DeepSeek: DeepSeek V4.1 Flash

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/deepseek-v4.1-flash-20260910

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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental [V4 Flash Vision Exp](https://openrouter.ai/deepseek/deepseek-v4-flash-vision-exp).

It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds [V4 Pro](https://openrouter.ai/deepseek/deepseek-v4-pro-0813) on performance, speed, and task completion time.

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
1048576
Published model ID
DeepSeek-V4.1-Flash
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

1–20 / 83

OpenRouter Benchmarks

90.78%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Mancer 2
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
470
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Mancer 2
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T09:05:48.501Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
470
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9078013574468085
accuracy_std_dev
0.012928926018815361
cost_per_task_usd
0.01807536170212766
output_tokens_per_task
17947.382978723403
latency_seconds_per_task
357.7867425531915
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
6
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

72.34%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Krea
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
517
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Krea
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-09-29T20:57:20.673Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
517
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7234044255319149
accuracy_std_dev
0.1917994784299478
cost_per_task_usd
0.033565591876208896
output_tokens_per_task
37102.30560928433
latency_seconds_per_task
242.77243907156674
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
1
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

64.556%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Krea
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
1
sample size
150
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Krea
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-09-29T19:45:03.655Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
150
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.6455556666666666
accuracy_std_dev
0.09964144484545016
cost_per_task_usd
0.11177372666666668
output_tokens_per_task
87845.5
latency_seconds_per_task
710.81772
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
1
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

90.943%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · NextBit
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
2
sample size
990
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
5
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
NextBit
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-03T09:34:35.533Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
990
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9094272
accuracy_std_dev
0.00547072746168187
cost_per_task_usd
0.025930728282828285
output_tokens_per_task
28121.050505050505
latency_seconds_per_task
177.8861121212121
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
10
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

76.254%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Crusoe
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
2
sample size
299
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
6
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Crusoe
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T12:18:15.192Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
299
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7625417625418061
accuracy_std_dev
0.01910679234955175
cost_per_task_usd
0.03341546153846154
output_tokens_per_task
21777.678929765887
latency_seconds_per_task
144.9030602006689
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
13
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

90.787%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Baidu
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
1326
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
7
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Baidu
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-10T18:05:49.922Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1326
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9078681221719456
accuracy_std_dev
0.005280935005338756
cost_per_task_usd
0.023841498491704374
output_tokens_per_task
27449.11161387632
latency_seconds_per_task
170.5565128205128
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
12
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

90.572%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · SiliconFlow
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
1782
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
9
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
SiliconFlow
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:29:56.453Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1782
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9057238888888889
accuracy_std_dev
0.009356618102764875
cost_per_task_usd
0.03432713860830528
output_tokens_per_task
28444.87317620651
latency_seconds_per_task
196.75796408529743
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
34
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

89.957%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DigitalOcean
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
1779
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
9
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
DigitalOcean
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:33:02.133Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1779
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8995687234401349
accuracy_std_dev
0.007447984730328704
cost_per_task_usd
0.0197627712197864
output_tokens_per_task
22859.64811691962
latency_seconds_per_task
382.0163063518831
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
23
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

89.431%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · ModelRun
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
533
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
ModelRun
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-28T05:00:14.622Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
533
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8943087542213883
accuracy_std_dev
0.03942204850926279
cost_per_task_usd
0.019450917448405252
output_tokens_per_task
28174.943714821762
latency_seconds_per_task
177.9272420262664
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
8
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

88.507%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DekaLLM
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
989
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
5
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
DekaLLM
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-10T08:22:45.418Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
989
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8850689656218401
accuracy_std_dev
0.014411932672615443
cost_per_task_usd
0.026149528816986855
output_tokens_per_task
26995.41152679474
latency_seconds_per_task
355.79747320525786
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
12
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

88.293%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Reka
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
783
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
4
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Reka
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:15:03.390Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
783
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8829290000000001
accuracy_std_dev
0.012699110785799135
cost_per_task_usd
0.027103435504469985
output_tokens_per_task
30539.469987228607
latency_seconds_per_task
200.8993601532567
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
13
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

87.744%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Ionstream
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
990
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
5
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Ionstream
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-21T11:23:15.101Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
990
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8774407999999999
accuracy_std_dev
0.00954717737134911
cost_per_task_usd
0.03921924343434343
output_tokens_per_task
37354.009090909094
latency_seconds_per_task
242.47004242424242
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
5
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

87.226%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · OpenInference
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
3
sample size
1584
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
8
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
OpenInference
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:09:31.159Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1584
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8722639999999998
accuracy_std_dev
0.01391911622553672
cost_per_task_usd
0.01943295707070707
output_tokens_per_task
35123.857954545456
latency_seconds_per_task
314.6860820707071
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
7
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

73.333%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Mancer 2
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
3
sample size
150
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Mancer 2
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T12:31:12.958Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
150
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7333333333333333
accuracy_std_dev
0.014401903168987377
cost_per_task_usd
0.06451945333333334
output_tokens_per_task
15144.64
latency_seconds_per_task
876.0850533333333
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
5
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

90.816%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Alibaba
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
4
sample size
1782
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
9
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Alibaba
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:40:16.353Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1782
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9081554444444445
accuracy_std_dev
0.008876832231665518
cost_per_task_usd
0.033613874298540965
output_tokens_per_task
27019.509539842875
latency_seconds_per_task
210.73789562289562
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
29
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

90.535%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · StreamLake
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
4
sample size
1782
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
9
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
StreamLake
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T09:01:06.228Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1782
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9053496666666667
accuracy_std_dev
0.008612696635394351
cost_per_task_usd
0.02068693490460157
output_tokens_per_task
28854.00224466891
latency_seconds_per_task
208.79350953984286
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
30
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

89.541%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · AtlasCloud
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
4
sample size
1584
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
8
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
AtlasCloud
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:27:49.932Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1584
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.895412375
accuracy_std_dev
0.020051295631065218
cost_per_task_usd
0.02414115151515151
output_tokens_per_task
27810.135101010103
latency_seconds_per_task
210.27494823232323
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
30
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

89.529%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Phala
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
4
sample size
1536
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
8
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Phala
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T09:17:17.877Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1536
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8952905937499999
accuracy_std_dev
0.016969367452854572
cost_per_task_usd
0.032397834635416664
output_tokens_per_task
32195.716796875
latency_seconds_per_task
236.218794921875
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
24
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

89.415%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Morph
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
4
sample size
1584
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
8
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Morph
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:33:46.211Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1584
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8941497500000002
accuracy_std_dev
0.012326495474687834
cost_per_task_usd
0.010706986111111112
output_tokens_per_task
20748.16351010101
latency_seconds_per_task
265.82926073232323
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
10
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

88.552%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · River
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
4
sample size
594
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
River
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-14T22:14:47.015Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
594
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8855219999999999
accuracy_std_dev
0.009912179612308596
cost_per_task_usd
0.016982043771043773
output_tokens_per_task
35207.07407407407
latency_seconds_per_task
144.32716498316498
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
6
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

Published prices

1–20 / 96

deepseek-ai/DeepSeek-V4.1-Flash ↗

$0.0030

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
tier
peak:off:14-24
label
14:00 – 24:00(UTC)
Billing label
Cached input tokens (per 1M)

deepseek-ai/DeepSeek-V4.1-Flash ↗

$0.01

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
tier
peak:on:0-14
label
00:00 – 14:00(UTC)
Billing label
Cached input tokens (per 1M)

deepseek-ai/DeepSeek-V4.1-Flash ↗

$0.15

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
input_tokens_per_million
Currency
USD
Billing conditions
tier
peak:off:14-24
label
14:00 – 24:00(UTC)
Billing label
Input tokens (per 1M)

deepseek-ai/DeepSeek-V4.1-Flash ↗

$0.30

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
input_tokens_per_million
Currency
USD
Billing conditions
tier
peak:on:0-14
label
00:00 – 14:00(UTC)
Billing label
Input tokens (per 1M)

deepseek-ai/DeepSeek-V4.1-Flash ↗

$0.60

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
output_tokens_per_million
Currency
USD
Billing conditions
tier
peak:off:14-24
label
14:00 – 24:00(UTC)
Billing label
Output tokens (per 1M)

deepseek-ai/DeepSeek-V4.1-Flash ↗

$1.20

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
output_tokens_per_million
Currency
USD
Billing conditions
tier
peak:on:0-14
label
00:00 – 14:00(UTC)
Billing label
Output tokens (per 1M)

deepseek/deepseek-v4.1-flash ↗

$0.02

Inference provider
vercelAIGatewayCatalog
Platform
alibaba
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
alibaba | deepseek/deepseek-v4.1-flash
model_type
language
peak_pricing
windows
  • end_minute_utc
    840
    start_minute_utc
    0
multiplier
2
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

deepseek/deepseek-v4.1-flash ↗

$0.15

Inference provider
vercelAIGatewayCatalog
Platform
alibaba
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
alibaba | deepseek/deepseek-v4.1-flash
model_type
language
peak_pricing
windows
  • end_minute_utc
    840
    start_minute_utc
    0
multiplier
2
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

deepseek/deepseek-v4.1-flash ↗

$0.60

Inference provider
vercelAIGatewayCatalog
Platform
alibaba
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
alibaba | deepseek/deepseek-v4.1-flash
model_type
language
peak_pricing
windows
  • end_minute_utc
    840
    start_minute_utc
    0
multiplier
2
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

deepseek/deepseek-v4.1-flash ↗

$0.01

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | deepseek/deepseek-v4.1-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

deepseek/deepseek-v4.1-flash ↗

$0.01

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
region
scope
zone
geo_region
us
endpoint
baseten | deepseek/deepseek-v4.1-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

deepseek/deepseek-v4.1-flash ↗

$0.30

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | deepseek/deepseek-v4.1-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

deepseek/deepseek-v4.1-flash ↗

$0.30

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
input_tokens_per_million
Currency
USD
Billing conditions
region
scope
zone
geo_region
us
endpoint
baseten | deepseek/deepseek-v4.1-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

deepseek/deepseek-v4.1-flash ↗

$1.20

Inference provider
vercelAIGatewayCatalog
Platform
baseten
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
baseten | deepseek/deepseek-v4.1-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–6 / 6

deepseek-ai/DeepSeek-V4.1-Flash ↗

source model id
azure-huggingface/deepseek-ai--deepseek-v4.1-flash@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
MIT
context length
1048576
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    deepseek-ai/DeepSeek-V4.1-Flash ↗

    source model id
    azure-huggingface/deepseek-ai--deepseek-v4.1-flash@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    MIT
    context length
    1048576
    architecture
    input_modalities
    • text
    • image
    output_modalities
    • text
    capabilities

      deepseek-v4.1-flash ↗

      source model id
      deepseek-ai/deepseek-v4.1-flash
      hosting
      nvidia-catalog
      platforms
      • NVIDIA Build / NIM
      context length
      1048576
      architecture
      input_modalities
      • text
      • image
      output_modalities
      • text
      capabilities
      • toolCalling
      • reasoning

      deepseek-ai/DeepSeek-V4.1-Flash ↗

      source model id
      deepseek-ai/DeepSeek-V4.1-Flash
      hosting
      siliconflow-hosted
      platforms
      • SiliconFlow
      max output tokens
      393216
      architecture
      input_modalities
      • text
      • image
      output_modalities
      • text
      capabilities
      • promptCaching
      • reasoning
      • structuredOutputs
      • toolCalling

      DeepSeek V4.1 Flash ↗

      source model id
      deepseek/deepseek-v4.1-flash
      hosting
      vercel-gateway
      platforms
      • Vercel AI Gateway
      context length
      1048576
      max output tokens
      32768
      architecture
      input_modalities
      • text
      • image
      • pdf
      output_modalities
      • text
      capabilities
      • promptCaching
      • reasoning
      • structuredOutputs
      • toolCalling
      • visionInput
      regions
      • us

      deepseek-ai/DeepSeek-V4.1-Flash ↗

      source model id
      publishers/deepseek-ai/models/deepseek-v4.1@deepseek-v4.1-flash
      hosting
      vertex-self-deployed
      platforms
      • Google Cloud Vertex AI
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities

        Safety assessments

        1–1 / 1

        Foundation Model Transparency Index 2025 ↗

        32 / 100

        source id
        stanfordFMTI
        canonical model id
        deepseek/deepseek-v4.1-flash-20260910
        taxonomy
        transparency
        hazard category
        transparency
        hazard name
        Organization transparency
        policy area
        DeepSeek
        assessment type
        organization-level disclosure
        metric
        disclosure_score
        result label
        32 / 100
        sample size
        100
        updated at
        2026-11-09T18:08:05.227Z

        Source specification observations

        1–11 / 11

        azureFoundry ↗

        field
        context_length
        value
        1048576
        normalized value
        1048576
        scope
        source-model
        source id
        azureFoundry
        confidence
        1

        azureFoundry ↗

        field
        context_length
        value
        1048576
        normalized value
        1048576
        scope
        source-model
        source id
        azureFoundry
        confidence
        1

        nvidiaNim ↗

        field
        context_length
        value
        1048576
        normalized value
        1048576
        scope
        source-model
        source id
        nvidiaNim
        confidence
        1

        openRouter ↗

        field
        context_length
        value
        1048576
        normalized value
        1048576
        scope
        source-model
        source id
        openRouter
        confidence
        1

        openRouter ↗

        field
        context_length
        value
        1048576
        normalized value
        1048576
        scope
        source-model
        source id
        openRouter
        confidence
        1

        siliconFlow ↗

        field
        context_length
        value
        1049K
        scope
        source-model
        source id
        siliconFlow
        confidence
        1

        vercelAIGatewayCatalog ↗

        field
        context_length
        value
        1048576
        normalized value
        1048576
        scope
        source-model
        source id
        vercelAIGatewayCatalog
        confidence
        1

        openRouter ↗

        field
        max_output_tokens
        value
        393216
        normalized value
        393216
        scope
        source-model
        source id
        openRouter
        confidence
        1

        openRouter ↗

        field
        max_output_tokens
        value
        131072
        normalized value
        131072
        scope
        source-model
        source id
        openRouter
        confidence
        1

        siliconFlow ↗

        field
        max_output_tokens
        value
        393K
        scope
        source-model
        source id
        siliconFlow
        confidence
        1

        vercelAIGatewayCatalog ↗

        field
        max_output_tokens
        value
        32768
        normalized value
        32768
        scope
        source-model
        source id
        vercelAIGatewayCatalog
        confidence
        1

        Original sources

        1–20 / 24

        SiliconFlow · Model page ↗

        Hugging Face · Model repository ↗

        Google Cloud · Model page ↗

        Microsoft Foundry · Model page ↗

        Microsoft Foundry · Model page ↗

        NVIDIA · Model page ↗

        OpenRouter · Model page ↗

        OpenRouter · Model page ↗

        SiliconFlow · Playground ↗

        Vercel AI Gateway · Model page ↗

        Google Cloud · Model documentation ↗

        Microsoft Foundry · Model documentation ↗

        NVIDIA · Documentation ↗

        SiliconFlow · API documentation ↗

        GitHub · Catalog ↗

        Google Cloud · Catalog ↗

        Hugging Face · Catalog ↗

        Hugging Face · Catalog ↗

        Microsoft Foundry · Catalog ↗

        NVIDIA · Catalog ↗

        Source links

        1–11 / 11

        Hugging Face model card

        1–1 / 1

        Explore more models

        Models

        Loading
        EVIDENCE / COMPARISON

        Benchmarks

        Explore every benchmark

        Loading

        These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

        Install TensorTrace