Open Llama instruction model for multilingual chat, reasoning, and coding
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Agentic Index | agentic | 0.3 | — | mirror | openrouter | Jul 23, 2026 |
| AA Coding Index | coding | 11.9 | — | mirror | openrouter | Jul 23, 2026 |
| AA Intelligence Index | intelligence | 9.4 | — | mirror | openrouter | Jul 23, 2026 |
Includes index data from Artificial Analysis.
Providers
Live operational stats per hosting endpoint, via OpenRouter.
| Provider | Quant | Context | $/1M in · out | Uptime 24h | Latency | Throughput |
|---|---|---|---|---|---|---|
| AkashML | fp8 | 131K | $0.13 · $0.4 | 97.94% | — | — |
| Cloudflare | fp8 | 24K | $0.293 · $2.25 | 97.79% | — | — |
| CoreWeave | fp16 | 128K | $0.71 · $0.71 | 99.77% | — | — |
| Crusoe | bf16 | 131K | $0.25 · $0.75 | 99.90% | — | — |
| DeepInfra | fp8 | 131K | $0.1 · $0.32 | 95.64% | — | — |
| — | 128K | $0.72 · $0.72 | 99.75% | — | — | |
| — | 128K | $0.72 · $0.72 | 99.89% | — | — | |
| Groq | — | 131K | $0.59 · $0.79 | 99.84% | — | — |
| Nebius | fp8 | 131K | $0.13 · $0.4 | 78.67% | — | — |
| Novita | bf16 | 6K | $0.135 · $0.4 | 90.36% | — | — |
| Parasail | fp8 | 131K | $0.22 · $0.5 | 96.73% | — | — |
| SambaNova | bf16 | 16K | $0.45 · $0.9 | 96.74% | — | — |
| Together | fp8 | 131K | $1.04 · $1.04 | 97.29% | — | — |