EnglishEN
Try OPTES
Model catalog

Crusoe

Inference providers

Managed inference with low cached-input prices: DeepSeek, Kimi, GLM, gpt-oss and Nemotron.

Models from this provider 9 models

Our price, per provider, in US dollars and Iraqi dinars (1 USD = 1,380 IQD, rounded up to 10 IQD).

ModelsContextInputOutputNote
GLM-5.3z-ai/glm-5.3—$2.10 · 2,900 IQD$6.60 · 9,110 IQDComing soon
GLM-5.3 Flashz-ai/glm-5.3-flash—$0.225 · 320 IQD$0.75 · 1,040 IQDComing soon
Kimi K2.6moonshotai/kimi-k2.6262K$1.05 · 1,450 IQD$5.25 · 7,250 IQDComing soon
DeepSeek V4 Prodeepseek/deepseek-v4-pro—$2.61 · 3,610 IQD$5.22 · 7,210 IQDComing soon
DeepSeek V4 Flashdeepseek/deepseek-v4-flash—$0.21 · 290 IQD$0.42 · 580 IQDComing soon
Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning—$0.075 · 110 IQD$0.30 · 420 IQDComing soon
Nemotron 3 Ultranvidia/nemotron-3-ultra—$1.50 · 2,070 IQD$4.80 · 6,630 IQDComing soon
Gemma 4 31Bgoogle/gemma-4-31b—$0.21 · 290 IQD$0.60 · 830 IQDComing soon
gpt-oss-120bopenai/gpt-oss-120b131K$0.075 · 110 IQD$0.30 · 420 IQDComing soon

Coming soon to OPTES Coming soon

Get your OPTES API key now. The same key will call this model when it opens.

The OPTES API, sign-up and keys open at launch on Friday, 2 October 2026. Third-party models are coming soon after that.