StatusOperational Live status
LLMAPI discountUp to −25%
Models on LLMAPI1
From$1.98 / 1M blended
RegionsGlobal
Best uptime (24h)99.98%
Verdict
DeepSeek produces open-weight models with frontier-level reasoning and coding performance at some of the lowest API prices in the industry. Through LLMAPI you reach 5 DeepSeek models on the same OpenAI-compatible endpoint as every other provider, so switching between them is a one-string change.
Good fit for
- Text Generation
- Code Generation
- Reasoning & Logic
- Mathematics
- Cheapest per Token
- Best Price-to-Performance
Consider another provider for
- No image generation models in this catalog
- No vision models in this catalog
- No video generation models in this catalog
- No video understanding models in this catalog
Key facts
Where a provider does not document something we say so rather than guess. Everything LLMAPI records about DeepSeek, in one table.
Overview | |
| Provider | DeepSeek |
| Website | deepseek.com |
| Best for | Reasoning and coding at the lowest per-token prices |
| Models on LLMAPI | 1 |
| Popular models | DeepSeek V4 Pro |
Access & routing | |
| API compatibility | OpenAI-compatible — /v1/chat/completions |
| Model ID prefix | deepseek/<model> |
| Regions | Global |
| Fallback | Configurable — on 429 or 5xx the router switches to any other model or provider on your list |
| Billing | One invoice across every provider, with per-key spend limits |
| Volume discount | Eligible |
Performance (median across listed models) | |
| Blended price / 1M | $1.98 |
| Uptime (24h) | 99.98% (median across listed models) |
Modality | |
| Tags | |
Capability | |
| Tags | |
Price & performance | |
| Tags | |
Deployment | |
| Tags | |
Workflow | |
| Tags | |
Trust & safety | |
| Tags | |
Audience | |
| Tags | |
Privacy & data | |
| Inference location | China-based infrastructure |
| Data residency | Not documented by the provider |
| Default retention | Retained under the provider terms |
| Zero-data retention | Not documented by the provider |
| Training on API data | Yes Review the provider terms before sending sensitive data |
| Human review | Not documented by the provider |
Compliance & lifecycle | |
| Certifications | Not documented by the provider |
| Deprecation notice | Not documented by the provider |
| Operational status | Operational Live status |
Prices and context from the OpenRouter public catalogue; uptime and output speed from OpenRouter provider endpoints; quality scores from LiveBench. Refreshed nightly — last updated 2026-09-29. — means no figure is published for that model.
Best DeepSeek models
A quick view of how DeepSeek 's 5 models compare on intelligence, output speed and price — so you can pick the right one for your use case.
Most intelligent
#1DeepSeek V345
#2DeepSeek V3.244
#3DeepSeek R143
#4DeepSeek Coder V239
Intelligence index · 5 models
Fastest
#1DeepSeek R1320 t/s
#2DeepSeek V3306 t/s
#3DeepSeek Coder V2236 t/s
#4DeepSeek V3.2112 t/s
Output tokens / second · 5 models
Lowest price
#1DeepSeek V3.2$2.89
#2DeepSeek R1 Zero$3.19
#3DeepSeek V3$6.77
#4DeepSeek R1$8.53
Blended price per 1M tokens · 5 models
Compared with other hosts
How DeepSeek sits against the rest of the catalog, using the same measurements shown on every provider page.
- Price. Median blended price of $6.77 per 1M tokens — 10% above the $6.13 median across all 50 providers in the catalog.
- Throughput. Median output speed of 236 tokens/s, 32% slower than the 348 tok/s catalog median.
- Catalog depth. 5 models listed, against a catalog average of 5 per provider.
- Integration. Identical to every other provider here — same endpoint, same SDK, same keys, so a switch costs one string change.
Median blended price per 1M tokens
lower is better| DeepSeek | $6.77 | |
| Thinking Machines | $6.75 | |
| Inception | $6.82 | |
| Reka AI | $6.69 | |
| Anthropic | $6.63 | |
| $6.31 |
Median output speed
higher is better| DeepSeek | 236 tok/s | |
| Thinking Machines | 119 tok/s | |
| Inception | 287 tok/s | |
| Reka AI | 249 tok/s | |
| Anthropic | 365 tok/s | |
| 239 tok/s |
Figures are medians across the models listed on each provider page and are refreshed with the catalog.
Models & pricing
Every DeepSeek model reachable with your LLMAPI key. Click a column heading to sort.
| Model | API model name | Uptime 24h | Price / 1M | Context |
|---|---|---|---|---|
| DeepSeek V4 Pro | deepseek-v4-pro | 99.98% | $ 1.98 | 1049 k |
Price is a blended per-1M-token figure; latency is time to first token and throughput is output tokens per second, measured on the LLMAPI edge.
Cost calculator
Pick a model, enter your traffic, and see the monthly bill at LLMAPI rates.
Estimates use the blended per-1M-token price shown in the table above. Word counts differ by language — Cyrillic and CJK text uses 2–3× more tokens per word.
DeepSeek via LLMAPI
Same models, same features, one key. Prefix the model ID with deepseek/ and point your OpenAI client at our base URL.
# Python · OpenAI SDK from openai import OpenAI client = OpenAI( base_url="https://api.llmapi.ai/v1", api_key="LLMAPI_KEY", ) r = client.chat.completions.create( model="deepseek/deepseek-v3-2", messages=[{"role": "user", "content": "Hello"}], )
| Pricing | Eligible for LLMAPI volume discounts; billed on one invoice with every other provider. |
| Features | Full pass-through — tool calling, JSON schema, streaming, vision and reasoning behave exactly as on DeepSeek’s own API. |
| Fallback | Configurable. On 429 or 5xx the router switches to any model or provider on your fallback list. |
| Regions | Global |
| Your data | LLMAPI stores request metadata only — model, token counts, latency and status. No prompt or completion content. |
Capabilities & use cases
Each tag below is its own catalog page listing every provider that shares it.
Text GenerationCode GenerationReasoning & LogicMathematicsCheapest per TokenBest Price-to-PerformanceOpen-Weight ModelsBest for Local DeploymentSelf-Hosted / On-PremiseFine-Tunable ModelsCoding AutocompleteAutonomous Software EngineeringDebugging & Code ReviewData AnalysisMost TransparentBest for DevelopersBest for Startups & Solo Builders
Developer resources
Where to go next.
Join thousands of developers building on one API key
Every provider in the catalog, one key, one invoice.
Questions
How do I call DeepSeek models through LLMAPI?
Point any OpenAI-compatible client at https://api.llmapi.ai/v1 and use the model ID deepseek/deepseek-v3-2. No other change is needed.
Does DeepSeek cost more through LLMAPI?
No. This provider is eligible for LLMAPI volume discounts, so heavy usage lands below list price.
Which regions are used?
Global
What happens if the provider returns an error?
On 429 or 5xx responses the router falls back to any other model or provider on your configured list, so requests keep succeeding.
How many DeepSeek models are available?
5 at the moment, all listed in the models table above and updated as the provider ships new ones.
Related providers
Providers covering similar use cases.