Japanese Llama 2 13B Fast Chat is Elyza's language model. A faster 13B-parameter Japanese chat LLM from ELYZA based on Llama 2, optimized for lower-latency conversational inference with Japanese instruction tuning.
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Llama 3.2 11B | 128K | $0.160 | $0.160 | Available | |
| Llama 3.2 11B Instruct | 128K | $0.350 | $0.350 | Deprecated | |
| Llama 3.2 1B Instruct | 128K | $0.027 | $0.080 | Deprecated | |
| Llama 3.2 3B Instruct | 131K | $0.015 | $0.020 | Deprecated | |
| Llama 3.2 90B | 128K | $0.720 | $0.720 | Available | |
| Llama 3.2 90B Instruct | 128K | $2.00 | $2.00 | Deprecated | |
| Llama 3.2 1B | 131K | $0.100 | $0.100 | Available | |
| Llama 3.2 3B | 131K | $0.040 | $0.080 | Available | |
| Llama 3.1 405B Instruct | 131K | $0.120 | $0.300 | Deprecating | |
| Llama 3.1 70B | 128K | $0.600 | $0.600 | Available | |
| Japanese Llama 2 13B Fast Chat | — | — | — | — | Current |