.325/M cache write | input_cache_write: 0.000000325 / token | |
| kie.ai | gpt-6-1-terra | $0.375/M cache write | 75 credits per million tokens ($0.375)Claims fal charges $1.25/M cache write | |
| OpenRouter | Google: Gemini 2.5 Pro5-min cache | $0.375/M cache write | input_cache_write: 0.000000375 / token | |
| OpenRouter | Google: Gemini 2.5 Pro Preview 06-055-min cache | $0.375/M cache write | input_cache_write: 0.000000375 / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image)5-min cache | $0.375/M cache write | input_cache_write: 0.000000375 / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image Preview)5-min cache | $0.375/M cache write | input_cache_write: 0.000000375 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview5-min cache | $0.375/M cache write | input_cache_write: 0.000000375 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview Custom Tools5-min cache | $0.375/M cache write | input_cache_write: 0.000000375 / token | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-04-205-min cache | $0.375/M cache write | input_cache_write: 0.000000375 / token | |
| OpenRouter | Qwen: Qwen3.7 Plus5-min cache | $0.4/M cache write | input_cache_write: 0.0000004 / token | |
| OpenRouter | Qwen: Qwen3 Coder Flash5-min cachePrompt > 32K | $0.40625/M cache write | input_cache_write: 0.00000040625 / token (>32000) | |
| OpenRouter | Qwen: Qwen3.6 Plus5-min cache | $0.40625/M cache write | input_cache_write: 0.00000040625 / token | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-04-205-min cachePrompt > 256K | $0.46875/M cache write | input_cache_write: 0.00000046875 / token (>256000) | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)1-h cachePrompt > 100K | $0.5/M cache write | input_cache_write_1h: 0.0000005 / token (>100000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna5-min cachePrompt > 272K | $0.5/M cache write | input_cache_write: 0.0000005 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro5-min cachePrompt > 272K | $0.5/M cache write | input_cache_write: 0.0000005 / token (>272000) | |
| OpenRouter | Anthropic: Claude Haiku 4.5 (batch)5-min cache | $0.625/M cache write | input_cache_write: 0.000000625 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.55-min cachePrompt > 100K | $0.625/M cache write | input_cache_write: 0.000000625 / token (>100000) | |
| OpenRouter | OpenAI: GPT-6.1 Terra Pro (batch)5-min cache | $0.625/M cache write | input_cache_write: 0.000000625 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra (batch)5-min cache | $0.625/M cache write | input_cache_write: 0.000000625 / token | |
| OpenRouter | Anthropic: Claude Haiku Latest5-min cachePrompt > 100K | $0.625/M cache write | input_cache_write: 0.000000625 / token (>100000) | |
| OpenRouter | Qwen: Qwen3 Coder Flash5-min cachePrompt > 128K | $0.65/M cache write | input_cache_write: 0.00000065 / token (>128000) | |
| kie.ai | gpt-5.6-terra | $0.7/M cache write | 140 credits per million tokens ($0.70)Claims fal charges $2.5/M cache write | |
| kie.ai | gpt-6-1-sol | $0.75/M cache write | 150 credits per million tokens ($0.75)Claims fal charges $2.5/M cache write | |
| kie.ai | gpt-6-sol | $0.75/M cache write | 150 credits per million tokens ($0.75)Claims fal charges $2.5/M cache write | |
| OpenRouter | Qwen: Qwen3.6 Flash5-min cachePrompt > 256K | $0.9375/M cache write | input_cache_write: 0.0000009375 / token (>256000) | |
| OpenRouter | Qwen: Qwen-Plus5-min cachePrompt > 256K | $0.975/M cache write | input_cache_write: 0.000000975 / token (>256000) | |
| OpenRouter | Anthropic: Claude Haiku 4.5 (batch)1-h cache | $1/M cache write | input_cache_write_1h: 0.000001 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.51-h cachePrompt > 100K | $1/M cache write | input_cache_write_1h: 0.000001 / token (>100000) | |
| OpenRouter | Anthropic: Claude Haiku Latest1-h cachePrompt > 100K | $1/M cache write | input_cache_write_1h: 0.000001 / token (>100000) | |
| OpenRouter | Qwen: Qwen3.7 Plus5-min cachePrompt > 256K | $1.2/M cache write | input_cache_write: 0.0000012 / token (>256000) | |
| OpenRouter | Anthropic: Claude Haiku 4.55-min cache | $1.25/M cache write | input_cache_write: 0.00000125 / token |
