DeepSeek Flash
This model always redirects to the latest model in the DeepSeek Flash family.
deepseek-flashReleased 14 Sep 2026 (Sep 2026)Pricing
List prices at DeepSeek, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.30 | $1.20 | |
| Cached input 98% off input | $0.006 | 98% off input | |
| Cache write, 5 minutes | $0.00 |
What it costs a month
At DeepSeek list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$154
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$117
- Coding agent1,000 requests a day, 40K in / 2K out, cached$185
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,008
Where to run it
3 hosts serve DeepSeek Flash. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
DeepSeekLab API deepseek-flash | $0.30 / $1.20 | deepseek-flash | |
Fireworks AIInference deepseek-flash-latest | $0.30 / $1.20 | deepseek-flash-latest | |
Inference APIsGateway deepseek-flash | $0.40 / $1.60 +33% vs headline | deepseek-flash |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| DeepSeek | |||||||
| Alias deepseek-flash | $0.30 / $1.20 | deepseek-flash | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Features
- Assistant prefillParallel tool callsPrompt caching
- Open weights
- License: DeepSeek License (MIT code)Runtimes: SGLang, TGI, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than DeepSeek.
Smaller DeepSeek models
No cheaper DeepSeek model keeps its key capabilities.
Other frontier labs
- 12% less
- 62% less
- 62% less
- 50% less
Open-weight picks
- 8% less
- 17% less
- 33% less
- 51% less
Call it
Using DeepSeek's API.
from litellm import completion
response = completion(
model="deepseek/deepseek-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek Flash cost?
On DeepSeek, DeepSeek Flash costs $0.30 per million input tokens and $1.20 per million output tokens. Cached input costs $0.006 per million tokens.
Which APIs offer DeepSeek Flash?
DeepSeek Flash runs on 3 APIs: DeepSeek, Fireworks AI and Inference APIs.
What is DeepSeek Flash's context window?
1M tokens, with up to 393K tokens in one reply.
Is DeepSeek Flash being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to DeepSeek Flash?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (12% less), Claude Haiku 5.5 on Anthropic (62% less) and Qwen3.7 Plus on Replicate (8% less). Savings are on a mix of 3 input tokens to 1 output token.
When was DeepSeek Flash released?
DeepSeek released it on 14 Sep 2026.
What is DeepSeek Flash's API model id?
Use deepseek-flash with DeepSeek. Other hosts use their own ids: deepseek-flash-latest on Fireworks AI.
Sources
Raw catalog entry for deepseek-flash on DeepSeek
{
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 6e-9,
"input_cost_per_token": 3e-7,
"input_cost_per_token_cache_hit": 6e-9,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"mode": "chat",
"off_peak_pricing": {
"cache_read_input_token_cost": 3e-9,
"input_cost_per_token": 1.5e-7,
"output_cost_per_token": 6e-7,
"windows": [
{
"hours_utc": [
"00:00-01:00",
"04:00-06:00",
"10:00-00:00"
],
"weekdays": [
1,
2,
3,
4,
5
]
},
{
"hours_utc": "00:00-00:00",
"weekdays": [
6,
7
]
}
]
},
"output_cost_per_token": 0.0000012,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
}