DeepSeek V4 Flash
Wandb textwandb/deepseek-ai/DeepSeek-V4-Flash
Input
$0.1400
per 1M input tokens
Output
$0.2800
per 1M output tokens
Cache read
$0.0700
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
1,049,000
Max output
1,048,576
Effective date
Oct 27, 2026
Estimate a workload
Enter token counts to see the cost at this model's rates.
Estimated cost:
$0.00
Price history
blended $ per 1M tokens (3:1)| Effective | Input | Output | Blended |
|---|---|---|---|
| Oct 27, 2026 | $0.14 | $0.28 | $0.18 |
| Sep 18, 2026 | $0.14 | $0.28 | $0.18 |
| Aug 28, 2026 | $0.14 | $0.28 | $0.18 |
DeepSeek V4 Flash on other providers
Openrouter
· $0.0075 in / $1.28 out
Deepinfra
· $0.0900 in / $0.1800 out
Gmi
· $0.0910 in / $0.1820 out
Pinstripes
· $0.1000 in / $0.2000 out
Kyma
· $0.1230 in / $0.2458 out
Nebius
· $0.1400 in / $0.2800 out
Fireworks Ai
· $0.1400 in / $0.2800 out
Fireworks Ai
· $0.1400 in / $0.2800 out
Tensormesh
· $0.1400 in / $0.2800 out
Streamlake
· $0.1400 in / $0.2800 out
Novita
· $0.1400 in / $0.2800 out
Tencent
· $0.1400 in / $0.2800 out
Other Wandb models
wandb/openai/gpt-oss-120b
· $0.1700/Mtok out
wandb/openai/gpt-oss-20b
· $0.1300/Mtok out
wandb/ibm-granite/granite-4.1-8b
· $0.1000/Mtok out
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct
· $0.1000/Mtok out
wandb/OpenPipe/Qwen3-14B-Instruct
· $0.2200/Mtok out
wandb/ibm-granite/granite-4.2-8b
· $0.1500/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.