Tiny Aya Global: Intelligence, Performance & Price Analysis
Available providers
Model summary
Verbosity
Tiny Aya Global supports text input, outputs text, and has a 8k tokens context window.
Pricing for Tiny Aya Global is $0.00 per 1M input tokens (competitively priced, median: $0.00) and $0.00 per 1M output tokens (competitively priced, median: $0.00).
| Reasoning | No |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 8k ~12 A4 pages of size 12 Arial font |
| Total parameters | 3.4B |
| License | Cc By Nc 4.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Tiny Aya Global | - | 3.4B | 8k | $0.00 | - | 131 |
Frequently Asked Questions
Common questions about Tiny Aya Global
Tiny Aya Global was released on February 17, 2026.
Tiny Aya Global was created by Cohere.
Tiny Aya Global has a time to first answer token of 0.18s (based on Cohere's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.60s).
Tiny Aya Global costs $0.00 per 1M input tokens (very competitive, median: $0.00) and $0.00 per 1M output tokens (very competitive, median: $0.00), based on Cohere's API.
Tiny Aya Global costs $0.00 per 1M input tokens and $0.00 per 1M output tokens (based on Cohere's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.00 per 1M tokens. Pricing may vary by provider. Compare provider pricing
No, Tiny Aya Global is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Tiny Aya Global supports text input.
Tiny Aya Global supports text output.
No, Tiny Aya Global does not support image input. It can only process text.
No, Tiny Aya Global is not multimodal. It only supports text input.
Tiny Aya Global has a context window of 8k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Tiny Aya Global is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Tiny Aya Global has 3.4B parameters.
Tiny Aya Global is released under the Cc By Nc 4.0 license. This license does not allow commercial use. View license
Yes, Tiny Aya Global is available via API through 1 provider. Compare API providers
Tiny Aya Global is available through 1 API provider. Compare providers