10,634 prices on 4,757 listings · last collected 22 min ago · 399 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on eight 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
Claude 
Gemini 
Qwen 
DeepSeek 
GLM 
Kimi 
Mistral 
MiniMax 
Hunyuan 
Nemotron 
Llama Unit price
All 3,235Per second of output 13Per image 6Per million input tokens 1,107Per million output tokens 1,071Per million tokens 5Per million cached input tokens (read) 594Per million cache-write tokens 224Per thousand characters 2Per second of compute time 12Per run (default parameters) 193Other units (see the platform’s wording) 8
Showing 201–300 of 594
Per million cached input tokens (read)100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| 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) | |
| OpenRouterOfficial | OpenAI: GPT-4.1 Mini (batch) | $0.05/M cache read | input_cache_read: 0.00000005 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Sol Pro (batch) | $0.05/M cache read | input_cache_read: 0.00000005 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Sol (batch) | $0.05/M cache read | input_cache_read: 0.00000005 / token (endpoint openai) | |
| OpenRouterOfficial partner | OpenAI: GPT-6.1 Terravia Azure | $0.05/M cache read | input_cache_read: 0.00000005 / token (endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-6.1 Terra Provia Azure | $0.05/M cache read | input_cache_read: 0.00000005 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Terra Pro (batch)Prompt > 272K | $0.05/M cache read | input_cache_read: 0.00000005 / token (>272000; endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Terra (batch)Prompt > 272K | $0.05/M cache read | input_cache_read: 0.00000005 / token (>272000; endpoint openai) | |
| OpenRouterThird-party | Reflection: Beam 1.0 501B A23Bvia Nebius · fp4 | $0.05/M cache read | input_cache_read: 0.00000005 / token (endpoint nebius/fp4) | |
| OpenRouterNot disclosed | Anthropic: Claude Haiku LatestPrompt > 100K | $0.05/M cache read | input_cache_read: 0.00000005 / token (>100000) | |
| OpenRouterNot disclosed | OpenAI: GPT Terra Latest | $0.05/M cache read | input_cache_read: 0.00000005 / token | |
| RunwareNot disclosed | Claude Haiku 5.5> 100K context | $0.05/M cache read | $5e-8 / cachedInputToken · > 100K context | |
| RunwareNot disclosed | GPT-6.1 Terra≤ 272K context | $0.05/M cache read | $5e-8 / cachedInputToken · ≤ 272K context | |
| OpenRouterOfficial | Qwen: Qwen-Plus | $0.052/M cache read | input_cache_read: 0.000000052 / token (endpoint alibaba) | |
| AibermNot disclosed | GPT-5.3 Codex | $0.054/M cache read | model_ratio 0.39 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| AibermNot disclosed | GPT-5.3 Codex | $0.054/M cache read | model_ratio 0.39 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| OpenRouterThird-party | Z.ai: GLM 4.6Vvia Novita · bf16 | $0.055/M cache read | input_cache_read: 0.000000055 / token (endpoint novita/bf16) | |
| KIENot disclosed | gpt-5.6-terra | $0.056/M cache read | 11.2 credits per million tokens ($0.056)Claims official or Fal price $0.2/M cache read | |
| KIENot disclosed | gpt-6-sol | $0.06/M cache read | 12 credits per million tokens ($0.06)Claims official or Fal price $0.2/M cache read | |
| OpenRouterThird-party | Elorian: Glimpse | $0.06/M cache read | input_cache_read: 0.00000006 / token (endpoint together) | |
| 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 | OpenAI: GPT-5.1 (batch) | $0.063/M cache read | input_cache_read: 0.0000000625 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-5 (batch) | $0.063/M cache read | input_cache_read: 0.0000000625 / token (endpoint openai) | |
| OpenRouterOfficial | Qwen: Qwen3.7 Plusvia Alibaba | $0.064/M cache read | input_cache_read: 0.000000064 / token (endpoint alibaba) | |
| OpenRouterOfficial | Qwen: Qwen3 Coder FlashPrompt > 32K | $0.065/M cache read | input_cache_read: 0.000000065 / token (>32000; endpoint alibaba) | |
| OpenRouterThird-party | MoonshotAI: Kimi K2.6via Baidu · fp4 | $0.066/M cache read | input_cache_read: 0.0000000656 / token (endpoint baidu/fp4) | |
| OpenRouterNot disclosed | Z.ai: GLM Latest | $0.069/M cache read | input_cache_read: 0.0000000689 / token | |
| AibermNot disclosed | Qwen3.5 Plus | $0.069/M cache read | model_ratio 0.75 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Qwen3.6 Plus | $0.069/M cache read | model_ratio 0.75 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| OpenRouterOfficial | Mistral: Mistral Large 4via Mistral · zdr | $0.07/M cache read | input_cache_read: 0.00000007 / token (endpoint mistral/zdr) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder Next | $0.07/M cache read | input_cache_read: 0.00000007 / token (endpoint parasail/bf16) | |
| AibermNot disclosed | Claude Sonnet 5.5 | $0.072/M cache read | model_ratio 3.1304 × $2/M · group default ×0.23 · cache_ratio 0.05 | |
| AibermNot disclosed | Claude Opus 4.5 20251101 | $0.075/M cache read | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| AibermNot disclosed | Claude Opus 4.5 20251101 Thinking | $0.075/M cache read | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| AibermNot disclosed | Claude Opus 4.6 | $0.075/M cache read | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| AibermNot disclosed | Claude Opus 4.6 Thinking | $0.075/M cache read | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| AibermNot disclosed | Claude Opus 4.7 | $0.075/M cache read | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| AibermNot disclosed | Claude Opus 4.8 | $0.075/M cache read | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouterOfficial | Google: Gemini 3.5 Flash (batch) | $0.075/M cache read | input_cache_read: 0.000000075 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.6 Flashvia Google AI Studio | $0.075/M cache read | input_audio_cache: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.6 Flashvia Google AI Studio | $0.075/M cache read | input_cache_read: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.7 Flashvia Google AI Studio | $0.075/M cache read | input_audio_cache: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.7 Flashvia Google AI Studio | $0.075/M cache read | input_cache_read: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.8 Flashvia Google AI Studio | $0.075/M cache read | input_audio_cache: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.8 Flashvia Google AI Studio | $0.075/M cache read | input_cache_read: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial partner | OpenAI: GPT-4o-minivia Azure | $0.075/M cache read | input_cache_read: 0.000000075 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-4o-mini (2024-07-18) | $0.075/M cache read | input_cache_read: 0.000000075 / token (endpoint openai) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.4 Minivia Azure | $0.075/M cache read | input_cache_read: 0.000000075 / token (endpoint azure) | |
| OpenRouterOfficial | Z.ai: GLM 5.3 FlashX | $0.075/M cache read | input_cache_read: 0.000000075 / token (endpoint z-ai/fp8) | |
| OpenRouterOfficial | Z.ai: GLM 5.3 FlashX Legal | $0.075/M cache read | input_cache_read: 0.000000075 / token (endpoint z-ai/fp8) | |
| OpenRouterNot disclosed | Google: Gemini Flash Latest | $0.075/M cache read | input_audio_cache: 0.000000075 / token | |
| OpenRouterNot disclosed | Google: Gemini Flash Latest | $0.075/M cache read | input_cache_read: 0.000000075 / token | |
| OpenRouterNot disclosed | OpenAI: GPT Mini Latest | $0.075/M cache read | input_cache_read: 0.000000075 / token | |
| RunwareNot disclosed | Gemini 3.7 FlashPer 1M | $0.075/M cache read | $7.5e-8 / cachedInputToken | |
| RunwareNot disclosed | Gemini 3.8 FlashPer 1M | $0.075/M cache read | $7.5e-8 / cachedInputToken | |
| AibermNot disclosed | o3 Mini | $0.076/M cache read | model_ratio 0.55 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| RunwareNot disclosed | DeepSeek-V4-Pro-0813Per 1M | $0.079/M cache read | $7.9e-8 / cachedInputToken | |
| KIENot disclosed | Kimi K3.1 Pro | $0.08/M cache read | 16 credits per million tokens ($0.08)Claims official or Fal price $0.2/M cache read | |
| OpenRouterThird-party | Thinking Machines: Inkling Small (batch) | $0.08/M cache read | input_cache_read: 0.00000008 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Xiaomi: MiMo-V2.5 | $0.08/M cache read | input_cache_read: 0.00000008 / token (endpoint venice/fp8) | |
| OpenRouterThird-party | Z.ai: GLM 4.6via Venice · fp4 | $0.08/M cache read | input_cache_read: 0.00000008 / token (endpoint venice/fp4) | |
| OpenRouterThird-party | Z.ai: GLM 4.7via DeepInfra · fp4 | $0.08/M cache read | input_cache_read: 0.00000008 / token (endpoint deepinfra/fp4) | |
| AibermNot disclosed | Kimi K2.5 | $0.083/M cache read | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Kimi K2.6 | $0.083/M cache read | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | GPT-5.2 Codex | $0.083/M cache read | model_ratio 0.6 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| AibermNot disclosed | Kimi K2.5 | $0.083/M cache read | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Kimi K2.5 Thinking | $0.083/M cache read | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | GPT-5.2 Codex | $0.083/M cache read | model_ratio 0.6 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| OpenRouterOfficial | OpenAI: GPT-5.2 (batch) | $0.088/M cache read | input_cache_read: 0.0000000875 / token (endpoint openai) | |
| AibermNot disclosed | Claude Sonnet | $0.088/M cache read | model_ratio 1.917 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouterThird-party | Z.ai: GLM 5.1via Chutes · fp8 | $0.09/M cache read | input_cache_read: 0.00000009 / token (endpoint chutes/fp8) | |
| AibermNot disclosed | MiniMax M2.7 | $0.091/M cache read | model_ratio 0.9852 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Gemini 3.5 Flash | $0.092/M cache read | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Gemini 3.6 Flash | $0.092/M cache read | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Gemini 3.7 Flash | $0.092/M cache read | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Gemini 3.8 Flash | $0.092/M cache read | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | MiMo V2 Omni | $0.092/M cache read | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Grok 4.5 | $0.095/M cache read | model_ratio 0.8261 × $2/M · group default ×0.23 · cache_ratio 0.25 | |
| AibermNot disclosed | Grok 4.6 | $0.095/M cache read | model_ratio 0.8261 × $2/M · group default ×0.23 · cache_ratio 0.25 | |
| AibermNot disclosed | GPT-5.6 Sol | $0.097/M cache read | model_ratio 1.413 × $2/M · group default ×0.23 · cache_ratio 0.15 | |
| OpenRouterNot disclosed | DeepSeek: DeepSeek Pro Latest | $0.1/M cache read | input_cache_read: 0.0000000999 / token | |
| OpenRouterOfficial | Anthropic: Claude Fable 5.2 (batch) | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint anthropic) | |
| OpenRouterOfficial partner | Anthropic: Claude Haiku 4.5via Azure · global | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint azure/global) | |
| OpenRouterOfficial | Anthropic: Claude Opus 5.5 (batch) | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint anthropic) | |
| OpenRouterOfficial partner | Anthropic: Claude Sonnet 5.5via Google · global | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Anthropic: Claude Sonnet 5 (batch) | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint anthropic) | |
| OpenRouterThird-party | ByteDance: UI-TARS 7B | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint parasail/bf16) | |
| OpenRouterOfficial | Google: Gemini 2.5 Flashvia Google AI Studio | $0.1/M cache read | input_audio_cache: 0.0000001 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3 Flash Previewvia Google AI Studio | $0.1/M cache read | input_audio_cache: 0.0000001 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 4 Argon | $0.1/M cache read | input_audio_cache: 0.0000001 / token | |
| OpenRouterOfficial | Google: Gemini 4 Argon | $0.1/M cache read | input_cache_read: 0.0000001 / token | |
| OpenRouterOfficial | Google: Gemini 4 Carbonvia Google AI Studio | $0.1/M cache read | input_audio_cache: 0.0000001 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 4 Carbonvia Google AI Studio | $0.1/M cache read | input_cache_read: 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) | |
| OpenRouterOfficial partner | OpenAI: GPT-4.1 Minivia Azure | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-5.6 Terra Pro (batch) | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint openai) |
