Cerebras
Inference providersThe fastest published speeds in the research: about 3,000 tokens a second on gpt-oss-120b.
Models from this provider 2 models
Our price, per provider, in US dollars and Iraqi dinars (1 USD = 1,380 IQD, rounded up to 10 IQD).
| Models | Context | Input | Output | Note |
|---|---|---|---|---|
| Qwen3.8 27Bqwen/qwen3.8-27b | 128K | $1.485 · 2,050 IQD | $2.235 · 3,090 IQD | Coming soon ~1850 tokens/s, 128K context |
| gpt-oss-120bopenai/gpt-oss-120b | 131K | $0.525 · 730 IQD | $1.125 · 1,560 IQD | Coming soon ~3000 tokens/s, 131K context |
Coming soon to OPTES Coming soon
Get your OPTES API key now. The same key will call this model when it opens.