8,429 prices on 4,154 listings · last collected 11 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 8,429Per second of output 1,919Per minute 34Per video 486Per 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) 1,023Other units (see the platform’s wording) 325
Showing 4701–4800 of 8,429
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | OpenAI: GPT-5.1 (batch) | $0.625/M in | prompt: 0.000000625 / token | |
| OpenRouter | OpenAI: GPT-5 (batch) | $0.625/M in | prompt: 0.000000625 / token | |
| OpenRouter | Google: Gemma 2 27B | $0.65/M in | prompt: 0.00000065 / token | |
| OpenRouter | MoonshotAI: Kimi K2.6 | $0.65/M in | prompt: 0.00000065 / token | |
| Replicate | meta/llama-2-70b | $0.65/M in | $0.65 per million input tokens | |
| Replicate | meta/llama-2-70b-chat | $0.65/M in | $0.65 per million input tokens | |
| Replicate | meta/meta-llama-3-70b | $0.65/M in | $0.65 per million input tokens | |
| Replicate | meta/meta-llama-3-70b-instruct | $0.65/M in | $0.65 per million input tokens | |
| OpenRouter | Qwen2.5 Coder 32B Instruct | $0.66/M in | prompt: 0.00000066 / token | |
| Replicate | moonshotai/kimi-k2-thinking | $0.66/M in | $0.66 per million input tokens | |
| Replicate | deepseek-ai/deepseek-v3.1 | $0.672/M in | $0.672 per million input tokens | |
| kie.ai | Gemini 2.5 Pro TTSText to Speech | $0.7/M in | 140 credits per million tokens ($0.7)Claims fal charges $1/M in | |
| kie.ai | Gemini 3.1 Flash TTSText to Speech | $0.7/M in | 140 credits per million tokens ($0.7)Claims fal charges $1/M in | |
| OpenRouter | AionLabs: Aion-3.0-Mini | $0.7/M in | prompt: 0.0000007 / token | |
| OpenRouter | AionLabs: Aion 3.5 Mini | $0.7/M in | prompt: 0.0000007 / token | |
| OpenRouter | Mistral: Mistral Large 4 | $0.7/M in | prompt: 0.0000007 / token | |
| OpenRouter | Meta: Llama 3.1 70B Instruct | $0.72/M in | prompt: 0.00000072 / token | |
| Replicate | moonshotai/kimi-k2.5 | $0.72/M in | $0.72 per million input tokens | |
| APIMart | kimi-k2.6 | $0.7429/M in | Input $0.7429 / Output $3.083 · Per 1M tokens | |
| APIMart | kimi-k2.7-code | $0.7429/M in | Input $0.7429 / Output $3.083 · Per 1M tokens | |
| OpenRouter | Google: Gemini 3.5 Flash (batch) | $0.75/M in | prompt: 0.00000075 / token | |
| OpenRouter | Google: Gemini 3.6 FlashAudio input | $0.75/M in | audio: 0.00000075 / token | |
| OpenRouter | Google: Gemini 3.6 Flash | $0.75/M in | prompt: 0.00000075 / token | |
| OpenRouter | Google: Gemini 3.7 FlashAudio input | $0.75/M in | audio: 0.00000075 / token | |
| OpenRouter | Google: Gemini 3.7 Flash | $0.75/M in | prompt: 0.00000075 / token | |
| OpenRouter | Mistral: Mistral Medium 3.5 (batch) | $0.75/M in | prompt: 0.00000075 / token | |
| OpenRouter | OpenAI: GPT-5.4 Mini | $0.75/M in | prompt: 0.00000075 / token | |
| OpenRouter | Qwen: Qwen3.6 FlashPrompt > 256K | $0.75/M in | prompt: 0.00000075 / token (>256000) | |
| OpenRouter | Google: Gemini Flash LatestAudio input | $0.75/M in | audio: 0.00000075 / token | |
| OpenRouter | Google: Gemini Flash Latest | $0.75/M in | prompt: 0.00000075 / token | |
| OpenRouter | OpenAI: GPT Mini Latest | $0.75/M in | prompt: 0.00000075 / token | |
| OpenRouter | Qwen: Qwen-PlusPrompt > 256K | $0.78/M in | prompt: 0.00000078 / token (>256000) | |
| APIMart | claude-haiku-4-5-20251001 | $0.8/M in | Input $0.8 / Output $4 · Per 1M tokens | |
| APIMart | claude-haiku-4-5-20251001-thinking | $0.8/M in | Input $0.8 / Output $4 · Per 1M tokens | |
| APIMart | glm-5 | $0.8/M in | Input $0.8 / Output $1.28 · Per 1M tokens | |
| APIMart | glm-5.1 | $0.8/M in | Input $0.8 / Output $1.44 · Per 1M tokens | |
| APIMart | gpt-3.5-turbo-1106 | $0.8/M in | Input $0.8 / Output $1.6 · Per 1M tokens | |
| APIMart | gpt-6.1-terra | $0.8/M in | Input $0.8 / Output $4 · Per 1M tokens | |
| APIMart | grok-build-0.1 | $0.8/M in | Input $0.8 / Output $1.6 · Per 1M tokens | |
| kie.ai | claude-sonnet-5-5 | $0.8/M in | 160 credits per million tokens ($0.8)Claims fal charges $2/M in | |
| kie.ai | Gemini 4 Argon | $0.8/M in | 160 credits per million tokens ($0.80)Claims fal charges $2/M in | |
| kie.ai | grok-4-5 | $0.8/M in | 160 credits per million tokens ($0.80)Claims fal charges $2/M in | |
| kie.ai | grok-4-6 | $0.8/M in | 160 credits per million tokens ($0.80)Claims fal charges $2/M in | |
| kie.ai | grok-4-7 | $0.8/M in | 160 credits per million tokens ($0.80)Claims fal charges $2/M in | |
| kie.ai | Kimi K3.1 Pro | $0.8/M in | 160 credits per million tokens ($0.80)Claims fal charges $2/M in | |
| OpenRouter | AionLabs: Aion-2.0 | $0.8/M in | prompt: 0.0000008 / token | |
| OpenRouter | AionLabs: Aion-RP 1.0 (8B) | $0.8/M in | prompt: 0.0000008 / token | |
| OpenRouter | Amazon: Nova Pro 1.0 | $0.8/M in | prompt: 0.0000008 / token | |
| OpenRouter | Morph: Morph V3 Fast | $0.8/M in | prompt: 0.0000008 / token | |
| OpenRouter | Qwen: Qwen2.5 VL 72B Instruct | $0.8/M in | prompt: 0.0000008 / token | |
| OpenRouter | Pareto 26.10 | $0.8/M in | prompt: 0.0000008 / token | |
| OpenRouter | Pareto Latest | $0.8/M in | prompt: 0.0000008 / token | |
| OpenRouter | Google: Gemini 3.8 FlashAudio input | $0.825/M in | audio: 0.000000825 / token | |
| OpenRouter | Google: Gemini 3.8 Flash | $0.825/M in | prompt: 0.000000825 / token | |
| Replicate | qwen/qwen3-7-plus256000 | $0.826/M in | $0.826 per million input tokens (256000,) | |
| OpenRouter | Tencent: Hy4 preview | $0.834/M in | prompt: 0.000000834 / token | |
| kie.ai | claude-sonnet-4-5 | $0.85/M in | 170 credits per million tokens ($0.850)Claims fal charges $3/M in | |
| kie.ai | Claude-Sonnet-4-6 | $0.85/M in | 170 credits per million tokens ($0.850)Claims fal charges $3/M in | |
| kie.ai | claude-sonnet-5 | $0.85/M in | 170 credits per million tokens ($0.850)Claims fal charges $2/M in | |
| OpenRouter | Relace: Relace Apply 3 | $0.85/M in | prompt: 0.00000085 / token | |
| OpenRouter | Sao10K: Llama 3.1 Euryale 70B v2.2 | $0.85/M in | prompt: 0.00000085 / token | |
| OpenRouter | OpenAI: GPT-5.2 (batch) | $0.875/M in | prompt: 0.000000875 / token | |
| APIMart | o1-mini | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o1-mini-2024-09-12 | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-2025-01-31 | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-2025-01-31-high | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-2025-01-31-low | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-2025-01-31-medium | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-high | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-low | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-medium | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o4-mini | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o4-mini-2025-04-16 | $0.88/M in | Input $0.88 / Output $3.52 · Per 1M tokens | |
| OpenRouter | Morph: Morph V3 Large | $0.9/M in | prompt: 0.0000009 / token | |
| APIMart | glm-5.2 | $0.9142/M in | Input $0.9142 / Output $3.1998 · Per 1M tokens | |
| OpenRouter | MoonshotAI: Kimi K3 (batch) | $0.917/M in | prompt: 0.000000917 / token | |
| OpenRouter | Sakana: Sakana Namazu | $0.95/M in | prompt: 0.00000095 / token | |
| Replicate | moonshotai/kimi-k2.6 | $0.95/M in | $0.95 per million input tokens | |
| OpenRouter | Qwen: Qwen3.7 PlusPrompt > 256K | $0.96/M in | prompt: 0.00000096 / token (>256000) | |
| APIMart | gpt-4o-mini-transcribe | $1/M in | Input $1 / Output $4 · Per 1M tokens | |
| APIMart | gpt-5 | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5-2025-08-07 | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5-chat-latest | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5-codex | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5-search-api | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5-search-api-2025-10-14 | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.1 | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.1-2025-11-13 | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.1-chat-latest | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.1-codex | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.1-codex-max | $1/M in | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | grok-4.20-0309-non-reasoning | $1/M in | Input $1 / Output $2 · Per 1M tokens | |
| APIMart | grok-4.20-0309-reasoning | $1/M in | Input $1 / Output $2 · Per 1M tokens | |
| APIMart | grok-4.20-multi-agent-0309 | $1/M in | Input $1 / Output $2 · Per 1M tokens | |
| APIMart | grok-4.3 | $1/M in | Input $1 / Output $2 · Per 1M tokens | |
| OpenRouter | Anthropic: Claude Haiku 4.5 | $1/M in | prompt: 0.000001 / token | |
| OpenRouter | Anthropic: Claude Sonnet 5.5 (batch) | $1/M in | prompt: 0.000001 / token | |
| OpenRouter | Anthropic: Claude Sonnet 5 (batch) | $1/M in | prompt: 0.000001 / token | |
| OpenRouter | ByteDance Seed: Seed-2.0-CodePrompt > 128K | $1/M in | prompt: 0.000001 / token (>128000) |
