Zurück zur EntwicklerzoneOffizielle Preise Offizielle Preise
Cohere Modelle
Entdecken Sie alle 2 Modelle von Cohere mit detaillierten Preisen, Vor- und Nachteilen sowie Entwicklerempfehlungen.
2
Modelle
$1.00
Niedrigster Input
256K
Max. Kontext
2
Qualitätsstufen
Schnellempfehlungen
Bestes Preis-Leistungs-Verhältnis: Command A ($1.00/1M)
Beste Qualität: Command A
Command A
FlagshipTool use, RAG, agents
Wann verwenden: Best Cohere model for enterprise tool use, RAG, and multilingual agent workloads.
Upgrade-Highlights
- ◆111B params — Cohere's largest and most capable model
- ◆256K context — 2x Command R+'s 128K for longer documents
- ◆150% higher throughput than Command R+ — faster production serving
- ◆23 languages supported — widest multilingual coverage at Cohere
- ◆Fine-tuning + function calling — purpose-built for enterprise agents
Input-Preis
$1.00
per 1M tokens
Output-Preis
$2.00
per 1M tokens
Cached Input
—
per 1M tokens
Batch-Input
—
per 1M tokens
Kontextfenster: 256K
Max. Output: 8,000 tokens
Wissensstand: 2025-03
VisionFunktionsaufrufFeinabstimmungJSON-ModusKostenlose Stufe
Vorteile
- 111B params, 256K context
- 150% higher throughput than Command R+
- 23 languages supported
Nachteile
- No vision support
- Smaller context than competitors
- Limited benchmarks available
Leistung
Ausgabegeschwindigkeit~60 tok/s
Rate-Limit3,000 RPM
Multimodal
BildeingabeBildausgabeAudioeingabeAudioausgabe
Benchmarks
MMLU
82.0%
HumanEval
79.0%
Command R+
Mid-tierRAG, enterprise search
Wann verwenden: Specialized for enterprise RAG and search — use when retrieval quality is the priority.
Upgrade-Highlights
- ◆Purpose-built for RAG pipelines — grounded generation with citations
- ◆Enterprise search optimization — best-in-class retrieval accuracy
- ◆Fine-tuning available — customize for domain-specific knowledge bases
- ◆4K max output is limiting — upgrade to Command A for 8K output
- ◆Expensive at $2.50/$10 — Command A offers more at $1/$2
Input-Preis
$2.50
per 1M tokens
Output-Preis
$10.00
per 1M tokens
Cached Input
—
per 1M tokens
Batch-Input
—
per 1M tokens
Kontextfenster: 128K
Max. Output: 4,000 tokens
Wissensstand: 2024-08
VisionFunktionsaufrufFeinabstimmungJSON-ModusKostenlose Stufe
Vorteile
- Purpose-built for RAG pipelines
- Enterprise search optimization
- Fine-tuning available
Nachteile
- Only 4K max output
- No vision
- Expensive for mid-tier
Leistung
Ausgabegeschwindigkeit~50 tok/s
Rate-Limit2,000 RPM
Multimodal
BildeingabeBildausgabeAudioeingabeAudioausgabe
Benchmarks
MMLU
78.0%
HumanEval
73.0%
Nebeneinander-Vergleich
| Modell | Stufe | Input | Output | Kontext |
|---|---|---|---|---|
| Command A | Flagship | $1.00 | $2.00 | 256K |
| Command R+ | Mid-tier | $2.50 | $10.00 | 128K |