Ψ
PHANTOM

Model Directory & Pricing

Transparent wholesale pricing per million tokens with automated prompt caching discounts. All open-weight models execute inside hardware-attested Intel TDX enclaves.

Model IDRouting TierContextInput / 1MCached InputOutput / 1M
phala/deepseek-v3.2Hardware TEE131k$0.27$0.030$1.10
phala/deepseek-r1Hardware TEE131k$0.55$0.060$2.19
phala/gpt-oss-120bHardware TEE131k$0.10$0.020$0.49
phala/qwen-2.5-coder-32bHardware TEE131k$0.12$0.020$0.35
phala/kimi-k2.6Hardware TEE262k$1.09$0.150$4.60
phala/glm-5.3Hardware TEE1000k$1.40$0.140$4.40
phala/llama-3.3-70b-instructHardware TEE131k$0.18$0.030$0.60
black-forest-labs/flux-1-schnellHardware TEE0k$5000.00$5000.000$0.00
black-forest-labs/flux-1-devHardware TEE0k$25000.00$25000.000$0.00
openai/dall-e-3Confidential Gateway0k$40000.00$40000.000$0.00
stabilityai/stable-diffusion-xl-base-1.0Confidential Gateway0k$8000.00$8000.000$0.00
openai/text-embedding-3-smallConfidential Gateway8k$0.02$0.020$0.00
openai/text-embedding-3-largeConfidential Gateway8k$0.13$0.130$0.00
voyageai/voyage-3Confidential Gateway32k$0.12$0.120$0.00
anthropic/claude-3-7-sonnetConfidential Gateway200k$3.00$0.300$15.00
anthropic/claude-3-5-sonnetConfidential Gateway200k$3.00$0.300$15.00
openai/gpt-4.5Confidential Gateway128k$5.00$1.250$20.00
openai/o3-miniConfidential Gateway200k$1.10$0.275$4.40
openai/o1Confidential Gateway200k$15.00$3.750$60.00
openai/gpt-4oConfidential Gateway128k$2.50$0.625$10.00
google/gemini-2.0-flashConfidential Gateway1049k$0.10$0.025$0.40
google/gemini-2.0-proConfidential Gateway2097k$1.25$0.313$5.00

OpenAI SDK Compatibility

Pass any model ID from the table above directly to client.chat.completions.create(model=...).