What does Ornith 1.5 35B cost on RunInfra?

Input costs $0.10 per 1M input tokens. Cached input costs $0.01 per 1M cached input tokens. Output costs $0.40 per 1M output tokens.

What are the limits for Ornith 1.5 35B?

Context window: 262,144 tokens. Maximum request size: 3.5 MB per request. Maximum generated output: 262,144 tokens.

Ornith 1.5 35B

ornith-ai/Ornith-1.5-35B-A3B

Get API key Chat Completions API reference

Ornith 1.5 35B is an LLM listed in RunInfra Model APIs. RunInfra serves it as ornith-ai/Ornith-1.5-35B-A3B at $0.10 per 1M input tokens and $0.40 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: $0.10
per 1M cached input tokens: $0.01
per 1M output tokens: $0.40

Measured performance

Output speed

216output tokens per second, model only

Time to first token

167milliseconds to first reasoning token

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: Your prompts are never stored and never used for training.

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: FP8, weights, activations and KV cache, with the vision, linear-attention and MTP layers left 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. 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

Code examples

Set RUNINFRA_GATEWAY_KEY to your workspace API key before using an example.

Trust and provenance

Verify the company and operating credentials behind this API.

RunInfra is a sub-product of RightNow Research Lab.

SOC 2 Type IIAudited access, logging, and incident response.
Y CombinatorBacked by Y Combinator.
NVIDIA InceptionMember of NVIDIA Inception.

View model

Ask AI about RunInfra