Jamba 1.5 Large
Jamba 1.5 Large is a language model with 398B parameters from AI21 Labs. It is currently free at 1 provider with up to 256K tokens of context. Its weights are open, so it can also run locally.
- Developer
- AI21 Labs
- Parameters
- 398B / 94B active
- Context
- 256K tokens
- Type
- Text
- License
- Open weights
Where to use Jamba 1.5 Large for free
Each row is a separate free endpoint with its own limits.
| Provider | Context | Limit | Card | |
|---|---|---|---|---|
NVIDIA Build ai21labs/jamba-1.5-large-instruct |
— | Free serverless inference for development; limits and model availability may change. | No | Open |
Quick start
curl https://integrate.api.nvidia.com/v1/chat/completions \
-H "Authorization: Bearer $NVIDIA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ai21labs/jamba-1.5-large-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(
base_url="https://integrate.api.nvidia.com/v1",
api_key="YOUR_NVIDIA_API_KEY",
)
reply = client.chat.completions.create(
model="ai21labs/jamba-1.5-large-instruct",
messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://integrate.api.nvidia.com/v1",
apiKey: process.env.NVIDIA_API_KEY,
});
const reply = await client.chat.completions.create({
model: "ai21labs/jamba-1.5-large-instruct",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(reply.choices[0].message.content);Example for NVIDIA Build. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.
Benchmarks
Source: Artificial Analysis · Jamba 1.5 Large
Similar free models
FAQ
Is Jamba 1.5 Large free?
Yes. As of November 2, 2026, Jamba 1.5 Large is free at NVIDIA Build. Each provider has its own limits — see the table above.
What is the context window of Jamba 1.5 Large?
The largest context among free routes is 256,000 tokens. Some providers cap it lower.
How do I call Jamba 1.5 Large via API?
Use any OpenAI-compatible client with base URL https://integrate.api.nvidia.com/v1, model ID ai21labs/jamba-1.5-large-instruct, and a NVIDIA Build key.
How good is Jamba 1.5 Large?
Artificial Analysis Intelligence Index: 6.0, GPQA Diamond: 43%. For comparison, the strongest free model in the catalog right now is GLM 5.3 Flash.
Is Jamba 1.5 Large open-weight?
Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.