Jamba Large 1.7
AI21 LabsReleased Aug 8, 2025
Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...
- Context window
- 256K tokens
- Max output
- 4K tokens
- Input
- text
- Output
- text
- Tokenizer
- Other
- Knowledge cutoff
- Aug 31, 2024
- Released
- Aug 8, 2025
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $2.00 | $0.060 | $2.06 |
| Output | $8.00 | $0.240 | $8.24 |
Supported parameters
- max_tokens
- response_format
- stop
- temperature
- tool_choice
- tools
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model ai21/jamba-large-1.7.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ai21/jamba-large-1.7",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="ai21/jamba-large-1.7",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "ai21/jamba-large-1.7",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does Jamba Large 1.7 cost via API?
- Through OpenKey, Jamba Large 1.7 costs $2.06 per 1M input tokens and $8.24 per 1M output tokens. That is the provider price ($2.00 / $8.00) plus a flat 3% fee — nothing else.
- What is Jamba Large 1.7's context window?
- Jamba Large 1.7 accepts up to 256K tokens of context and returns up to 4K tokens per request.
- Is Jamba Large 1.7 OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "ai21/jamba-large-1.7" using any OpenAI SDK — only the base URL and API key change.
- What inputs does Jamba Large 1.7 support?
- Jamba Large 1.7 accepts text input and produces text output. Its knowledge cutoff is Aug 31, 2024.