Live pricing — last refreshed Apr 21, 2026

Cohere: Command R7B (12-2024) vs DeepSeek: DeepSeek V3.1 Terminus

Head-to-head API pricing and cost comparison between Cohere’s Cohere: Command R7B (12-2024) and DeepSeek’s DeepSeek: DeepSeek V3.1 Terminus. Prices auto-refresh daily from OpenRouter.

Verdict

Cohere: Command R7B (12-2024) is 82% cheaper for input tokens; Cohere: Command R7B (12-2024) also wins on output tokens.

Side-by-side comparison

SpecCohere: Command R7B (12-2024)DeepSeek: DeepSeek V3.1 Terminus
Input price (per 1M)$0.04$0.21
Cached input (per 1M)$0.13
Output price (per 1M)$0.15$0.79
Batch input (per 1M)
Batch output (per 1M)
Reasoning price (per 1M)
Context window128K164K
Vision supportNoNo
Caching supportNoYes
Batch APINoNo
Reasoning capabilityNoNo

Monthly cost at volume

Estimated monthly API spend at common production traffic levels (input/output tokens per request shown).

VolumeCohere: Command R7B (12-2024)DeepSeek: DeepSeek V3.1 TerminusSavings
1K req/day
500in / 200out tokens
$1.46$7.89$6.43
Cohere: Command R7B (12-2024) wins
10K req/day
1500in / 500out tokens
$39.38$213.00$173.63
Cohere: Command R7B (12-2024) wins
100K req/day
3000in / 800out tokens
$697.50$3,786$3,089
Cohere: Command R7B (12-2024) wins
1M req/day
8000in / 2000out tokens
$18,000$97,800$79,800
Cohere: Command R7B (12-2024) wins
Open in interactive calculator →

Adjust input/output token counts, request volume, batch & cached pricing.

Related comparisons

Frequently asked questions

Which is cheaper, Cohere: Command R7B (12-2024) or DeepSeek: DeepSeek V3.1 Terminus?

For input tokens, Cohere: Command R7B (12-2024) is roughly 82% cheaper at $0.04/1M vs $0.21/1M. For output tokens, Cohere: Command R7B (12-2024) wins at $0.15/1M. Real-world cost depends on your input/output ratio — use the calculator to model your actual workload.

What’s the context window difference?

Cohere: Command R7B (12-2024) has a context window of 128K tokens. DeepSeek: DeepSeek V3.1 Terminus offers 164K tokens. Larger context windows are valuable for long documents, RAG pipelines, and multi-turn conversations — but they come with higher input-token bills if you fill them every request.

Should I use Cohere: Command R7B (12-2024) or DeepSeek: DeepSeek V3.1 Terminus?

Choose Cohere: Command R7B (12-2024) if you’re already on the Cohere stack, want broad ecosystem support, or prefer its lower input price. Choose DeepSeek: DeepSeek V3.1 Terminus for DeepSeek’s ecosystem, or its differentiated capabilities. Run a small benchmark on your own prompts before committing — price is only one axis.

How are these prices kept current?

Prices are pulled directly from OpenRouter’s public models API once every 24 hours via a Convex cron job, then normalized to per-1M-token figures. Last refresh: Apr 21, 2026.