Head-to-Head Pricing Benchmark
Side-by-side pricing and context window comparison for production model selection.
Default Recommendation (120M input + 60M output)
Cohere: Command R7B (12-2024) is lower-cost for the default monthly workload scenario.
Adjust the workload in the calculator below to see a live recommendation for your usage.
| Metric | Cohere: Command R7B (12-2024) | OpenAI: gpt-oss-120b |
|---|---|---|
| Developer | cohere | openai |
| Context Window | 128,000 | 131,072 |
| Max Output Tokens | 4,000 | — |
| Input Cost / 1M Tokens | $0.0375 | $0.0390 |
| Output Cost / 1M Tokens | $0.1500 | $0.1900 |
| Projected Monthly Cost | $14 | $16 |
| Vision | ❌ No | ❌ No |
| Tool Calling | ❌ No | ✅ Yes |
| Structured Output | ✅ Yes | ✅ Yes |
| Reasoning | ❌ No | ✅ Yes |
| Web Search | ❌ No | ❌ No |
| Tokenizer | Cohere | GPT |
| MMLU Score | N/A | 77.5 |
| GPQA | N/A | 67.2 |
Price History
Current Input / 1M
$0.0375
Current Output / 1M
$0.1500
Price History
Current Input / 1M
$0.0390
Current Output / 1M
$0.1900
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
99.9%
Adjust your workload to see projected monthly costs.
Cohere: Command R7B (12-2024)
$14
per month
Lower costOpenAI: gpt-oss-120b
$16
per month
Live Recommendation
Cohere: Command R7B (12-2024) is lower-cost at 120M input + 60M output tokens/month.
Continue evaluation with more “A vs B pricing” decision pages.