Skip to main content

ALIA 40B

Alia Salamandra 40b is a multilingual Salamandra-family language model focused on European and Iberian languages.

Model card on Hugging Face
Input / output price
$0.30 / $0.60 per 1M
Context
66K tokens
Released
Aug 19, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "alia-40b".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Nextbit256nextbit256/alia-salamandra:40b
$0.30/M$0.60/M

Pricing

USD per 1M tokens on Nextbit256, after gateway discounts.

Input
$0.30 per 1M
Output
$0.60 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.30/MNextbit256

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

21tokens/sacross providers

Faster than 38% of the other 599 models on the gateway

Response latency

Lower is better

3.7sacross providers

Faster than 37% of the other 780 models on the gateway

Benchmarks

3 published scores from 1 source, each linked to where it was published.

Published scores

BenchmarkScore
ARC Easy (5-shot)huggingface.co86.5%
PIQA (5-shot)huggingface.co81.7%
ARC Challenge (5-shot)huggingface.co59.4%

Apps

Use ALIA 40B in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

ALIA 40B FAQ

Short answers, built from the data on this page.

ALIA 40B is a model from Barcelona Supercomputing Center, released on Aug 19, 2026. Alia Salamandra 40b is a multilingual Salamandra-family language model focused on European and Iberian languages.

On the Respan gateway, ALIA 40B costs $0.30 per 1M input tokens and $0.60 per 1M output tokens on Nextbit256, after gateway discounts.

ALIA 40B is served by Nextbit256.

ALIA 40B accepts up to 66K tokens of context.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "alia-40b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

ALIA 40B has 3 published benchmark scores, including ARC Easy (5-shot) 86.5%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.