Alia Salamandra 40B
Alia Salamandra 40b is a multilingual Salamandra-family language model focused on European and Iberian languages.
- Tool Use
# Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
- Context window
- 66K tokens
- Input from
- $0.30/M
- Output from
- $0.60/M
- Providers
- 1
- Released
- Aug 19, 2026
Providers
One provider serves this model through the Respan gateway. Copy a model ID to call that route directly.
| Provider | Input | Output |
|---|---|---|
Nextbit256 nextbit256/alia-salamandra:40b | $0.30/M | $0.60/M |
Pricing
USD per 1M tokens on Nextbit256, after gateway discounts.
- Input
- $0.30/M
- Output
- $0.60/M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages per provider from requests through the Respan gateway, best first.
Output speed
Higher is better26tokens/son Nextbit256
- Nextbit25626 tok/s
Response latency
Lower is better2.5son Nextbit256
- Nextbit2562.5 s
Apps
Use Alia Salamandra 40B in the tools you already run. Each guide points the app at the Respan gateway, then you pick this model.
Claude CodeAnthropic's coding agent for the terminal
OpenCodeOpen-source terminal coding agent
Kilo CodeOpen-source coding agent for your editor
PiMinimal terminal coding agent
Codex CLIOpenAI's coding agent for the terminal
CursorAI code editor
LangChainFramework for LLM apps and agents
LlamaIndexAgents and RAG over your data
CrewAITeams of collaborating agents
Pydantic AIType-safe Python agent framework
Vercel AI SDKTypeScript toolkit for AI apps
Anthropic SDKAnthropic's client for Python and TS
Google Gen AIGoogle's SDK for Gemini models
LiteLLMOne Python interface for every provider
InstructorStructured outputs from LLMs
Setup guides for more apps are in the integration docs.
Alia Salamandra 40B FAQ
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
