Best configuration ranks #320 of 610 on the BenchLeader Index at 48.6 ±9.6 (thinking reasoning effort). Released 15 Dec 2025.
Blended price
$0.088/M
$0.050 in · $0.200 out
Output speed
231 tok/s
First answer
9.82 s
first token 0.97 s
Context
1M
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
Overall index49
Agents & tools45
Knowledge40
Instruction following69
Long context45
Composite40
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.
Effort
Index
Rank
Speed
First answer
Chat reply cost
Categories
thinkingbest
48.6
#320
231 tok/s
9.82 s
$0.0001
Agents & tools 45 · Composite 40 · Instruction following 69 · Knowledge 40 · Long context 45
default
43.4
#437
166 tok/s
0.97 s
$0.0001
Agents & tools 44 · Coding 49 · Composite 38 · Human preference 48 · Instruction following 40 · Knowledge 31 · Long context 30 · Reasoning 48
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
Provider
Speed
First token
Input $/M
Output $/M
Context
Quantisation
NovitaAI
191 tok/s
0.44 s
$0.050
$0.200
262k
fp4
Crusoe
146 tok/s
0.28 s
$0.050
$0.200
262k
fp8
Nebius Token Factory
94 tok/s
0.27 s
$0.060
$0.240
262k
fp8
DeepInfra
81 tok/s
3.43 s
$0.050
$0.200
262k
fp4
Price history
Listed price per 1M tokens over time, as recorded by OpenRouter for the provider with the longest history.
input outputnow $0.050 in · $0.200 out
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.025 per 1M. Reasoning tokens are not modelled.
NVIDIA