8,429 prices on 4,154 listings · last collected 18 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 6601–6700 of 7,913
Per million cached input tokens (read)100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | OpenAI: GPT-5 Image Mini | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-5.4 | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-5.4 (batch)Prompt > 272K | $0.25/M cache read | input_cache_read: 0.00000025 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.5 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | OpenAI: o3 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Qwen: Qwen3.8 2.4T A95B | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Qwen: Qwen3.8 Max (0902) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Sakana: Fugu Max | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | TheDrummer: Skyfall 36B V2 | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Pareto 26.9 | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Anthropic: Claude Fable Latest | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Z.ai: GLM 5.1 | $0.26/M cache read | input_cache_read: 0.00000026 / token | |
| OpenRouter | OpenAI: o3 Mini (batch) | $0.275/M cache read | input_cache_read: 0.000000275 / token | |
| kie.ai | gpt-6-astra | $0.28/M cache read | 56 credits per million tokens ($0.28)Claims fal charges $1/M cache read | |
| OpenRouter | Meta: Llama 3.3 70B Instruct | $0.295/M cache read | input_cache_read: 0.000000295 / token | |
| OpenRouter | Qwen: Qwen3.7 Max | $0.295/M cache read | input_cache_read: 0.000000295 / token | |
| OpenRouter | Anthropic: Claude Sonnet 4.5 | $0.3/M cache read | input_cache_read: 0.0000003 / token | |
| OpenRouter | Anthropic: Claude Sonnet 4.5 (batch)Prompt > 200K | $0.3/M cache read | input_cache_read: 0.0000003 / token (>200000) | |
| OpenRouter | Anthropic: Claude Sonnet 4.6 | $0.3/M cache read | input_cache_read: 0.0000003 / token | |
| OpenRouter | Fireworks: Ember-1 | $0.3/M cache read | input_cache_read: 0.0000003 / token | |
| OpenRouter | Google: Gemini 3.5 Flash | $0.3/M cache read | input_audio_cache: 0.0000003 / token | |
| OpenRouter | Qwen: Qwen3.5 397B A17B | $0.3/M cache read | input_cache_read: 0.0000003 / token | |
| OpenRouter | SpaceXAI: Grok 4.5 | $0.3/M cache read | input_cache_read: 0.0000003 / token | |
| OpenRouter | SpaceXAI: Grok 4.3 (batch)Prompt > 200K | $0.32/M cache read | input_cache_read: 0.00000032 / token (>200000) | |
| OpenRouter | DeepSeek: R1 0528 | $0.35/M cache read | input_cache_read: 0.00000035 / token | |
| OpenRouter | ReMM SLERP 13B | $0.35/M cache read | input_cache_read: 0.00000035 / token | |
| OpenRouter | Google: Gemini 3.1 Pro PreviewPrompt > 200K | $0.4/M cache read | input_audio_cache: 0.0000004 / token (>200000) | |
| OpenRouter | Google: Gemini 3.1 Pro PreviewPrompt > 200K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | Google: Gemini 3.1 Pro Preview Custom ToolsPrompt > 200K | $0.4/M cache read | input_audio_cache: 0.0000004 / token (>200000) | |
| OpenRouter | Google: Gemini 3.1 Pro Preview Custom ToolsPrompt > 200K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | Mancer: Weaver (alpha) | $0.4/M cache read | input_cache_read: 0.0000004 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol | $0.4/M cache read | input_cache_read: 0.0000004 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol Pro | $0.4/M cache read | input_cache_read: 0.0000004 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol Pro (batch)Prompt > 272K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Sol (batch)Prompt > 272K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 TerraPrompt > 272K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Terra ProPrompt > 272K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 SolPrompt > 272K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Sol ProPrompt > 272K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | Qwen: Qwen2.5 VL 72B Instruct | $0.4/M cache read | input_cache_read: 0.0000004 / token | |
| OpenRouter | SpaceXAI: Grok 4.20Prompt > 200K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.20 Multi-AgentPrompt > 200K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.3Prompt > 200K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.6 (batch) | $0.4/M cache read | input_cache_read: 0.0000004 / token | |
| OpenRouter | SpaceXAI: Grok 4.7 (batch) | $0.4/M cache read | input_cache_read: 0.0000004 / token | |
| OpenRouter | SpaceXAI: Grok Build 0.1Prompt > 200K | $0.4/M cache read | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | Anthropic: Claude Fable 5 (batch) | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Opus 4.5 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Opus 4.6 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Opus 4.7 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Opus 4.8 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Opus 5 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-4.1 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-5.4Prompt > 272K | $0.5/M cache read | input_cache_read: 0.0000005 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.5 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-5.5 (batch)Prompt > 272K | $0.5/M cache read | input_cache_read: 0.0000005 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra Pro (batch) | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-6 Astra (batch) | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT Chat Latest | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: o3 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | Qwen: Qwen3.8 Max Prime | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | Sakana: Fugu Ultra | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | Sakana: Fugu Ultra v2 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | SpaceXAI: Grok 4.6 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | SpaceXAI: Grok 4.7 | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | xAI: Grok Latest | $0.5/M cache read | input_cache_read: 0.0000005 / token | |
| OpenRouter | Z.ai: GLM 5.3 Prime | $0.56/M cache read | input_cache_read: 0.00000056 / token | |
| OpenRouter | Anthropic: Claude Sonnet 4.5Prompt > 200K | $0.6/M cache read | input_cache_read: 0.0000006 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.5Prompt > 200K | $0.6/M cache read | input_cache_read: 0.0000006 / token (>200000) | |
| OpenRouter | Amazon: Nova Premier 1.0 | $0.625/M cache read | input_cache_read: 0.000000625 / token | |
| OpenRouter | OpenAI: GPT-4o (batch) | $0.625/M cache read | input_cache_read: 0.000000625 / token | |
| OpenRouter | AionLabs: Aion-3.0 | $0.75/M cache read | input_cache_read: 0.00000075 / token | |
| OpenRouter | AionLabs: Aion 3.5 | $0.75/M cache read | input_cache_read: 0.00000075 / token | |
| OpenRouter | Anthropic: Claude Opus 4.1 (batch) | $0.75/M cache read | input_cache_read: 0.00000075 / token | |
| OpenRouter | OpenAI: GPT-5.6 SolPrompt > 272K | $0.8/M cache read | input_cache_read: 0.0000008 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Sol ProPrompt > 272K | $0.8/M cache read | input_cache_read: 0.0000008 / token (>272000) | |
| OpenRouter | SpaceXAI: Grok 4.6 (batch)Prompt > 200K | $0.8/M cache read | input_cache_read: 0.0000008 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.7 (batch)Prompt > 200K | $0.8/M cache read | input_cache_read: 0.0000008 / token (>200000) | |
| OpenRouter | Anthropic: Claude Fable 5 | $1/M cache read | input_cache_read: 0.000001 / token | |
| OpenRouter | OpenAI: GPT-5.5Prompt > 272K | $1/M cache read | input_cache_read: 0.000001 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra | $1/M cache read | input_cache_read: 0.000001 / token | |
| OpenRouter | OpenAI: GPT-6 Astra Pro | $1/M cache read | input_cache_read: 0.000001 / token | |
| OpenRouter | OpenAI: GPT-6 Astra Pro (batch)Prompt > 272K | $1/M cache read | input_cache_read: 0.000001 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra (batch)Prompt > 272K | $1/M cache read | input_cache_read: 0.000001 / token (>272000) | |
| OpenRouter | Sakana: Fugu UltraPrompt > 272K | $1/M cache read | input_cache_read: 0.000001 / token (>272000) | |
| OpenRouter | Sakana: Fugu Ultra v2Prompt > 272K | $1/M cache read | input_cache_read: 0.000001 / token (>272000) | |
| OpenRouter | SpaceXAI: Grok 4.6Prompt > 200K | $1/M cache read | input_cache_read: 0.000001 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.7Prompt > 200K | $1/M cache read | input_cache_read: 0.000001 / token (>200000) | |
| OpenRouter | OpenAI: GPT Astra Latest | $1/M cache read | input_cache_read: 0.000001 / token | |
| OpenRouter | xAI: Grok LatestPrompt > 200K | $1/M cache read | input_cache_read: 0.000001 / token (>200000) | |
| kie.ai | gpt-image-2-6-flareText to imageImage editingText Input | $1.125/M cache read | 225 credits per million tokens ($1.125)Claims fal charges $1.25/M cache read | |
| kie.ai | gpt-image-2-6-sunburstText to imageImage editingText Input | $1.125/M cache read | 225 credits per million tokens ($1.125)Claims fal charges $1.25/M cache read | |
| fal | GPT Image 2 APItext | $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 2.5 Flare EditImage 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 | |
| fal | GPT Image 2.5 Flare 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 2.5 Sunburst Edit Image 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 | |
| fal | GPT Image 2.5 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 2.6 Flare EditImage 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 | |
| fal | GPT Image 2.6 Flare 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 2.6 Sunburst EditImage 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 |
