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

21–40 / 83

OpenRouter Benchmarks

86.476%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Cohere
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
Cohere
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:15:03.392Z
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
0.8647586666666667
accuracy_std_dev
0.008943734131906087
cost_per_task_usd
0.05048964983164983
output_tokens_per_task
41902.75589225589
latency_seconds_per_task
169.53773232323232
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

76.417%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · DigitalOcean
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
4
sample size
400
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
tau_bench_verified_airline
name
tau2-bench Verified Airline
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
2026-10-31T12:30:14.640Z
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
400
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7641665000000001
accuracy_std_dev
0.021586383312171588
cost_per_task_usd
0.0185151775
output_tokens_per_task
14323.5575
latency_seconds_per_task
270.0966575
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
20
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

75.47%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Baidu
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
4
sample size
248
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
tau_bench_verified_airline
name
tau2-bench Verified Airline
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
2026-11-10T18:13:04.202Z
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
248
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7547045887096774
accuracy_std_dev
0.03743255869747622
cost_per_task_usd
0.02217318548387097
output_tokens_per_task
15344.233870967742
latency_seconds_per_task
116.33360483870968
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
11
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

73.733%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Ionstream
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
4
sample size
250
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
tau_bench_verified_airline
name
tau2-bench Verified Airline
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
2026-10-21T12:36:51.217Z
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
250
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7373334
accuracy_std_dev
0.020482933819157834
cost_per_task_usd
0.039714615999999994
output_tokens_per_task
27822.08
latency_seconds_per_task
174.77363200000002
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

72.444%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · River
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
4
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
River
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-14T23:10:29.432Z
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
0.7244443333333334
accuracy_std_dev
0.017708476037072058
cost_per_task_usd
0.01403336
output_tokens_per_task
21082.76
latency_seconds_per_task
98.4962
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

90.277%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Novita
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
5
sample size
1781
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
Novita
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:31:10.643Z
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
1781
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9027699539584503
accuracy_std_dev
0.006295075818094274
cost_per_task_usd
0.028251830432341377
output_tokens_per_task
28841.043234138124
latency_seconds_per_task
172.53925996631108
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
59
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

89.267%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · InferenceNet
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
5
sample size
2337
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
12
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
InferenceNet
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-04T21:06:11.704Z
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
2337
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8926684364569961
accuracy_std_dev
0.021409854620919034
cost_per_task_usd
0.01926024176294395
output_tokens_per_task
30225.52802738554
latency_seconds_per_task
249.78602053915276
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

88.565%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Sail Research
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
5
sample size
1491
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
Sail Research
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-24T09:01:43.485Z
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
1491
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8856471629778674
accuracy_std_dev
0.009013068317726206
cost_per_task_usd
0.010023977867203217
output_tokens_per_task
28220.264922870556
latency_seconds_per_task
270.7399617706237
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
11
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

88.218%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · PrimeIntellect
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
5
sample size
1184
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
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
PrimeIntellect
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:31:11.691Z
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
1184
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8821789256756756
accuracy_std_dev
0.01706691482241463
cost_per_task_usd
0.04157157263513513
output_tokens_per_task
34476.61317567567
latency_seconds_per_task
164.1069873310811
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
22
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

88.103%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Crusoe
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
5
sample size
1188
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
gpqa_diamond
name
GPQA Diamond
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
2026-10-31T08:47:44.999Z
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
1188
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8810325
accuracy_std_dev
0.016020429392393534
cost_per_task_usd
0.03953295538720539
output_tokens_per_task
32800.2398989899
latency_seconds_per_task
203.57452356902357
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
15
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

87.598%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Decart
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
5
sample size
1059
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
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Decart
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:15:03.294Z
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
1059
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8759833172804533
accuracy_std_dev
0.02383166285579381
cost_per_task_usd
0.006660402266288952
output_tokens_per_task
36610.579792256845
latency_seconds_per_task
451.84041265344666
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
9
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%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · DekaLLM
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
5
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
DekaLLM
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-10T11:23:23.352Z
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
0.76
accuracy_std_dev
0.014401594564491825
cost_per_task_usd
0.019761673333333334
output_tokens_per_task
17811.393333333333
latency_seconds_per_task
291.19325333333336
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

75.733%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · NextBit
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
5
sample size
250
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
tau_bench_verified_airline
name
tau2-bench Verified Airline
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
2026-10-03T08:55:31.322Z
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
250
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7573333999999999
accuracy_std_dev
0.03991088294989224
cost_per_task_usd
0.023026752
output_tokens_per_task
18473.992
latency_seconds_per_task
161.149652
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

74.583%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Decart
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
5
sample size
200
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
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Decart
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-24T12:31:49.408Z
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
200
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.74583325
accuracy_std_dev
0.03402396010442498
cost_per_task_usd
0.02499106
output_tokens_per_task
52531.49
latency_seconds_per_task
929.62778
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
9
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

72.833%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · PrimeIntellect
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
5
sample size
300
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
PrimeIntellect
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T12:19:28.999Z
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
300
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7283335
accuracy_std_dev
0.024626886091898288
cost_per_task_usd
0.04604961333333333
output_tokens_per_task
26239.556666666667
latency_seconds_per_task
118.63039
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
21
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

89.853%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · GMICloud
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
6
sample size
2178
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
11
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
GMICloud
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-10T06:04:30.952Z
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
2178
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8985305454545454
accuracy_std_dev
0.018596178744147863
cost_per_task_usd
0.023964589072543615
output_tokens_per_task
27930.285583103763
latency_seconds_per_task
168.61135950413225
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
26
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

88.006%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Modal
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
6
sample size
1580
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
Modal
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T09:42:46.430Z
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
1580
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8800631670886074
accuracy_std_dev
0.006743341790240229
cost_per_task_usd
0.033778830379746834
output_tokens_per_task
27961.480379746834
latency_seconds_per_task
152.0458943037975
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
11
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

87.405%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Makora
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
6
sample size
1973
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
10
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Makora
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:10:37.345Z
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
1973
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8740494840344654
accuracy_std_dev
0.0038017229265163467
cost_per_task_usd
0.04434169640141917
output_tokens_per_task
38209.482513938165
latency_seconds_per_task
202.1977790167258
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

83.979%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Io Net
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
6
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
Io Net
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T17:44:47.331Z
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
0.8397870000000001
accuracy_std_dev
0.06305207943174174
cost_per_task_usd
0.013501392255892255
output_tokens_per_task
24293.242424242424
latency_seconds_per_task
269.24517676767675
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
15
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v4.1-flash-20260910
source model id
deepseek/deepseek-v4.1-flash-20260910
Original result ↗

OpenRouter Benchmarks

74.259%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Sail Research
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
6
sample size
450
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
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Sail Research
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-24T12:29:34.092Z
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
450
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7425926666666667
accuracy_std_dev
0.03165311687654157
cost_per_task_usd
0.013586744444444443
output_tokens_per_task
22693.746666666666
latency_seconds_per_task
236.88698000000002
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
11
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