Skip to content
Model Pareto

Command A

CohereOpen weightsartificialanalysis.ai ↗
Input
$2.50/M tok
Output
$10/M tok
Blended
$4.375/M tok · 3:1
Speed
57tok/s
Context
256Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Command A. Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
2× H200 141GB
FP8 weights
Throughput
~2,291 tok/s
many requests batched
Price
$0.53–4.35 /M tok
busy → light use
On your own machine
Mac Studio M5 Max 128GB (int4, ~8 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (111B params) + 25% KV-cache headroom ≈ 139 GB
  • 2× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~2,291 output tok/s aggregate at batch 82 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~8,424 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Writing & chat

Hard reasoning

Agents

~#13 of 15 (estimated)~51.8%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #12Nemotron 3.5 Super VL NVFP452.3%
  4. ~#13Command AEstimated51.8%
  5. #13Nemotron 3.5 Super VL51.1%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Command AEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#21 of 22 (estimated)~34.0%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #20Nemotron 3 Ultra44.4%
  4. ~#21Command AEstimated34.0%
  5. #21Mistral Small 421.3%
No published score — estimated from related benchmarks
~#60 of 92 (estimated)~712 Elo
  1. #1Claude Opus 5.51866
  2. #2Muse Wonder Full1857
  3. #59Claude Haiku 4.5719
  4. ~#60Command AEstimated712
  5. #60MiniCPM5-2B694
No published score — estimated from related benchmarks
~#79 of 85 (estimated)~0.3%
  1. #1Claude Fable 5.276.4%
  2. #2Muse Wonder Full71.3%
  3. #77Granite 4.2 3B0.4%
  4. ~#79Command AEstimated0.3%
  5. #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
~#91 of 91 (estimated)~3.1%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #90Llama 4 Scout3.3%
  4. ~#91Command AEstimated3.1%
No published score — estimated from related benchmarks