- input
- $0.10
- cached
- $0.025
- output
- $0.90
- Context
- 262Ktokens
- Released
- 6mo ago
- Size
- 35Bparameters
Cost/1M tokens
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
 PrimeIntellect | primeintellect/fp8 | 262K | $0.017 | $0.155 | $0.015 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
 Darkbloom | darkbloom/fp4 | 262K | $0.05 | $0.70 | $0.025 | — | 99.81% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
 AkashML | akashml/fp8 | 262K | $0.10 | $0.90 | $0.05 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
 CoreWeave | coreweave/fp8 | 262K | $0.10 | $0.89 | $0.035 | — | 98.76% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
 DeepInfra | deepinfra/fp8 | 262K | $0.10 | $0.95 | $0.10 | — | 98.88% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
 DekaLLM | dekallm | 262K | $0.10 | $1.00 | $0.05 | — | 84.09% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-11 |
 Parasail | parasail/fp8 | 262K | $0.10 | $0.90 | $0.025 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
 Venice | venice/fp8 | 256K | $0.10 | $1.00 | — | — | 99.65% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
 SiliconFlow | siliconflow/fp8 | 262K | $0.24 | $1.80 | $0.15 | — | 99.17% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
 AtlasCloud | atlas-cloud/fp8 | 262K | $0.25 | $1.25 | $0.25 | — | 57.18% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
Provider data:OpenRouter