impulse

Jamba Mini 1.6

Open weights
API id jamba-mini-1.6
Input / 1M
$0.20
at AI21 Studio
Output / 1M
$0.40
at AI21 Studio
Context window
256K
tokens
Max output
256K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at AI21 Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.20$0.40

What it costs a month

At AI21 Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$90.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$110
  • Coding agent1,000 requests a day, 40K in / 2K out$264
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$576
Use your own numbers

Where to run it

1 host serve Jamba Mini 1.6. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
jamba-mini-1.6
$0.20 / $0.40

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Jamba Open Model License
Runtimes: vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than AI21 Studio.

Smaller AI21 Labs models

No cheaper AI21 Labs model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    20% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    20% less

Open-weight picks

  • Qwen3 Coder Next
    Alibaba Qwen · on AIHubMix
    $0.137 / $0.548
    Has every key capability
    4% less
  • Ministral 14B 2512
    Mistral AI · on Mistral AI
    $0.20 / $0.20
    Has every key capability
    20% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    28% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    36% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedJamba Mini 1.7Latest$0.20 / $0.40
  2. UndatedJamba Mini 1.6This page$0.20 / $0.40
  3. UndatedJamba 1.5 Mini$0.20 / $0.40

Call it

Using AI21 Studio's API.

Python
from litellm import completion

response = completion(
    model="ai21/jamba-mini-1.6",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Jamba Mini 1.6 cost?

On AI21 Studio, Jamba Mini 1.6 costs $0.20 per million input tokens and $0.40 per million output tokens.

Which APIs offer Jamba Mini 1.6?

Jamba Mini 1.6 runs on 1 API: AI21 Studio.

What is Jamba Mini 1.6's context window?

256K tokens, with up to 256K tokens in one reply.

Is Jamba Mini 1.6 being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Jamba Mini 1.6?

Yes. Jamba Mini 1.7 is the newest model in this line.

What are cheaper alternatives to Jamba Mini 1.6?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (20% less), GPT-6 Luna on OpenAI (20% less) and Qwen3 Coder Next on AIHubMix (4% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Jamba Mini 1.6's API model id?

Use jamba-mini-1.6 with AI21 Studio.

Sources

Raw catalog entry for jamba-mini-1.6 on AI21 Studio
{
  "input_cost_per_token": 2e-7,
  "litellm_provider": "ai21",
  "max_input_tokens": 256000,
  "max_output_tokens": 256000,
  "mode": "chat",
  "output_cost_per_token": 4e-7,
  "supports_tool_choice": true
}