Crusoe
Explore Crusoe models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Crusoecrusoe
No provider claim
| Provider | Crusoe |
|---|---|
| Provider website | https://www.crusoe.ai/ |
| Models | 15 public models |
| Prepaid routes | 15 |
| BYOK routes | 15 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | No provider-ZDR claim is tracked here. Crusoe's Managed Inference docs and pricing/catalog pages are linked for model and API data-handling review. Policy source |
Measured performance
50 samplesContinuously sampled across Crusoe's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 2148 ms |
|---|---|
| Effective throughput | 61 tok/s n=5 |
| Uptime | 98.00% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| nvidia/nemotron-3-super-120b-a12b | 966 ms | 966 ms | — | 100.00% | — | 4 |
| yutori/n1.5 | 1247 ms | 1247 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-nano-omni-reasoning-30b-a3b | 1337 ms | 1337 ms | — | 100.00% | — | 6 |
| google/gemma-4-31b-it | 1351 ms | 1350 ms | 54 tok/s n=1 | 100.00% | — | 8 |
| openai/gpt-oss-120b | 1459 ms | 1459 ms | 72 tok/s n=1 | 100.00% | — | 2 |
| nvidia/nemotron-3-nano-30b-a3b | 1613 ms | 1613 ms | — | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b-2507 | 1725 ms | 1725 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 2148 ms | 2147 ms | 83 tok/s n=1 | 100.00% | — | 3 |
| meta-llama/llama-3.3-70b-instruct | 2469 ms | 2469 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.1 | 2820 ms | 2820 ms | — | 100.00% | — | 6 |
| deepseek/deepseek-v3-0324 | 3160 ms | 3160 ms | — | 100.00% | — | 5 |
| deepseek/deepseek-v4-flash | 3776 ms | 3776 ms | 61 tok/s n=2 | 100.00% | — | 3 |
| nvidia/nemotron-3.5-lightning-30b-a3b | 3805 ms | 3804 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.6 | 2474 ms | 2474 ms | — | 80.00% | — | 5 |
Crusoe performance history · Full provider & model leaderboard.
Models served by Crusoe.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
deepseek/deepseek-v3-0324DeepSeek V3 0324 |
— | 163,840 | 2 | $0.525/1M | $1.575/1M | prepaid BYOK |
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 |
IQ 113#35 | 1,048,576 | 2 | $0.147/1M | $0.294/1M | prepaid BYOK |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro |
IQ 117#25 | 1,048,576 | 2 | $1.827/1M | $3.654/1M | prepaid BYOK |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#66 | 262,144 | 2 | $0.147/1M | $0.42/1M | prepaid BYOK |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | 2 | $0.2625/1M | $0.7875/1M | prepaid BYOK |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 119#19 | 262,144 | 2 | $0.735/1M | $3.675/1M | prepaid BYOK |
nvidia/nemotron-3-nano-30b-a3bNVIDIA: Nemotron 3 Nano 30B A3B |
— | 262,144 | 2 | $0.0525/1M | $0.21/1M | prepaid BYOK |
nvidia/nemotron-3-nano-omni-reasoning-30b-a3bnvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B |
— | 262,144 | 2 | $0.315/1M | $1.9215/1M | prepaid BYOK |
nvidia/nemotron-3-super-120b-a12bNVIDIA: Nemotron 3 Super |
— | 1,000,000 | 2 | $0.315/1M | $2.52/1M | prepaid BYOK |
nvidia/nemotron-3.5-lightning-30b-a3bnvidia/Nemotron-3.5-Lightning-30B-A3B |
— | 262,144 | 2 | $0.0525/1M | $0.21/1M | prepaid BYOK |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#53 | 131,072 | 2 | $0.0525/1M | $0.2625/1M | prepaid BYOK |
qwen/qwen3-235b-a22b-2507Qwen: Qwen3 235B A22B Instruct 2507 |
— | 262,144 | 2 | $0.231/1M | $0.84/1M | prepaid BYOK |
yutori/n1.5yutori/n1.5 |
— | 128,000 | 2 | $1.575/1M | $5.25/1M | prepaid BYOK |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 114#32 | 204,800 | 2 | $1.26/1M | $4.62/1M | prepaid BYOK |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#16 | 1,048,576 | 2 | $1.47/1M | $4.62/1M | prepaid BYOK |
Questions
Does Crusoe have zero data retention?
TrustedRouter does not currently mark Crusoe as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Crusoe end-to-end encrypted?
TrustedRouter does not currently mark Crusoe as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Crusoe models are available through TrustedRouter?
This page currently lists 15 public Crusoe models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.