CohereCommand A
Best configuration ranks #470 of 610 on the BenchLeader Index at 42.1 ±6.2. Released 13 Mar 2025.
- Blended price
- $4.38/M
- $2.50 in · $10.00 out
- Output speed
- 67 tok/s
- First answer
- 1.62 s
- first token 0.29 s
- Context
- 256k
- Overall index42
- Reasoning29
- Agents & tools50
- Knowledge41
- Instruction following39
- Long context36
- Composite38
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 |
|---|---|---|---|---|---|---|
| thinking | – | – | 67 tok/s | 1.62 s | $0.0040 | Agents & tools 67 |
| defaultbest | 42.1 | #470 | 67 tok/s | 1.62 s | $0.0040 | Agents & tools 50 · Composite 38 · Instruction following 39 · Knowledge 41 · Long context 36 · Reasoning 29 |
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.
Reasoning
| Benchmark | thinking | default | Source |
|---|---|---|---|
| GPQA Diamond (AA)not in index | – | 52.7%#394 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | – | 4.0%#463 | Artificial Analysis |
| Kagi LLM Benchmark | – | 28.8%#124 | Kagi LLM Benchmark |
Agents & tools
| Benchmark | thinking | default | Source |
|---|---|---|---|
| Terminal-Bench Hard | – | 0.8%#332 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | – | 15.2%#346 | Artificial Analysis |
| BFCL Overall | 57.1%#11 | 46.5%#28 | Berkeley Function Calling Leaderboard |
Knowledge
| Benchmark | thinking | default | Source |
|---|---|---|---|
| AA-Omniscience | – | -48.3#301 | Artificial Analysis |
Instruction following
| Benchmark | thinking | default | Source |
|---|---|---|---|
| IFBench | – | 36.5%#285 | Artificial Analysis |
Long context
| Benchmark | thinking | default | Source |
|---|---|---|---|
| AA-LCR | – | 21.3%#355 | Artificial Analysis |
Composite
| Benchmark | thinking | default | Source |
|---|---|---|---|
| AA Intelligence Index | – | 7.0#417 | Artificial Analysis |
Where to run it
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 |
|---|---|---|---|---|---|---|
| Cohere | 55 tok/s | 0.29 s | $2.50 | $10.00 | 256k | – |
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. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0040 | – | 6.1 s |
| Summarise a 30-page report | 12,000 / 600 | $0.036 | – | 10.6 s |
| Code edit | 6,000 / 1,500 | $0.030 | – | 24.0 s |
| Agentic coding session | 60,000 / 4,000 | $0.190 | – | 1.0 min |
| Structured extraction | 2,000 / 200 | $0.0070 | – | 4.6 s |
See also
Data as of 9 Sept 2026. Compare these configurations.