cd /news/large-language-models/deepseek-v4-pro-at-207-tok-s-with-th… · home topics large-language-models article
[ARTICLE · art-99213] src=runinfra.ai ↗ pub= topic=large-language-models verified=true sentiment=· neutral

DeepSeek V4 Pro at 207 tok/s with the full 1M context, no quantization

RunInfra lists DeepSeek V4 Pro as deepseek-ai/DeepSeek-V4-Pro-0813, an LLM with a 1,048,576-token context window and a throughput of 207 tokens per second with no quantization. The API, priced at $0.60 per 1M input tokens and $1.90 per 1M output tokens, offers OpenAI-compatible chat completions.

read1 min views1 publishedAug 17, 2026
DeepSeek V4 Pro at 207 tok/s with the full 1M context, no quantization
Image: source

deepseek-ai/DeepSeek-V4-Pro-0813 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.

USD, pay per token

Confirm how your client reaches this model.

Check the limits your workload must fit.

See which request modes the API supports.

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

Verify the company and operating credentials behind this API.

© 2026 RunInfra. All rights reserved.

── more in #large-language-models 4 stories · sorted by recency
thewatershed.markpesce.com · · #large-language-models
AI Comes Home
── more on @runinfra 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/deepseek-v4-pro-at-2…] indexed:0 read:1min 2026-08-17 ·