impulse

Fw Gpt Oss 120B

API id FW-GPT-OSS-120B
Input / 1M
$0.165
at Azure AI Foundry
Output / 1M
$0.66
at Azure AI Foundry
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Azure AI Foundry, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.165$0.66
Cached input
50% off input
$0.082

What it costs a month

At Azure AI Foundry list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$91.53
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$83.04
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$168
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$554
Use your own numbers

Where to run it

1 host serve Fw Gpt Oss 120B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
FW-GPT-OSS-120B
$0.165 / $0.66
Retires 1 Jul 2027

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
Features
Parallel tool callsPrompt caching

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 Azure AI Foundry.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    31% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    31% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    9% less

Open-weight picks

  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    13% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    38% less
  • DeepSeek V4.1 Flash
    DeepSeek · on Sail
    $0.09 / $0.30
    Has every key capability
    51% less
  • MiMo V2.6 Flash
    Xiaomi · on GMI Cloud
    $0.112 / $0.224
    Has every key capability
    52% less

Call it

Using Azure AI Foundry's API.

Python
from litellm import completion

response = completion(
    model="azure_ai/FW-GPT-OSS-120B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Fw Gpt Oss 120B cost?

On Azure AI Foundry, Fw Gpt Oss 120B costs $0.165 per million input tokens and $0.66 per million output tokens. Cached input costs $0.082 per million tokens.

Which APIs offer Fw Gpt Oss 120B?

Fw Gpt Oss 120B runs on 1 API: Azure AI Foundry.

What is Fw Gpt Oss 120B's context window?

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

Is Fw Gpt Oss 120B being retired?

Azure AI Foundry retires it on 1 Jul 2027. No API serves it after that.

What are cheaper alternatives to Fw Gpt Oss 120B?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (31% less), GPT-6 Luna on OpenAI (31% less) and Qwen3.8 27B on EmpirioLabs AI (13% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Fw Gpt Oss 120B's API model id?

Use FW-GPT-OSS-120B with Azure AI Foundry.

Sources

Raw catalog entry for FW-GPT-OSS-120B on Azure AI Foundry
{
  "deprecation_date": "2027-07-01",
  "cache_read_input_token_cost": 8.2e-8,
  "input_cost_per_token": 1.65e-7,
  "litellm_provider": "azure_ai",
  "max_input_tokens": 131072,
  "max_output_tokens": 131072,
  "mode": "chat",
  "output_cost_per_token": 6.6e-7,
  "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
  "supports_function_calling": true,
  "supports_parallel_function_calling": true,
  "supports_pdf_input": false,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true
}