DeepSeek
DeepSeek V3
model
deepseek-chatBudgetStableStreamingToolsLong contextChina
Context
131K
Input / 1M tokens
$0.2800
Output / 1M tokens
$0.4200
Weighted tokens formula
1× provider × 1× tier
About this model
DeepSeek V3
DeepSeek's direct DeepSeek-V3 endpoint. Same weights as our `deepseek-v3` slug but a different route (DeepSeek's own infrastructure). Use this slug when you want the deterministic direct route at standard published pricing.
Released
2024-12
Training cutoff
2024-07
Parameters
MoE 671B (37B active)
Best for
Use cases
- ✓Customers pinning to DeepSeek's direct route
- ✓Same use cases as DeepSeek V3
Strengths
What it does well
- ●Direct provider route
- ●Standard DeepSeek pricing
- ●Same weights as deepseek-v3
Limitations
Know the trade-offs
- !More expensive than the deepseek-v3 alternative route
- !Same model, double the cost
Code example
Chat completion with DeepSeek V3
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="deepseek-chat",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Weighted tokens
weighted_tokens = raw_tokens × 1 (provider) × 1 (tier)
Pro plan: 20M weighted tokens/month. Combined multiplier 1×: 20,000,000 raw tokens available.
Alternatives
Similar models in our catalog
Workloads that fit DeepSeek V3 often fit these too. Compare benchmarks and pricing before locking in a default.