Cohere
Generative, embedding, reranking, document and speech models with mixed distribution terms.
34 records cover current retrieval models, original generation/embedding families, twelve dated early versions and the historical managed Moderate component. Family selectors, redirected names and original releases are distinguished. Parse identity, missing specifications and historical lifecycle remain under review.
Browse by model typeCapabilities can overlap
Start with the job your model needs to do. Then narrow by capabilities, provider and price.
What does one question cost?
Compare every model with the same request.
Estimate = (input tokens × input price + output tokens × output price) / 1,000,000. Include conversation history in input and billed reasoning in output. Input-only decision models ignore the output setting; enter all billed input for one decision, including its question and criteria. Media, tools and discounts are separate.
34 models
| Compare | Model | Input tokensPublished limit* | Output tokensMaximum per response* | Input pricePer 1M tokens | Output pricePer 1M tokens | Cost per question1,000 input + 500 outputEstimated · uncached |
|---|---|---|---|---|---|---|
| 128,000context tokens | 256, 512, 1024, 1536vector dimensions | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 32,768context tokens | JSON: ordered results with document index and relevance_scoreoutput formats | Usage pricing $5.00 / instance-hourHourly · Cohere Model Vault$3,250.00 / instance-monthMonthly · Cohere Model VaultRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 32,768context tokens | JSON: ordered results with document index and relevance_scoreoutput formats | Usage pricing $5.00 / instance-hourHourly · Cohere Model Vault$3,250.00 / instance-monthMonthly · Cohere Model VaultRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 128,000max input tokens | 256, 512, 768, 1024, 1536, 2048vector dimensions | Usage pricing $0.12 / 1M text tokensText embeddings · Cohere API$0.40 / 1M image tokensImage embeddings · Cohere APIRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 128,000max input tokens | 256, 512, 768, 1024, 1536, 2048vector dimensions | Usage pricing $0.08 / 1M text tokensText embeddings · Cohere API$0.40 / 1M image tokensImage embeddings · Cohere APIRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 512max input tokens | 1024vector dimensions | Usage pricing $0.10 / 1M text tokensText input · Amazon Bedrock$0.0001 / imageImage input · Amazon BedrockRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 512max input tokens | 384vector dimensions | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 512max input tokens | 1024vector dimensions | Usage pricing $0.10 / 1M text tokensText input · Amazon Bedrock$0.0001 / imageImage input · Amazon BedrockRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 512max input tokens | 384vector dimensions | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 512context tokens | Not collected | Historical pricing $1.00 / 1K searchesReranking searches · Cohere API (retired)Rates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 512context tokens | Not collected | Historical pricing $1.00 / 1K searchesReranking searches · Cohere API (retired)Rates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 4,096context tokens | JSON: ordered results with document index and relevance_scoreoutput formats | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 4,096context tokens | JSON: ordered results with document index and relevance_scoreoutput formats | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 4,096context tokens | JSON: ordered results with document index and relevance_scoreoutput formats | Usage pricing $2.00 / 1K queriesReranking queries · Amazon Bedrock$2.00 / 1K queriesReranking queries · Vercel AI GatewayRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 512max input tokens | 4096vector dimensions | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 512max input tokens | 1024vector dimensions | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 256max input tokens | 768vector dimensions | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 4K (provider-rounded)context tokens | 4,096max output tokens | Historical pricing $1.00 / 1M tokensInput tokens · Amazon Bedrock (historical model)$2.00 / 1M tokensOutput tokens · Amazon Bedrock (historical model)Rates & conditions ↗ | No text-only estimatePrice details ↗ | |||
| 4K (provider-rounded)context tokens | 4,096max output tokens | Historical pricing $0.30 / 1M tokensInput tokens · Amazon Bedrock (historical model)$0.60 / 1M tokensOutput tokens · Amazon Bedrock (historical model)Rates & conditions ↗ | No text-only estimatePrice details ↗ | |||
| 2,048context tokens | Not collected | Usage pricingNot collected | Needs rate detailsPrice details ↗ | |||
| Not collected | Not collected | Usage pricingNot collected | Needs rate detailsPrice details ↗ | |||
| 1,024context tokens | Not collected | Usage pricingNot collected | Needs rate detailsPrice details ↗ | |||
| Not collected | Not collected | Usage pricingNot collected | Needs rate detailsPrice details ↗ | |||
| Not collected | Not collected | Usage pricingNot collected | Needs rate detailsPrice details ↗ | |||
| Not collected | Not collected | Usage pricingNot collected | Needs rate detailsPrice details ↗ | |||
| Not collected | Not collected | Usage pricingNot collected | Needs rate detailsPrice details ↗ | |||
| Not collected | Not collected | Usage pricingNot collected | Needs rate detailsPrice details ↗ | |||
| Not collected | Not collected | Usage pricingNot collected | Needs rate detailsPrice details ↗ | |||
| Not collected | Not collected | Usage pricingNot collected | Needs rate detailsPrice details ↗ | |||
| 512max input tokens | Not collected | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 1,024max input tokens | Not collected | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 1,024max input tokens | Not collected | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| 1,024max input tokens | Not collected | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| Not collected | Not collected | Usage pricingNot collected | Task-based pricingPrice details ↗ | |||
* Media models show their native limits. A shared context window includes both input and output tokens.
Original currency and billing unit, without currency conversion. Rates are dated snapshots; open the conditions for tiers, promotions and endpoint restrictions.How to read the data
Catalog coverage
Closed-weight model variants and explicitly identified closed-source managed model components across language, code, image, video, audio and other documented modalities. Global provider and historical-release coverage is being expanded; this is not yet exhaustive. 172 company reviews are still open.
See what is being reviewed