DeepSeek V4 Pro

Backed by

Combinator

Ask AI about RunInfra

RunInfra is a sub-product of RightNow Research Lab.

DeepSeek V4 Pro

deepseek-ai/DeepSeek-V4-Pro-0813

Get API key View docs

DeepSeek V4 Pro is an LLM listed in RunInfra Model APIs. RunInfra serves it as deepseek-ai/DeepSeek-V4-Pro-0813 at $0.60 per 1M input tokens and $1.90 per 1M output tokens. Its context window is 1,048,576 tokens. The API provides OpenAI-compatible chat completions.

Pricing

USD, pay per token

per 1M input tokens: $0.60
per 1M output tokens: $1.90

Measured performance

Output speed

207output tokens per second, model only

Time to first token

520milliseconds to first token

Access

Confirm how your client reaches this model.

Provider: DeepSeek
API compatibility: OpenAI-compatible chat completions
Accepted input: Text only
Availability: Available
Data retention: Your prompts are never stored and never used for training. Billing keeps token counts, cost, timing, and a request id. An Idempotency-Key you send holds that response body for 24 hours.

Capacity

Check the limits your workload must fit.

Context window: 1,048,576 tokens
Maximum request size: 3.5 MB per request
Maximum generated output: 32,768 tokens
Streaming time to first token limit: 60 seconds
Maximum request duration: 240 seconds

Capabilities

See which request modes the API supports.

Tool calling: Supported
JSON mode: Supported
Streaming: Supported

View Full Spec

Gateway compatibility: OpenAI-compatible chat completions for compatible clients and gateways
OpenRouter Provider Monitor: Provider metadata published as ready for discovery. Not proof of a live OpenRouter listing or callability.
Prefix caching: Automatic prefix caching runs on every replica. Requests are spread across replicas without session affinity, so a repeated prompt is not guaranteed to reach the cache holding it. Cached input is billed at the standard input rate. Responses do not report cached token counts.
Upstream model: View 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.

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

RunInfraby RightNow

Backed by

Combinator

Ask AI about RunInfra

RunInfraby RightNow

Backed by

Combinator

Ask AI about RunInfra

RunInfra is a sub-product of RightNow Research Lab.

DeepSeek V4 Pro

deepseek-ai/DeepSeek-V4-Pro-0813

Get API key View docs

Pricing

USD, pay per token

per 1M input tokens: $0.60
per 1M output tokens: $1.90

Measured performance

Output speed

207output tokens per second, model only

Time to first token

520milliseconds to first token

Access

Confirm how your client reaches this model.

Provider: DeepSeek
API compatibility: OpenAI-compatible chat completions
Accepted input: Text only
Availability: Available
Data retention: Your prompts are never stored and never used for training. Billing keeps token counts, cost, timing, and a request id. An Idempotency-Key you send holds that response body for 24 hours.

Capacity

Check the limits your workload must fit.

Context window: 1,048,576 tokens
Maximum request size: 3.5 MB per request
Maximum generated output: 32,768 tokens
Streaming time to first token limit: 60 seconds
Maximum request duration: 240 seconds

Capabilities

See which request modes the API supports.

Tool calling: Supported
JSON mode: Supported
Streaming: Supported

View Full Spec

Gateway compatibility: OpenAI-compatible chat completions for compatible clients and gateways
OpenRouter Provider Monitor: Provider metadata published as ready for discovery. Not proof of a live OpenRouter listing or callability.
Prefix caching: Automatic prefix caching runs on every replica. Requests are spread across replicas without session affinity, so a repeated prompt is not guaranteed to reach the cache holding it. Cached input is billed at the standard input rate. Responses do not report cached token counts.
Upstream model: View 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.

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

RunInfraby RightNow

Backed by

Combinator

Ask AI about RunInfra