Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of Cohere: Command A+, embeddinggemma-2
2 modelscohereCohere: Command A+Remove ×googleembeddinggemma-2Remove ×
What’s differentCommand A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...EmbeddingGemma 2 is a 740M parameter multimodal embedding model from Google DeepMind that maps text (incl. code), images, video and audio, alone or interleaved, into a single 768-dimensional vector space,…
DateSep 22, 2026ListedOct 8, 2026Listed
Listed rate$0.30 in / $1.50 out/ 1M tokensCohere · via OpenRouter · all routes ↗cohereSee provider quotes
Provider endpoints2 endpoints →0 endpoints →
Context window192K8.2K
Max output64K—
Parameters——
Tool callingSupportedNot reported
Structured outputSupportedNot reported
Image inputSupportedNot reported
ReasoningSupportedNot reported
Prompt cachingSupportedNot reported

Add another model

Search all models →