TO
Token Harbor
Aggregator
AI model gateway: one OpenAI- and Anthropic-compatible API across frontier chat models from Anthropic, OpenAI, Google, xAI, Moonshot, Alibaba, Z.ai, DeepSeek, Xiaomi and Muse. Transparent per-token pricing (vendor price + per-model markup, 0% default), semantic/exact response caching, th-orchestra agentic model routing, no silent model swaps. Free monthly allowance on selected models; optional Agent/Office/Frontier passes add included usage and 5-15% pay-as-you-go discounts.
Features
OpenAI Compatible
Streaming
Batching
Fine-tuning
Embeddings
Vision
Audio
Function Calling
JSON Mode
Compliance
SOC 2
HIPAA
GDPR
Pricing Model
per token Free tier: Standing free monthly allowance on selected models (currently DeepSeek V4 Flash, DeepSeek V4.1 Flash, MiMo V2.5).
Details
Models 18
API Base
https://tokenharbor.ai/v1 LLM InferenceMulti-Modal
Model Catalog (18)
| Model | Type | Input $/1M | Output $/1M | Context | Speed | Status |
|---|---|---|---|---|---|---|
| Claude Fable 5.1 Anthropic | llm | $10.00 | $50.00 | 1M | — | |
| Claude Opus 5 Anthropic | llm | $5.00 | $25.00 | 1M | — | |
| DeepSeek V4.1 Flash DeepSeek | llm | $0.300 | $1.20 | 1M | — | |
| GLM 5.3 Z.ai | llm | $1.40 | $4.40 | 200k | — | |
| GLM 5.3 Flash Z.ai | llm | $0.150 | $0.500 | 1M | — | |
| GPT-5.6 Luna OpenAI | llm | $0.200 | $1.20 | — | — | |
| GPT-5.6 Sol OpenAI | llm | $4.00 | $20.00 | — | — | |
| GPT-5.6 Terra OpenAI | llm | $2.00 | $12.00 | — | — | |
| GPT-6 Astra OpenAI | llm | $10.00 | $50.00 | — | — | |
| Gemini 3.8 Flash Google | llm | $0.750 | $3.75 | 1M | — | |
| Grok 4.6 xAI | llm | $2.00 | $6.00 | 500k | — | |
| Kimi K3 Moonshot AI | llm | $3.00 | $15.00 | 1.0M | — | |
| MiMo V2.5 Xiaomi | llm | $0.140 | $0.280 | 1.0M | — | |
| MiMo V2.5 Pro Xiaomi | llm | $0.435 | $0.870 | 1.0M | — | |
| Muse Spark 1.3 Muse | llm | $1.25 | $4.25 | — | — | |
| Qwen3.8 27B Alibaba | llm | $0.350 | $2.10 | 992k | — | |
| Qwen3.8 Flash Alibaba | llm | $0.150 | $0.470 | — | — | |
| Qwen3.8 Max Alibaba | llm | $2.00 | $6.00 | — | — |