Ornith 1.5 122B at 302tps

RunInfra is serving Ornith 1.5 122B, a mixture-of-experts reasoning model with about 10B active parameters that accepts text and image input, at $0.20 per 1M input tokens and $0.80 per 1M output tokens. The API offers a 262,144-token context window, OpenAI-compatible chat completions and Anthropic-compatible Messages via POST /v1/messages, with tool calling, JSON mode, streaming and BF16 unquantized precision. Cached input is billed at $0.02 per 1M tokens, and RunInfra states the model runs with zero data retention by default and is never used for training.

Ornith 1.5 122B ornith-ai/ Ornith 1.5 122B is a mixture-of-experts reasoning model with about 10B active parameters. It takes text and image input. RunInfra serves it as ornith-ai/Ornith-1.5-122B at $0.20 per 1M input tokens and $0.80 per 1M output tokens. Its context window is 262,144 tokens. The API provides OpenAI-compatible chat completions and Anthropic-compatible Messages, POST /v1/messages. Pricing USD, pay per token - per 1M input tokens - $0.20 - per 1M cached input tokens - $0.02 - per 1M output tokens - $0.80 Measured performance Access Confirm how your client reaches this model. - Provider - Ornith - API compatibility - OpenAI-compatible chat completions - Anthropic compatibility - Anthropic-compatible Messages, POST /v1/messages - Accepted input - Text and images - Availability - Available - Data retention - Zero data retention by default. Never used for training. https://runinfra.ai/docs/security/data-retention Capacity Check the limits your workload must fit. - Context window - 262,144 tokens - Maximum request size - 3.5 MB per request - Maximum generated output - 262,144 tokens Capabilities See which request modes the API supports. - Tool calling - Supported - JSON mode - Supported - Streaming - Supported - Precision - BF16, unquantized View full spec - Gateway compatibility - OpenAI- and Anthropic-compatible APIs for compatible clients, tools, and gateways - Prefix caching - Automatic prefix caching runs on every replica, and requests from the same session or conversation are routed back to the replica that holds their cached prefix. A stable session hint or prompt cache key provides explicit grouping; otherwise RunInfra derives it from the start of the conversation or, failing that, the workspace. Hits remain best effort until eviction or a serve restart, never guaranteed. Cached input is billed at the cached input rate. Responses report cached token counts. - Cache retention - Prefix cache is held on the serving GPU and evicted under memory pressure. Retention is best effort. - Upstream model - View model https://huggingface.co/ornith-ai/Ornith-1.5-122B