deepseek
Call the DeepSeek API (deepseek-flash, deepseek-v4-pro, deepseek-v4-flash, and deepseek-v4-flash-vision-exp) through RunAPI using OpenAI-compatible Chat Completions and Responses. Use deepseek-flash for the current V4.1 Flash 1017 model; the v4 names remain compatibility aliases.
DeepSeek on RunAPI
The current official revision is DeepSeek-V4.1-Flash-1017, updated on
2026-10-17. V4.1 Flash first launched on 2026-09-10. Use deepseek-flash;
deepseek-v4-flash and deepseek-v4-flash-vision-exp remain compatibility
names. The official upgrade does not establish the revision of every RunAPI
service option. Third-party versions remain unconfirmed unless separately
verified. See the current model reference.
Use OpenAI-compatible endpoints at https://runapi.ai/v1 as the primary protocol.
Primary protocol recipe
Authenticate
Set OPENAI_API_KEY to a RunAPI API key and OPENAI_BASE_URL to https://runapi.ai/v1.
Send request
from openai import OpenAI
client = OpenAI(api_key="YOUR_RUNAPI_TOKEN", base_url="https://runapi.ai/v1")
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Explain this decision."}],
)
print(response.choices[0].message.content)
print(response.usage)
For long output, set stream=True and
stream_options={"include_usage": True}; consume through [DONE].
deepseek-v4-flash additionally supports one custom function on Responses;
keep automatic tool selection and one serial call/result lifecycle.
For image input, use deepseek-flash only where the current model contract
permits it. DeepSeek documents image input, but RunAPI has not tested vision
on every service option. The retired deepseek-v4-flash-vision-exp name is
a historical compatibility alias, not a separate recommended vision model.
Verify result
For Chat, require final assistant content, finish_reason, and usage. For
Responses, require final output, one usage-bearing response.completed, and
[DONE] when streaming.
Stop boundaries
Correct a rejected shape once using the structured error. Retry transport once only before any response or Usage and when replay is safe. Record a terminal error and stop without changing model or protocol. Add tools, reasoning, storage, cache controls, documents, or multimodal input only when the current RunAPI contract verifies the exact model/protocol shape.
Compatibility protocols
Load compatibility protocols only when an existing client requires Anthropic Messages or Gemini contents.
Supported models
| Model ID | Use when |
|---|---|
deepseek-flash | Current V4.1 Flash 1017 official revision for fast text and reasoning |
deepseek-v4-flash-vision-exp | Historical compatibility alias, not a separate vision model |
deepseek-v4-pro | Higher-quality verified text workloads |
deepseek-v4-flash | Compatibility alias for Flash |
References
- Downloads
- Security audit
- Pass
- Last updated
- 3w ago
- Current version
- v0.1.7
- License
- MIT-0
