DeepSeek v4 Flash
Qwen Ai Platform textqwen_ai_platform/deepseek-v4-flash
Input
$0.2000
per 1M input tokens
Output
$0.4000
per 1M output tokens
Cache read
$0.0400
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
1,000,000
Max output
393,216
Effective date
Sep 2, 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)One price on record so far (Sep 2, 2026). This chart fills in as the price changes over time. We check daily.
| Effective | Input | Output | Blended |
|---|---|---|---|
| Sep 2, 2026 | $0.20 | $0.40 | $0.25 |
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
Wandb
· $0.1400 in / $0.2800 out
Novita
· $0.1400 in / $0.2800 out
Other Qwen Ai Platform models
qwen_ai_platform/qwen-turbo
· $0.2000/Mtok out
qwen_ai_platform/qwen-turbo-2024-11-01
· $0.2000/Mtok out
qwen_ai_platform/qwen-turbo-2025-04-28
· $0.2000/Mtok out
qwen_ai_platform/qwen-turbo-latest
· $0.2000/Mtok out
qwen_ai_platform/qwen3.8-flash
· $0.4700/Mtok out
qwen_ai_platform/qwen3.8-omni-flash
· $0.4700/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.