Skip to main content
All guides
DeepSeek basics

DeepSeek API models overview: V3, R1, Coder and live availability

Model IDs, context windows, pricing tiers, endpoint URLs and supported capabilities for every DeepSeek API model — plus how to monitor availability in real time.

DeepSeek provides two primary production API models: deepseek-chat (powered by DeepSeek-V3 for general conversation and coding) and deepseek-reasoner (powered by DeepSeek-R1 for complex reasoning). Both feature a 64K token context window and use https://api.deepseek.com as their OpenAI-compatible endpoint.

Last updated September 3, 2026

The model line-up at a glance

  • deepseek-chat — the DeepSeek-V3 general-purpose chat model. 64K context, fastest and cheapest, supports JSON mode and tool calling.
  • deepseek-reasoner — the DeepSeek-R1 reasoning model. 64K context, emits a separate reasoning_content chain-of-thought, higher output pricing, best for multi-step logic.
  • DeepSeek-Coder — the code-specialized line. Its capabilities are largely folded into V3 on the hosted API; the standalone weights remain available on Hugging Face for self-hosting.
  • Older dated snapshots are retired on roughly 30 days' notice, so pin a model family rather than a snapshot ID in production.

Endpoints and how to list models

Everything lives under https://api.deepseek.com. The chat endpoint is /v1/chat/completions and the model catalogue is /models (also reachable as /v1/models). Both require an Authorization: Bearer <key> header. Calling the models endpoint is the cheapest way to confirm your key works and to see which IDs are currently served — it costs nothing and returns instantly, which makes it the ideal health probe for a monitoring script.

Context windows and output limits

Hosted DeepSeek models accept a 64K-token context window. Output is capped well below that — plan for around 8K tokens of completion on deepseek-chat and note that on deepseek-reasoner the internal chain-of-thought consumes part of that budget before the visible answer starts. If a reasoner reply gets truncated mid-sentence, the usual cause is a max_tokens value that was sized for the answer alone and not for the reasoning that precedes it.

Pricing tiers by model

deepseek-chat bills roughly $0.14 per million input tokens on a cache hit, $0.55 per million on a miss, and $0.28 per million output tokens. deepseek-reasoner uses the same input structure but a higher output rate, because the hidden reasoning tokens are billed as output. That single fact explains most surprise invoices: a reasoner request that returns 200 visible tokens may have billed 2,000. Estimate reasoner cost at several times the equivalent chat call, and reserve it for tasks where the accuracy gain pays for itself.

Supported capabilities

  • OpenAI-compatible chat completions, including streaming via server-sent events.
  • JSON mode through response_format — reliable on deepseek-chat, and best avoided on the reasoner, where the chain-of-thought competes with strict formatting.
  • Tool / function calling on deepseek-chat with the standard OpenAI tools schema.
  • Prefix caching on both models, applied automatically to the leading matched tokens of a prompt.
  • Open weights for V3 and R1 under permissive licenses, so the same model families can be self-hosted through vLLM, Ollama or Hugging Face Transformers.

Choosing between deepseek-chat and deepseek-reasoner

Default to deepseek-chat. It handles classification, extraction, summarization, refactoring, and the overwhelming majority of agent steps at a fraction of the cost and latency. Escalate to deepseek-reasoner when a task involves multi-step arithmetic, constraint satisfaction, subtle debugging, or planning where a wrong intermediate step invalidates the answer. A useful pattern is a two-tier router: run deepseek-chat first, and retry with deepseek-reasoner only when a validator rejects the output.

Monitoring real-time model availability

Model availability and API availability are not the same thing. The edge can answer while a specific model is capacity-constrained and returns 429 or 503 for a stretch. Probe both: a cheap call to /models proves the platform is up, and a one-token completion against each model ID you depend on proves that model is actually serving. Run both on a short interval, alert on consecutive failures rather than single blips, and record latency percentiles so you can tell degradation from a hard outage. The live dashboard on this site performs the reachability half of that check from your own browser, which also catches regional routing problems that a server-side monitor in another country would miss.

Handling deprecations and version pinning

DeepSeek retires dated snapshots with about 30 days of notice. Reference the stable aliases deepseek-chat and deepseek-reasoner in application code, and keep the exact snapshot IDs only in evaluation runs where reproducibility matters. Log the model field returned in each API response so that when behaviour shifts you can prove whether the served model changed. Re-run your evaluation suite whenever the alias points somewhere new; prompt tweaks that were tuned against an older snapshot occasionally need adjusting.

Self-hosting the same models

Because V3 and R1 weights are open, the hosted API is not the only route. Distilled R1 variants run on a single consumer GPU, while full V3 needs serious multi-GPU hardware. Self-hosting removes rate limits and provider outages from the equation, and adds capacity planning, GPU cost and ops burden instead. Most teams use the hosted API as the primary path and keep a small self-hosted or third-party OpenAI-compatible fallback for continuity during incidents.

FAQ

What are the primary DeepSeek API model names?
The active model IDs are deepseek-chat (DeepSeek-V3) for chat and coding, and deepseek-reasoner (DeepSeek-R1) for multi-step reasoning with chain-of-thought outputs.
What is the context window for DeepSeek API models?
Both deepseek-chat and deepseek-reasoner support a 64K token context window with up to 8K maximum output tokens per completion request.
What is the official DeepSeek API base URL?
The official OpenAI-compatible base URL for all DeepSeek models is https://api.deepseek.com (or https://api.deepseek.com/v1).
What models does the DeepSeek API offer?
deepseek-chat (DeepSeek-V3) and deepseek-reasoner (DeepSeek-R1) on the hosted API, both with a 64K context window. DeepSeek-Coder weights remain available for self-hosting.
How do I list available DeepSeek models?
Send an authenticated GET request to https://api.deepseek.com/models with an Authorization: Bearer header. It returns the currently served model IDs and costs nothing.
What is the DeepSeek context window?
64K tokens for the hosted models, shared between the prompt and the completion. On deepseek-reasoner the hidden reasoning tokens also draw from the output budget.
Does DeepSeek support JSON mode and tool calling?
Yes on deepseek-chat, using the same response_format and tools schema as the OpenAI API. Strict JSON output is less reliable on the reasoner.
How can I monitor DeepSeek uptime per model?
Poll /models for platform health and send a one-token completion to each model ID you depend on. Alert on consecutive failures and track latency percentiles to distinguish degradation from an outage.

Related on this site

Related services in the .health network

Keep reading

Also in the .health network