Loading the model catalog…
Every model and sub-provider pool our supply marketplace publishes, including the ones we do not sell. Prices and offer counts come from the same 5-minute board as the ladders above.
Loading the model catalog…
Every model and sub-provider pool our supply marketplace publishes, including the ones we do not sell. Prices and offer counts come from the same 5-minute board as the ladders above.
Price per 1M tokens (input / output)/ | |||
|---|---|---|---|
OpenAIGPT-6 Sol | Input / Output $0.1096 / $0.548cache ×0.1 | Savings−95% | Cacheread 0.01096 |
OpenAIGPT-6 Luna | Input / Output $0.0055 / $0.0274cache ×0.1 | Savings−95% | Cacheread 0.00055 |
OpenAIGPT-6 Astra | Input / Output $0.548 / $2.7398cache ×0.1 | Savings−95% | Cacheread 0.0548 |
AnthropicClaude Opus 5.5 | Input / Output ≈ $0.3766 / $1.8828cache ×0.09 | Savings−92% | Cacheread 0.029232 |
DeepSeekDeepSeek V4.1 Flash | Input / Output ≈ $0.0135 / $0.0538cache ×0.1 | Savings−96% | Cacheread 0.00112 |
xAIGrok 4.7 | Input / Output $0.0572 / $0.1715cache ×0.25 | Cacheread 0.0143 | |
OpenAIGPT-5.6 Luna | Input / Output ≈ $0.0059 / $0.0354cache ×0.1 | Savings−99% | Cacheread 0.00027 |
OpenAIGPT-5.6 Terra | Input / Output ≈ $0.0383 / $0.2296cache ×0.1 | Savings−97% | Cacheread 0.0056 |
OpenAIGPT-5.6 Sol | Input / Output ≈ $0.0859 / $0.5152cache ×0.1 | Savings−98% | Cacheread 0.008 |
AnthropicClaude Opus 5 | Input / Output $0.8334 / $4.1667cache ×0.1 | Savings−83% | Cacheread 0.08334 |
AnthropicClaude Sonnet 5 | Input / Output $0.3334 / $1.6667cache ×0.1 | Savings−89% | Cacheread 0.03334 |
MoonshotKimi K3 | Input / Output ≈ $0.1284 / $0.642cache ×0.1 | Savings−94% | Cacheread 0.01758 |
Zhipu AIGLM-5.3 | Input / Output ≈ $0.0167 / $0.0524cache ×0.1 | Savings−93% | Cacheread 0.01 |
DeepSeekDeepSeek V4 Flash | Input / Output ≈ $0.0191 / $0.0572cache ×0.1 | Savings−85% | Cacheread 0.00176 |
DeepSeekDeepSeek V4 Pro | Input / Output ≈ $0.0458 / $0.1372cache ×0.1 | Savings−86% | Cacheread 0.00528 |
MetaMuse Ember 1.0 | Input / Output $0.071 / $0.355cache ×0.1 | Cacheread 0.0071 | |
GoogleGemini 4 Carbon | Input / Output $0.5715 / $2.8572cache ×0.1 | Cacheread 0.05715 | |
AnthropicClaude Fable 5.2 | Input / Output ≈ $0.8746 / $4.3729cache ×0.03 | Savings−92% | Cacheread 0.017067 |
OpenAIGPT-6.1 Terra | Input / Output $0.0548 / $0.274cache ×0.05 | Cacheread 0.00274 | |
MoonshotKimi K3.1 Pro | Input / Output ≈ $0.1612 / $0.806cache ×0.1 | Cacheread 0.016 | |
DeepSeekDeepSeek V4 Pro Uncensored | Input / Output $1.3334 / $2.6667cache ×1 | Cacheread 1.3334 | |
OtherHermes 4-405B | Input / Output $1.60 / $6.40cache ×1 | Cacheread 1.60 | |
MoonshotKimi K2.6 Uncensored | Input / Output $1.56 / $9.7867cache ×1 | Cacheread 1.56 | |
XiaomiMimo V2.5 Uncensored | Input / Output $1.00 / $5.3334cache ×1 | Cacheread 1.00 | |
| Input / Output $2.6667 / $8.00cache ×1 | Cacheread 2.6667 | ||
| Input / Output $1.50 / $8.80cache ×1 | Cacheread 1.50 | ||
Alibaba (Qwen)Qwen3.8-27B Uncensored | Input / Output $1.6667 / $5.00cache ×1 | Cacheread 1.6667 | |
MetaMuse Spark 1.3 | Input / Output ≈ $0.7657 / $2.6033cache ×0.1 | Cacheread 0.08875 | |
MiniMaxMiniMax M3.1 Flash | Input / Output ≈ $0.0143 / $0.0569cache ×0.1 | Cacheread 0.00129 | |
MoonshotKimi K2.8 | Input / Output ≈ $0.0586 / $0.2466cache ×0.1 | Cacheread 0.0038 | |
| Input / Output $0.1715 / $0.6429cache ×0.21 | Cacheread 0.035729 | ||
DeepSeekDeepSeek V4.1 Flash 1017 | Input / Output ≈ $0.0125 / $0.0497cache ×0.1 | Savings−93% | Cacheread 0.00108 |
GoogleGemini 4 Argon | Input / Output $1.4286 / $8.5715cache ×0.1 | Savings−20% | Cacheread 0.14286 |
MetaLlama 4 Maverick | Input / Output $0.3334 / $1.3334 | none | |
| Input / Output $0.1417 / $0.6667 | none | ||
NVIDIANemotron 3.5 Lightning | Input / Output $0.10 / $0.2667cache ×0.5 | Cacheread 0.05 | |
AnthropicClaude Haiku 5.5 | Input / Output $0.0267 / $0.1334cache ×0.1 | Savings−74% | Cacheread 0.00267 |
Alibaba (Qwen)Qwen 3.8 Omni Flash | Input / Output ≈ $0.0447 / $0.1399cache ×0.1 | Cacheread 0.00022 | |
OpenAIGPT-6.1 Sol | Input / Output $0.1096 / $0.548cache ×0.05 | Savings−95% | Cacheread 0.00548 |
AnthropicClaude Sonnet 5.5 | Input / Output ≈ $0.3458 / $1.7286cache ×0.06 | Savings−91% | Cacheread 0.010421 |
XiaomiMiMo V2.6 Flash | Input / Output ≈ $0.1001 / $0.2001cache ×0.1 | Cacheread 0.01 | |
XiaomiMiMo V2.6 Pro | Input / Output ≈ $0.3112 / $0.6223cache ×0.1 | Cacheread 0.03108 | |
GoogleGemma 4 Uncensored | Input / Output $0.20 / $0.9334cache ×1 | Cacheread 0.20 | |
Zhipu AIGLM-5.2 Uncensored | Input / Output $6.6667 / $6.6667cache ×0.06 | Cacheread 0.400002 | |
Zhipu AIGLM-5.3 Flash Uncensored | Input / Output $0.2667 / $1.0667cache ×0.5 | Cacheread 0.13335 | |
Zhipu AIGLM-5.3 Uncensored | Input / Output $6.6667 / $6.6667cache ×0.06 | Cacheread 0.400002 | |
GoogleGemini 3.8 Flash | Input / Output ≈ $0.0587 / $0.2933cache ×0.1 | Savings−99% | Cacheread 0.00097 |
AnthropicClaude Fable 5.1 | Input / Output ≈ $0.7237 / $3.6182cache ×0.03 | Savings−91% | Cacheread 0.021668 |
TencentTencent Hy4 Preview | Input / Output ≈ $0.0398 / $0.1194cache ×0.1 | Cacheread 0.00334 | |
Alibaba (Qwen)Qwen 3.8 Flash | Input / Output ≈ $0.0288 / $0.0901cache ×0.1 | Cacheread 0.0027 | |
Zhipu AIGLM-5.3 Flash | Input / Output ≈ $0.0139 / $0.0461cache ×0.1 | Savings−93% | Cacheread 0.00112 |
Alibaba (Qwen)Qwen3.8-27B | Input / Output ≈ $0.0054 / $0.0324cache ×0.1 | Cacheread 0.0005 | |
ByteDanceDoubao Seed 2.1 Turbo (ByteDance) | Input / Output $0.7536 / $3.7679cache ×1 | Cacheread 0.7536 | |
Alibaba (Qwen)Qwen3.8-2.4T-A95B | Input / Output ≈ $0.0202 / $0.0605cache ×0.1 | Cacheread 0.002 | |
Alibaba (Qwen)Qwen3.8 Max | Input / Output ≈ $0.0138 / $0.0414cache ×0.1 | Savings−92% | Cacheread 0.01543 |
TencentTencent Hy3 | Input / Output ≈ $0.0033 / $0.0135cache ×0.1 | Savings−98% | Cacheread 0.0002 |
Zhipu AIGLM-5.2 | Input / Output ≈ $0.0345 / $0.1084cache ×0.1 | Savings−80% | Cacheread 0.0098 |
MoonshotKimi K2.7 Code | Input / Output ≈ $0.0022 / $0.0092cache ×0.1 | Savings−45% | Cacheread 0.0414 |
AnthropicClaude Fable 5 | Input / Output $2.6667 / $13.3334cache ×0.1 | Savings−74% | Cacheread 0.26667 |
MiniMaxMiniMax M3 | Input / Output ≈ $0.023 / $0.0919cache ×0.1 | Savings−95% | Cacheread 0.00148 |
AnthropicClaude Opus 4.8 | Input / Output $1.3334 / $6.6667cache ×0.1 | Savings−74% | Cacheread 0.13334 |
XiaomiMiMo V2.5 | Input / Output $0.0594 / $0.1188cache ×0.1 | Savings−58% | Cacheread 0.00594 |
XiaomiMiMo V2.5 Pro | Input / Output $0.1846 / $0.3692cache ×0.1 | Savings−58% | Cacheread 0.01846 |
AnthropicClaude Opus 4.7 | Input / Output $0.6286 / $3.1429cache ×0.1 | Savings−88% | Cacheread 0.06286 |
GoogleGemma 4 | Input / Output $0.1286 / $0.4858cache ×0.56 | Cacheread 0.071444 | |
MiniMaxMiniMax M2.7 | Input / Output ≈ $0.022 / $0.0877cache ×0.1 | Savings−96% | Cacheread 0.00125 |
ByteDanceDoubao Seed 2.0 Lite (ByteDance) | Input / Output $0.3768 / $3.0143cache ×1 | Cacheread 0.3768 | |
ByteDanceDoubao Seed 2.0 Mini (ByteDance) | Input / Output $0.1508 / $0.6029cache ×1 | Cacheread 0.1508 | |
GoogleGemini 3.1 Pro | Input / Output $0.2515 / $1.5086cache ×0.1 | Savings−88% | Cacheread 0.02515 |
AnthropicClaude Sonnet 4.6 | Input / Output $0.8572 / $4.2858cache ×0.1 | Savings−72% | Cacheread 0.08572 |
AnthropicClaude Opus 4.6 | Input / Output $0.6286 / $3.1429cache ×0.1 | Savings−88% | Cacheread 0.06286 |
AnthropicClaude Haiku 4.5 | Input / Output $0.2858 / $1.4286cache ×0.1 | Savings−72% | Cacheread 0.02858 |
Decisions model: call it through POST /v1/decisions, not chat/completions. | Input / Output $0.056 / $0.00 | none | |
Decisions model: instead of text it returns typed answers — a yes/no probability (noul), a pick from your options (choice), a rating on your scale (score) — each with confidence, for routing, classification and moderation. Call it through POST /v1/decisions (state + named questions), not chat/completions. Only input is billed; output is free. Context 64K per request (32K per question). Experimental: images and box questions with the TypeSafe-Danger-Zone-Images: true header; long context with TypeSafe-Danger-Zone-Long-Context: true. | Input / Output $0.056 / $0.00 | none | |
OpenAI-compatible API. Text — price $/1M tokens (input / output) for the default variant. “+N” — alternative providers. Media — price per image / second / request; cache and context don't apply (“—”). “In API” — the exact value for the model. “Savings” — how far our price sits below the model maker’s official price: we compare a basket of 3 input tokens to 1 output token against the official list price converted at the current USD rate; a dash means we have no official reference for that model.
priceRub field of the GET /api/media/jobs/{jobId} response and in the dashboard spending history.Create a task via POST /api/media/generate with the same key Bearer sk-pv-…. The response includes a jobId. Video is generated asynchronously (seconds to minutes) — poll GET /api/media/jobs/{jobId} until status: "success", then fetch resultUrls.
# 1. create a task
curl https://getvibeapi.com/api/media/generate \
-H "Authorization: Bearer $GETVIBE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"MODEL_ID","prompt":"a cat on a skateboard"}'
# → {"jobId":"...","status":"processing"}
# 2. poll the result (video takes seconds to minutes)
curl https://getvibeapi.com/api/media/jobs/JOB_ID \
-H "Authorization: Bearer $GETVIBE_API_KEY"
# → {"status":"success","resultUrls":["https://..."]}