DeepSeek V4 Flash 0731
Wandb textwandb/deepseek-ai/DeepSeek-V4-Flash-0731
Input
$0.1300
per 1M input tokens
Output
$0.2700
per 1M output tokens
Cache read
$0.0500
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
262,000
Max output
262,144
Effective date
Nov 7, 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 |
|---|---|---|---|
| Nov 7, 2026 | $0.13 | $0.27 | $0.17 |
| Oct 27, 2026 | $0.13 | $0.28 | $0.17 |
| Sep 18, 2026 | $0.13 | $0.28 | $0.17 |
| Aug 28, 2026 | $0.13 | $0.28 | $0.17 |
DeepSeek V4 Flash 0731 on other providers
Openrouter
· $0.0060 in / $1.28 out
Deepinfra
· $0.0600 in / $0.1800 out
Sail
· $0.0900 in / $0.1800 out
Baseten
· $0.1300 in / $0.2600 out
Perplexity
· $0.1300 in / $0.2600 out
Nebius
· $0.1400 in / $0.2800 out
Together Ai
· $0.1400 in / $0.2800 out
Inferenceapis
· $0.1900 in / $0.3800 out
Dashscope
· $0.2000 in / $0.4000 out
Qwencloud
· $0.2000 in / $0.4000 out
Qwen Ai Platform
· $0.2000 in / $0.4000 out
Fireworks Ai
· $0.2200 in / $0.6600 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.