Loading...
Loading...
DeepSeek Coder V2 — code-specialized MoE model supporting 338 languages, competitive with GPT-4 Turbo on coding benchmarks.
$0.800
per 1M input tokens
—
top score across benchmarks
1
APIs serving this model
128K
max token window
| Provider / Variant | Input $/1M | Output $/1M | Latency | Context | |
|---|---|---|---|---|---|
BEST PRICE deepseek-ai Deepseek Coder 33B Instruct | $0.800 | $0.800 | 244ms | 16k |
Looking for alternatives?
Find cheaper or faster models in the same class.
See DeepSeek Coder V2 alternatives →