impulse

gpt-oss-120b-ultra

Frontier lab
API id gpt-oss-120b-Ultra
Input / 1M
$0.20
at DeepInfra
Output / 1M
$0.95
at DeepInfra
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.20$0.95

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$131
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$130
  • Coding agent1,000 requests a day, 40K in / 2K out$297
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$708
Use your own numbers

Where to run it

1 host serve gpt-oss-120b-ultra. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
gpt-oss-120b-Ultra
$0.20 / $0.95

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 DeepInfra.

Smaller OpenAI models

  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    48% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    32% less

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    48% less

Open-weight picks

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/gpt-oss-120b-Ultra",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does gpt-oss-120b-ultra cost?

On DeepInfra, gpt-oss-120b-ultra costs $0.20 per million input tokens and $0.95 per million output tokens.

Which APIs offer gpt-oss-120b-ultra?

gpt-oss-120b-ultra runs on 1 API: DeepInfra.

What is gpt-oss-120b-ultra's context window?

131K tokens, with up to 131K tokens in one reply.

Is gpt-oss-120b-ultra being retired?

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

What are cheaper alternatives to gpt-oss-120b-ultra?

Models that cost less and keep most of what it can do: GPT-6 Luna on OpenAI (48% less), Claude Haiku 5.5 on Anthropic (48% less) and Qwen3.5 397B A17B on AIHubMix (5% less). Savings are on a mix of 3 input tokens to 1 output token.

What is gpt-oss-120b-ultra's API model id?

Use gpt-oss-120b-Ultra with DeepInfra.

Sources

Raw catalog entry for gpt-oss-120b-Ultra on DeepInfra
{
  "max_output_tokens": 131072,
  "max_input_tokens": 131072,
  "input_cost_per_token": 2e-7,
  "output_cost_per_token": 9.5e-7,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_tool_choice": true,
  "supports_response_schema": true,
  "supports_reasoning": true,
  "supports_vision": false,
  "source": "https://deepinfra.com/pricing"
}