What is RunInfra Model APIs?

RunInfra Model APIs is a hosted model library with published availability, pricing, limits, and capabilities. The library currently lists 4 models.

How do I call RunInfra Model APIs?

Model APIs is RunInfra's hosted model API product at https://api.runinfra.ai/v1. Each model publishes its operation and compatibility. Chat models expose OpenAI-compatible chat completions at POST /v1/chat/completions and Anthropic-compatible Messages at POST /v1/messages. Chat model requests use workspace API keys and support streaming. JSON mode is supported per chat model, and a model that requires a specific reasoning_effort to deliver it publishes that value with its capabilities. Pricing is published per model in USD with only the billed dimensions shown.

Which models are currently served by RunInfra Model APIs?

Currently available models: GLM 5.3 Flash, Nemotron 3.5 Lightning 30B, Qwen3.8 27B, Ornith 1.5 35B.

Model Library

Built for agents that replay context. Agent traffic resends the whole conversation on every tool call. Here the repeated part hits cache and bills at the cached input rate.

4 models

Capabilities

FiltersAll models

Capabilities

GLM 5.3 Flash

glm-5-3-flashTrending

Model capabilities: Tool calling / JSON mode / Streaming / Image input

$0.10

per 1M input tokens

$0.01

per 1M cached input tokens

$0.40

per 1M output tokens

99.6%

cache hit, last 24 hours

254.1

output tok/s, model only

Effective input $0.011 per 1M at that hit rate Effective input rate $0.011 per 1M tokens, from the measured cache share on billed agent traffic in the last 24 hours.

Nemotron 3.5 Lightning 30B

nemotron-3-5-lightning-30b

Model capabilities: Tool calling / JSON mode / Streaming

$0.05

per 1M input tokens

$0.01

per 1M cached input tokens

$0.15

per 1M output tokens

95.3%

cache hit, last 24 hours

540.9

output tok/s, model only

Effective input $0.012 per 1M at that hit rate Effective input rate $0.012 per 1M tokens, from the measured cache share on billed agent traffic in the last 24 hours.

Qwen3.8 27B

qwen3-8-27b

Model capabilities: Tool calling / JSON mode / Streaming / Image input

$0.10

per 1M input tokens

$0.01

per 1M cached input tokens

$0.40

per 1M output tokens

96.7%

cache hit, last 24 hours

140

output tok/s, end to end

Effective input $0.013 per 1M at that hit rate Effective input rate $0.013 per 1M tokens, from the measured cache share on billed agent traffic in the last 24 hours.

Ornith 1.5 35B

ornith-1-5-35b

Model capabilities: Tool calling / JSON mode / Streaming / Image input

$0.10

per 1M input tokens

$0.01

per 1M cached input tokens

$0.40

per 1M output tokens

cache hit, not yet published

216

output tok/s, model only

Model Library

Built for agents that replay context. Agent traffic resends the whole conversation on every tool call. Here the repeated part hits cache and bills at the cached input rate.

4 models

Capabilities

FiltersAll models

Capabilities

GLM 5.3 Flash

glm-5-3-flashTrending

Model capabilities: Tool calling / JSON mode / Streaming / Image input

$0.10

per 1M input tokens

$0.01

per 1M cached input tokens

$0.40

per 1M output tokens

99.6%

cache hit, last 24 hours

254.1

output tok/s, model only

Effective input $0.011 per 1M at that hit rate Effective input rate $0.011 per 1M tokens, from the measured cache share on billed agent traffic in the last 24 hours.

Nemotron 3.5 Lightning 30B

nemotron-3-5-lightning-30b

Model capabilities: Tool calling / JSON mode / Streaming

$0.05

per 1M input tokens

$0.01

per 1M cached input tokens

$0.15

per 1M output tokens

95.3%

cache hit, last 24 hours

540.9

output tok/s, model only

Effective input $0.012 per 1M at that hit rate Effective input rate $0.012 per 1M tokens, from the measured cache share on billed agent traffic in the last 24 hours.

Qwen3.8 27B

qwen3-8-27b

Model capabilities: Tool calling / JSON mode / Streaming / Image input

$0.10

per 1M input tokens

$0.01

per 1M cached input tokens

$0.40

per 1M output tokens

96.7%

cache hit, last 24 hours

140

output tok/s, end to end

Effective input $0.013 per 1M at that hit rate Effective input rate $0.013 per 1M tokens, from the measured cache share on billed agent traffic in the last 24 hours.

Ornith 1.5 35B

ornith-1-5-35b

Model capabilities: Tool calling / JSON mode / Streaming / Image input

$0.10

per 1M input tokens

$0.01

per 1M cached input tokens

$0.40

per 1M output tokens

cache hit, not yet published

216

output tok/s, model only