MoonshotAI: Kimi K3.1 Pro

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D creatio…

moonshotai/kimi-k3.1-pro-20261023

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D creation, financial research, and end-to-end agentic knowledge work, with native image and video understanding.

Specifications & capabilities

Input
text, image, video
Output
text
Context window · tokens
1048576
Published model ID
Kimi-K3.1-Pro
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

1–20 / 38

OpenRouter Benchmarks

93.939%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Nebius
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Nebius
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-04T21:00:08.522Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.939394
cost_per_task_usd
0.06875348484848484
output_tokens_per_task
6669.813131313132
latency_seconds_per_task
279.5326212121212
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
25
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

93.874%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Sail Research
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
759
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
Sail Research
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-06T22:04:38.207Z
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
759
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9387350223978919
accuracy_std_dev
0.0014398627538762172
cost_per_task_usd
0.14429597496706192
output_tokens_per_task
6705.238471673254
latency_seconds_per_task
118.27040579710146
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

93.687%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · River
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
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
2026-11-14T22:21:55.037Z
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
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9368685
accuracy_std_dev
0.000841499999999995
cost_per_task_usd
0.07695460606060606
output_tokens_per_task
7488.792929292929
latency_seconds_per_task
94.15375505050504
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

93.266%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Decart
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
2026-11-11T15:01:28.174Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.93266
cost_per_task_usd
0.04747170707070707
output_tokens_per_task
7164.717171717171
latency_seconds_per_task
97.3390303030303
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

93.266%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DigitalOcean
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
2026-11-07T03:00:36.225Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.93266
cost_per_task_usd
0.06645131313131314
output_tokens_per_task
6433.60101010101
latency_seconds_per_task
52.64973232323233
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

93.182%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Modal
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
2026-11-04T21:00:08.524Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.931818
cost_per_task_usd
0.07295092424242425
output_tokens_per_task
7118.949494949495
latency_seconds_per_task
39.086474747474746
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

93.098%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Parasail
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Parasail
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-04T21:00:08.540Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.930976
cost_per_task_usd
0.07401931818181819
output_tokens_per_task
7194.131313131313
latency_seconds_per_task
70.60726262626262
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
36
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

93.068%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · InferenceNet
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
969
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
InferenceNet
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-05T00:00:09.926Z
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
969
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9306844829721364
accuracy_std_dev
0.007658821616932981
cost_per_task_usd
0.0836984004127967
output_tokens_per_task
7439.702786377709
latency_seconds_per_task
71.15875335397317
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

92.929%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Moonshot AI
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Moonshot AI
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-04T18:03:37.503Z
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
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9292930000000001
accuracy_std_dev
0.003367000000000009
cost_per_task_usd
0.10512464646464648
output_tokens_per_task
6756.267676767677
latency_seconds_per_task
151.92342676767677
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

92.929%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Morph
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
2026-11-05T06:00:06.218Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9292929999999999
cost_per_task_usd
0.11162276262626263
output_tokens_per_task
9183.469696969696
latency_seconds_per_task
129.8331919191919
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

92.929%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · AkashML
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
AkashML
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-05T06:00:43.810Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9292929999999999
cost_per_task_usd
0.08810357575757576
output_tokens_per_task
8602.494949494949
latency_seconds_per_task
85.56265151515152
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

92.761%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Fireworks
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Fireworks
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-05T15:00:03.242Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.927609
cost_per_task_usd
0.07610462626262626
output_tokens_per_task
7400.540404040404
latency_seconds_per_task
98.16792929292929
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
17
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

92.733%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · PrimaLabs
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
172
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
PrimaLabs
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-06T15:43:35.998Z
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
172
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.927326
cost_per_task_usd
0.04753577906976744
output_tokens_per_task
5210.343023255814
latency_seconds_per_task
65.22577325581395
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
3
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

92.677%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Phala
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
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
2026-11-05T18:00:48.183Z
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
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9267675
accuracy_std_dev
0.002525500000000014
cost_per_task_usd
0.07679769191919193
output_tokens_per_task
7530.295454545455
latency_seconds_per_task
175.5164292929293
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

92.424%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Together
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Together
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-04T18:00:08.306Z
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
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9242420000000001
cost_per_task_usd
0.09054113636363637
output_tokens_per_task
8895.065656565657
latency_seconds_per_task
151.3992323232323
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
25
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

91.919%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Wafer
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
1
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Wafer
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-05T21:03:19.219Z
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
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9191920000000001
accuracy_std_dev
0.003367000000000009
cost_per_task_usd
0.07685085101010102
output_tokens_per_task
7560.146464646465
latency_seconds_per_task
125.614
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

78.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Fireworks
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
1
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
Fireworks
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-05T15:41:01.946Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.786667
cost_per_task_usd
0.20422622
output_tokens_per_task
10146.04
latency_seconds_per_task
176.47164
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
14
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

77.333%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Relace
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
1
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
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
Relace
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-05T22:50:26.968Z
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
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.773333
cost_per_task_usd
0.14084568
output_tokens_per_task
10689.44
latency_seconds_per_task
130.9128
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

77%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Moonshot AI
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
1
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
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
Moonshot AI
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-11-04T18:56:58.927Z
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
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.77
accuracy_std_dev
0.016666999999999987
cost_per_task_usd
0.28240516
output_tokens_per_task
10658.56
latency_seconds_per_task
307.07221000000004
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

OpenRouter Benchmarks

76.842%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · River
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
1
sample size
95
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
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
2026-11-14T22:28:02.624Z
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
95
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7684208947368422
accuracy_std_dev
0.005185000000000051
cost_per_task_usd
0.17065703157894738
output_tokens_per_task
8865.2
latency_seconds_per_task
126.58122105263158
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
moonshotai/kimi-k3.1-pro-20261023
source model id
moonshotai/kimi-k3.1-pro-20261023
Original result ↗

Published prices

41–60 / 67

moonshotai/kimi-k3.1-pro ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
parasail
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
parasail | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$2.00

Inference provider
vercelAIGatewayCatalog
Platform
parasail
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
parasail | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$10.00

Inference provider
vercelAIGatewayCatalog
Platform
parasail
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
parasail | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.14

Inference provider
vercelAIGatewayCatalog
Platform
pareto
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
pareto | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$1.40

Inference provider
vercelAIGatewayCatalog
Platform
pareto
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
pareto | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$7.00

Inference provider
vercelAIGatewayCatalog
Platform
pareto
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
pareto | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
relace
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
relace | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.24

Inference provider
vercelAIGatewayCatalog
Platform
relace
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
relace | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$8.41

Inference provider
vercelAIGatewayCatalog
Platform
relace
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
relace | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
runware
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
runware | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$2.00

Inference provider
vercelAIGatewayCatalog
Platform
runware
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
runware | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$10.00

Inference provider
vercelAIGatewayCatalog
Platform
runware
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
runware | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
togetherai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
togetherai | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$2.00

Inference provider
vercelAIGatewayCatalog
Platform
togetherai
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
togetherai | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$10.00

Inference provider
vercelAIGatewayCatalog
Platform
togetherai
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
togetherai | moonshotai/kimi-k3.1-pro
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
varies_by_provider
true
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$0.18

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
region
us
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
varies_by_provider
true
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$2.00

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
input_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
varies_by_provider
true
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$1.80

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
input_tokens_per_million
Currency
USD
Billing conditions
region
us
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
varies_by_provider
true
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k3.1-pro ↗

$10.00

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
varies_by_provider
true
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–2 / 2

Kimi K3.1 Pro ↗

source model id
moonshotai/kimi-k3.1-pro
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
1000000
max output tokens
262144
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput
regions
  • us

kimi-k3.1-pro ↗

source model id
moonshotai/kimi-k3_1-pro
hosting
nvidia-catalog
platforms
  • NVIDIA Build / NIM
context length
1048576
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • toolCalling
  • structuredOutputs
  • reasoning

Source specification observations

1–7 / 7

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

vercelAIGatewayCatalog ↗

field
context_length
value
1000000
normalized value
1000000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

openRouter ↗

field
max_output_tokens
value
943718
normalized value
943718
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
943718
normalized value
943718
scope
source-model
source id
openRouter
confidence
1

vercelAIGatewayCatalog ↗

field
max_output_tokens
value
262144
normalized value
262144
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

Original sources

1–12 / 12

Hugging Face · Model reference ↗

NVIDIA · Model page ↗

OpenRouter · Model page ↗

OpenRouter · Model page ↗

Vercel AI Gateway · Model page ↗

NVIDIA · Documentation ↗

Epoch AI · Catalog ↗

Hugging Face · Catalog ↗

NVIDIA · Catalog ↗

OpenRouter · Catalog ↗

OpenRouter · Catalog ↗

Vercel AI Gateway · Catalog ↗

Source links

1–8 / 8

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