Benchmarks

DeepSeek: DeepSeek V3

deepseek/deepseek-chat

DeepSeek V3 is the open reasoning standout, ranking #3 on DROP and #193 of 262 overall. It's served by 2 independent hosts from $0.32/$0.89 per million input/output tokens — about the going rate for its score class.

Prompt $/1M
$0.320
Completion $/1M
$0.890
Context
163,840 tok
Best provider
35 tok/s · StreamLake

Specs

Model id
deepseek/deepseek-chat
Display name
DeepSeek: DeepSeek V3
Modality
text->text
Tokenizer
DeepSeek
Instruct type
—
Context length
163,840
Max completion
16,384
Prompt $/1M
$0.320
Completion $/1M
$0.890
Free tier
no

Capabilities

  • Function callingno
  • JSON modeno
  • System promptno
  • Visionno
  • Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Providertok/s
StreamLakefastest35
DeepInfra21