DeepSeek: DeepSeek V4.1 Flash
DeepSeek: DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash
Kilo Catalog ChangesLast Observed: 2026-10-15 06:04:16.393291 UTC
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
- Context Tokens: 1048576
- Input Price (Native Units): 0.000000300000
- Output Price (Native Units): 0.000001200000
- Output Token Limit: 943718
- Find Similar · At Least This Context And The Same Reported Modality
Architecture And Modalities · 2
Architecture · Modality
API Details/architecture/modality text+image->text |
text+image->text |
|---|---|
Architecture · Tokenizer
API Details/architecture/tokenizer DeepSeek |
DeepSeek |
Catalog Identity And Metadata · 19
Context Tokens
API Details/context_length 1048576 |
1,048,576 |
|---|---|
Created
API Details/created 1789021285 |
2026-09-10 06:21:25 UTC |
Description
API Details/description DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on... |
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on... |
Expiration Date
API Details/expiration_date Explicit Null |
Explicit Null |
Id
API Details/id deepseek/deepseek-v4.1-flash |
deepseek/deepseek-v4.1-flash |
Is Free
API Details/isFree False |
False |
May Train On Your Prompts
API Details/mayTrainOnYourPrompts False |
False |
Name
API Details/name DeepSeek: DeepSeek V4.1 Flash |
DeepSeek: DeepSeek V4.1 Flash |
Opencode · Variants · High · Reasoning · Effort
API Details/opencode/variants/high/reasoning/effort high |
high |
Opencode · Variants · High · Reasoning · Enabled
API Details/opencode/variants/high/reasoning/enabled True |
True |
Opencode · Variants · Low · Reasoning · Effort
API Details/opencode/variants/low/reasoning/effort low |
low |
Opencode · Variants · Low · Reasoning · Enabled
API Details/opencode/variants/low/reasoning/enabled True |
True |
Opencode · Variants · Max · Reasoning · Effort
API Details/opencode/variants/max/reasoning/effort max |
max |
Opencode · Variants · Max · Reasoning · Enabled
API Details/opencode/variants/max/reasoning/enabled True |
True |
Opencode · Variants · None · Reasoning · Effort
API Details/opencode/variants/none/reasoning/effort none |
none |
Opencode · Variants · None · Reasoning · Enabled
API Details/opencode/variants/none/reasoning/enabled False |
False |
Preferred Index
API Details/preferredIndex 6 |
6 |
Terminal Bench · Avg Attempt Cost Usd
API Details/terminalBench/avgAttemptCostUsd 2.5831196000000003 |
2.5831196000000003 |
Terminal Bench · Overall Score
API Details/terminalBench/overallScore 0.75280899 |
0.75280899 |
Request Limits · 1
Per Request Limits
API Details/per_request_limits Explicit Null |
Explicit Null |
|---|
Pricing · 3
Output Price · USD/Token
API Details/pricing/completion 0.000001200000 |
0.000001200000 |
|---|---|
Pricing · Input Cache Read
API Details/pricing/input_cache_read 0.000000006000 |
0.000000006000 |
Input Price · USD/Token
API Details/pricing/prompt 0.000000300000 |
0.000000300000 |
Provider Limits · 3
Top Provider · Context Length
API Details/top_provider/context_length 1048576 |
1,048,576 |
|---|---|
Top Provider · Is Moderated
API Details/top_provider/is_moderated False |
False |
Top Provider · Max Completion Tokens
API Details/top_provider/max_completion_tokens 943718 |
943,718 |
API Structure And Container Types
Architecture
API Details/architecture Object · See Fields |
Object · See Fields |
|---|---|
Architecture · Input Modalities
API Details/architecture/input_modalities Array · See Items |
Array · See Items |
Architecture · Output Modalities
API Details/architecture/output_modalities Array · See Items |
Array · See Items |
Opencode
API Details/opencode Object · See Fields |
Object · See Fields |
Opencode · Variants
API Details/opencode/variants Object · See Fields |
Object · See Fields |
Opencode · Variants · High
API Details/opencode/variants/high Object · See Fields |
Object · See Fields |
Opencode · Variants · High · Reasoning
API Details/opencode/variants/high/reasoning Object · See Fields |
Object · See Fields |
Opencode · Variants · Low
API Details/opencode/variants/low Object · See Fields |
Object · See Fields |
Opencode · Variants · Low · Reasoning
API Details/opencode/variants/low/reasoning Object · See Fields |
Object · See Fields |
Opencode · Variants · Max
API Details/opencode/variants/max Object · See Fields |
Object · See Fields |
Opencode · Variants · Max · Reasoning
API Details/opencode/variants/max/reasoning Object · See Fields |
Object · See Fields |
Opencode · Variants · None
API Details/opencode/variants/none Object · See Fields |
Object · See Fields |
Opencode · Variants · None · Reasoning
API Details/opencode/variants/none/reasoning Object · See Fields |
Object · See Fields |
Pricing
API Details/pricing Object · See Fields |
Object · See Fields |
Supported Parameters
API Details/supported_parameters Array · See Items |
Array · See Items |
Terminal Bench
API Details/terminalBench Object · See Fields |
Object · See Fields |
Top Provider
API Details/top_provider Object · See Fields |
Object · See Fields |
Architecture · Input Modalities
2 items · source order preserved
- text
- image
API Details
| Item | /architecture/input_modalities/* |
|---|---|
| 1 | text |
| 2 | image |
Architecture · Output Modalities
1 items · source order preserved
- text
API Details
| Item | /architecture/output_modalities/* |
|---|---|
| 1 | text |
Supported Parameters
20 items · source order preserved
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- reasoning_effort
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
API Details
| Item | /supported_parameters/* |
|---|---|
| 1 | frequency_penalty |
| 2 | include_reasoning |
| 3 | logit_bias |
| 4 | logprobs |
| 5 | max_tokens |
| 6 | min_p |
| 7 | presence_penalty |
| 8 | reasoning |
| 9 | reasoning_effort |
| 10 | repetition_penalty |
| 11 | response_format |
| 12 | seed |
| 13 | stop |
| 14 | structured_outputs |
| 15 | temperature |
| 16 | tool_choice |
| 17 | tools |
| 18 | top_k |
| 19 | top_logprobs |
| 20 | top_p |
Recorded Value History
Input Price · USD/Token
6 of 6 records plotted · 0 excluded for missing or invalid coordinates.
Up to 100 recorded versions, spaced by observation order rather than elapsed time. Array fields use the minimum numeric item in each version. Missing values are omitted. Select a point to open its archived snapshot; comparison actions use the current listing. History begins at the first recorded baseline.
Select a point to open its listing or add it to compare.