NOT DEPRECATED
Listed by litellm, openrouter. No retirement date announced. Neither the provider's API nor its documentation has been checked for this model. Sources disagree on: context_tokens, input_price_per_mtok, max_output_tokens, output_price_per_mtok.
state=alive sunset=none days_remaining=n/a severity=low sources=litellm,openrouter evidence_tier=catalog confirmed_by_endpoint=false documented_by_provider=false replacement=none corroborated=yes divergent_fields=context_tokens,input_price_per_mtok,max_output_tokens,output_price_per_mtok checked=2026-09-30 15:40Z
openai/gpt-oss-120b
Vendor: openai. Tracked by 2 of 5 sources.
What each source reports
| Source | ID | Context | Max out | In $/Mtok | Out $/Mtok | Sunset |
|---|---|---|---|---|---|---|
| litellm | baseten/openai/gpt-oss-120b | 128,072 | 128,072 | $0.1 | $0.5 | — |
| openrouter | openai/gpt-oss-120b | 131,072 | 117,964 | $0.037 | $0.17 | — |
Change history
| Severity | Change | What | Detected |
|---|---|---|---|
| low | modified | openai/gpt-oss-120b: max_output_tokens raised 65,536 to 117,964 | 2026-09-29 |
| info | repriced | openai/gpt-oss-120b: input_price_per_mtok $0.15/Mtok to $0.04/Mtok | 2026-09-29 |
| info | repriced | openai/gpt-oss-120b: output_price_per_mtok $0.60/Mtok to $0.17/Mtok | 2026-09-29 |
| info | repriced | openai/gpt-oss-120b: cache_read_price_per_mtok $0.07/Mtok to n/a | 2026-09-29 |
| low | modified | baseten/openai/gpt-oss-120b: capabilities gained function_calling, prompt_caching, reasoning, response_schema, tool_choice | 2026-09-22 |
| info | repriced | baseten/openai/gpt-oss-120b: cache_read_price_per_mtok n/a to $0.10/Mtok | 2026-09-22 |
| high | modified | openrouter/openai/gpt-oss-120b: max_output_tokens cut 117,964 to 65,536 | 2026-09-19 |
| low | modified | openrouter/openai/gpt-oss-120b: capabilities gained prompt_caching | 2026-09-19 |
| medium | repriced | openrouter/openai/gpt-oss-120b: input_price_per_mtok $0.04/Mtok to $0.15/Mtok | 2026-09-18 |
| medium | repriced | openrouter/openai/gpt-oss-120b: output_price_per_mtok $0.17/Mtok to $0.60/Mtok | 2026-09-18 |
| low | modified | openrouter/openai/gpt-oss-120b: max_output_tokens raised 32,768 to 117,964 | 2026-09-18 |
| info | repriced | openrouter/openai/gpt-oss-120b: cache_read_price_per_mtok n/a to $0.07/Mtok | 2026-09-18 |
| high | modified | openai/gpt-oss-120b: max_output_tokens cut 117,964 to 65,536 | 2026-09-18 |
| medium | repriced | openai/gpt-oss-120b: input_price_per_mtok $0.04/Mtok to $0.15/Mtok | 2026-09-18 |
| medium | repriced | openai/gpt-oss-120b: output_price_per_mtok $0.17/Mtok to $0.60/Mtok | 2026-09-18 |
| info | repriced | openai/gpt-oss-120b: cache_read_price_per_mtok n/a to $0.07/Mtok | 2026-09-18 |
| high | modified | novita/openai/gpt-oss-120b: capabilities lost vision | 2026-09-06 |
| low | added | new model nebius/openai/gpt-oss-120b (131,072 ctx) | 2026-09-06 |
| low | modified | watsonx/openai/gpt-oss-120b: context_tokens raised 8,192 to 131,072 | 2026-09-06 |
| low | modified | watsonx/openai/gpt-oss-120b: max_output_tokens raised 8,192 to 131,072 | 2026-09-06 |
| low | repriced | watsonx/openai/gpt-oss-120b: input_price_per_mtok $0.15/Mtok to $0.16/Mtok | 2026-09-06 |
| low | repriced | watsonx/openai/gpt-oss-120b: output_price_per_mtok $0.60/Mtok to $0.64/Mtok | 2026-09-06 |
| info | repriced | openrouter/openai/gpt-oss-120b: input_price_per_mtok $0.18/Mtok to $0.04/Mtok | 2026-09-06 |
| info | repriced | openrouter/openai/gpt-oss-120b: output_price_per_mtok $0.80/Mtok to $0.17/Mtok | 2026-09-06 |
| info | repriced | deepinfra/openai/gpt-oss-120b: input_price_per_mtok $0.05/Mtok to $0.04/Mtok | 2026-08-28 |
| info | repriced | deepinfra/openai/gpt-oss-120b: output_price_per_mtok $0.45/Mtok to $0.17/Mtok | 2026-08-28 |
| info | modified | [source artifact — 7 providers changed identically on the same day] openai/gpt-oss-120b: max_output_tokens cut 131,072 to 117,964 | 2026-08-25 |
| low | repriced | openai/gpt-oss-120b: input_price_per_mtok $0.03/Mtok to $0.04/Mtok | 2026-08-22 |
| info | repriced | openai/gpt-oss-120b: cache_read_price_per_mtok $0.03/Mtok to n/a | 2026-08-22 |
| low | modified | groq/openai/gpt-oss-120b: max_output_tokens raised 32,766 to 65,536 | 2026-08-13 |
| info | repriced | openai/gpt-oss-120b: input_price_per_mtok $0.04/Mtok to $0.03/Mtok | 2026-08-12 |
| info | repriced | openai/gpt-oss-120b: cache_read_price_per_mtok n/a to $0.03/Mtok | 2026-08-12 |
| info | repriced | sambanova/gpt-oss-120b: input_price_per_mtok $3.00/Mtok to $0.22/Mtok | 2026-06-26 |
| info | repriced | sambanova/gpt-oss-120b: output_price_per_mtok $4.50/Mtok to $0.59/Mtok | 2026-06-26 |
| low | added | new model cloudflare/@cf/openai/gpt-oss-120b (128,000 ctx) | 2026-06-23 |
| high | modified | fireworks_ai/accounts/fireworks/models/gpt-oss-120b: max_output_tokens cut 131,072 to 32,768 | 2026-06-18 |
| low | added | new model fireworks_ai/gpt-oss-120b (131,072 ctx) | 2026-06-18 |
| info | repriced | fireworks_ai/accounts/fireworks/models/gpt-oss-120b: cache_read_price_per_mtok n/a to $0.01/Mtok | 2026-06-18 |
| low | added | new model scaleway/openai/gpt-oss-120b (128,000 ctx) | 2026-06-12 |