Magnum v4 72B
Anthracite · Open weights · Released Oct 22, 2024 · anthracite-org/magnum-v4-72b
Best $2.50 in / $5.00 out via Mancer 2 · fp8
33K contextStructured outputPrompt cachingOpen weights
Available from 1 providerUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 19 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $2.50 | $5.00 | $2.50 | 33K | fp8 | 3.9s | 19 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 19 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$2.50 / $5.00
per MTok in / out
CACHE READ $2.50
About
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of Qwen2.5 72B.
Specifications
Context window32,768
Max output4,096
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedOct 22, 2024
Knowledge cutoff2024-06-30
TokenizerQwen
WeightsHugging Face ↗
Open weights
safetensors
Embed badge
[](https://modelindex.ai/models/anthracite-org/magnum-v4-72b)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks19 days ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.