gpt-oss-120b APIOPEN WEIGHTS131K context

Pricing & specs mirror our live pricing as of July 2026 (pay-as-you-go).

What is gpt-oss-120b?

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

gpt-oss-120b on the release timeline

gpt-oss-120b pricing

Pay-as-you-go on DataLLM Lab — these are our live list prices (identical to the pricing page):

On output price, gpt-oss-120b is cheaper than 92% of the 309 models in the catalog. It is served by 20 providers; the best combined rate at our last snapshot was ≈ $0.03 / $0.15 per 1M via Mara, with upstream quantizations bf16, fp16, fp4, fp8.

What gpt-oss-120b costs per month

Cost = input price × input volume + output price × output volume. The same five workloads run on every model page, so any two compare directly.

gpt-oss-120b vs alternatives

Specs

How to call gpt-oss-120b

Copyfrom openai import OpenAI
client = OpenAI(base_url="https://api.datallmlab.com/v1", api_key="YOUR_DATALLM_LAB_KEY")
resp = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "Hello"}],
    # supports tools=[...] and tool_choice
)
print(resp.choices[0].message.content)

Copycurl https://api.datallmlab.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-oss-120b","messages":[{"role":"user","content":"Hello"}]}'

Copyimport OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.datallmlab.com/v1", apiKey: process.env.DATALLM_KEY });
const r = await client.chat.completions.create({
  model: "openai/gpt-oss-120b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);

The same key routes gpt-oss-120b and 300+ other models — switch models by changing one string. How OpenAI-compatible APIs work.

Prompting tips for gpt-oss-120b

• State the goal, not every step. gpt-oss-120b reasons internally — give it the objective, constraints and success criteria and let it plan the approach; over-scripting each step tends to lower quality. Turn effort up for hard problems.
• Give it real tools. Pass a tools=[...] schema instead of asking it to "pretend" — let gpt-oss-120b emit tool calls, execute them, and feed results back for the next turn.
• Constrain JSON with a schema. Use response_format / structured outputs rather than "reply in JSON" to get valid, parseable objects every time.
• Cheap enough to batch. Great for high-volume classification, extraction and drafting — template the prompt, batch requests, and validate outputs programmatically.
• Use the system role for rules. Put persistent instructions in the system message and keep user turns task-specific; pair with structured outputs for reliable automation.

Tips are derived from gpt-oss-120b's actual capabilities — context window, tool & JSON support, modality and price tier — not generic advice.

Open-source tools for gpt-oss-120b

Popular open-source projects for running and building with gpt-oss-120b — star counts pulled from GitHub (July 2026).

Listed by GitHub stars; inclusion is by ecosystem relevance (inference engines, agent frameworks and SDKs), not affiliation. Stars change — see each repo for current numbers.

Migrating to gpt-oss-120b

Coming from OpenAI or another gateway? On an OpenAI-compatible setup the only changes are base_url → https://api.datallmlab.com/v1 and model → openai/gpt-oss-120b. Messages, streaming, tool calls and the rest of your code stay the same. Routing & failover guide.

Self-host or use the API?

gpt-oss-120b ships open weights (openai/gpt-oss-120b, ~4.1M downloads and 4.9K likes in the last 30 days), with community quantizations (bf16, fp16, fp4, fp8) for smaller GPUs, so you can run it yourself. Most teams still use the API: no GPU to provision or keep warm, no inference ops, and instant access across 20 providers with automatic failover. Self-host when data residency or fixed per-token economics matter most.

Rate limits & reliability

Rate limits here are the DataLLM Lab gateway's, not the upstream vendor's. On 429 (rate limited) or 503 (provider busy), retry with exponential backoff; because gpt-oss-120b is served by 20 providers, requests can fail over to a healthy one automatically. See the error-code guide and failover setup.

Related reading

Frequently asked questions