DeepSeek

Hangzhou, ChinaFounded 2023
5 models

DeepSeek develops cutting-edge open-weight reasoning models including DeepSeek V3 and DeepSeek R1, rivaling frontier closed models on math, code, and reasoning benchmarks.

5 models from DeepSeek on Railwail

Access every DeepSeek model through Railwail's OpenAI-compatible API.

5 models

  • DeepSeek V4 Pro

    Text & ChatDeepSeek
    New

    DeepSeek's April 2026 flagship. 1.6T MoE / 49B active params, 1M context, rivals top closed-source models on STEM and coding at a fraction of the price.

    $1.58 / 1M input
    deepseekopen-weightsmoe
  • DeepSeek V4 Flash

    Text & ChatDeepSeek
    New

    Efficiency-optimized variant of DeepSeek V4. 284B MoE / 13B active, 1M context, ultra-low pricing for high-throughput workloads.

    $0.36 / 1M input
    deepseekopen-weightsmoe
  • DeepSeek V4.1 Flash

    Text & ChatDeepSeek
    New

    DeepSeek's current Flash model (API name deepseek-flash, model version DeepSeek-V4.1-Flash): 1M-token context, up to 384K output tokens, JSON output, tool calls and vision input.

    $0.36 / 1M input
    deepseekopen-weightscost-efficient
  • DeepSeek-VL 7B

    MultimodalDeepSeek

    DeepSeek-VL 7B chat model. Vision-language model with hybrid vision encoder and strong real-world visual question answering performance.

    $0.0086 / run
    replicatemultimodalvision-understanding
  • Janus Pro 7B

    ImageDeepSeek

    DeepSeek's unified multimodal model. Decouples vision encoding for both understanding and generation tasks.

    $0.017 / run
    deepseekjanusopen-weights

Currently unavailable (4)

Listed for reference. These models have no verified price or are no longer served, so the API does not run them.

Frequently asked questions

How is DeepSeek pricing handled on Railwail?
Railwail uses transparent per-call or per-token credit pricing for all DeepSeek models. You pay only for what you use — no monthly minimums, no upfront commitments. Pricing for every individual DeepSeek model is shown on its detail page.
Are there rate limits when using DeepSeek via Railwail?
Default rate limits depend on your account tier and the underlying DeepSeek capacity. Free-tier accounts get sensible defaults for development; paid accounts can request higher limits. Contact support if you need dedicated throughput or burst capacity.
Which regions does DeepSeek support through Railwail?
DeepSeek models are served from Railwail's globally distributed edge infrastructure. EU, US, and Asia-Pacific traffic is automatically routed to the nearest available provider region. GDPR-compliant EU-only routing is available on request.
Is there a sandbox or free tier to test DeepSeek models?
Accounts created with Google get 10 trial credits ($0.10), usable 24 hours after sign-up for runs of up to 2 credits each, so you can test the cheaper DeepSeek models. Email and GitHub sign-ups start without trial credits. No credit card is required to sign up.
Categories DeepSeek works in

Start building with DeepSeek today

Free credits on sign-up. No credit card required. Access DeepSeek and 27+ other providers through a single API.