impulse

Babbage 002

Frontier lab
API id babbage-002
Input / 1M
$0.40
at OpenAI
Output / 1M
$0.40
at OpenAI
Context window
16K
tokens
Max output
4K
tokens per reply
Hosts
1
2 listings
Released
-
date not published

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.40$0.40
Batch
50% off
$0.20$0.20

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$150
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$206
  • Coding agent1,000 requests a day, 40K in / 2K out$504
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$528
Use your own numbers

Where to run it

1 host serve Babbage 002. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
babbage-002
$0.40 / $0.40
Show 1 more listings: regions, snapshots and variants
OpenAI
fine-tuning
ft:babbage-002
$1.60 / $1.60

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

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 OpenAI.

Smaller OpenAI models

  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    50% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    34% less

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    50% less

Open-weight picks

  • MiniMax M3
    MiniMax · on EmpirioLabs AI
    $0.225 / $0.90
    Has every key capability
    2% less
  • Qwen3.5 397B A17B
    Alibaba Qwen · on AIHubMix
    $0.164 / $0.986
    Has every key capability
    8% less
  • Muse Glimmer 30B
    Meta · on EmpirioLabs AI
    $0.20 / $0.80
    Has every key capability
    13% less
  • Mistral Small 2603
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    34% less

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="babbage-002", input="Hello")
print(response.output_text)

Quick answers

How much does Babbage 002 cost?

On OpenAI, Babbage 002 costs $0.40 per million input tokens and $0.40 per million output tokens.

Which APIs offer Babbage 002?

Babbage 002 runs on 1 API: OpenAI.

What is Babbage 002's context window?

16K tokens, with up to 4K tokens in one reply.

Is Babbage 002 being retired?

It has been retired: OpenAI retired it on 28 Sep 2026.

What are cheaper alternatives to Babbage 002?

Models that cost less and keep most of what it can do: GPT-6 Luna on OpenAI (50% less), Claude Haiku 5.5 on Anthropic (50% less) and MiniMax M3 on EmpirioLabs AI (2% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Babbage 002's API model id?

Use babbage-002 with OpenAI.

Sources

Raw catalog entry for babbage-002 on OpenAI
{
  "deprecation_date": "2026-09-28",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-5.6-terra",
  "input_cost_per_token": 4e-7,
  "input_cost_per_token_batches": 2e-7,
  "litellm_provider": "text-completion-openai",
  "max_input_tokens": 16384,
  "max_output_tokens": 4096,
  "mode": "completion",
  "output_cost_per_token": 4e-7,
  "output_cost_per_token_batches": 2e-7,
  "source": "https://developers.openai.com/api/docs/pricing"
}