OpenAI: gpt-oss-120b API pricing on OpenRouter
- id
- openai/gpt-oss-120b
- openai
- First seen 2026-11-07 13:53 UTC
- Open on openrouter.ai/openai/gpt-oss-120b
RouteThird-partyvia Amazon Bedrock + AkashML + BaseTen + 19 more
Basis: OpenRouter endpoints: Amazon Bedrock (amazon-bedrock): partner; AkashML (akashml): third_party; BaseTen (baseten): third_party; Cerebras (cerebras): third_party; CoreWeave (coreweave): third_party; Crusoe (crusoe): third_party; DeepInfra (deepinfra): third_party; DekaLLM (dekallm): third_party; DigitalOcean (digitalocean): third_party; Google (google-vertex): third_party; Groq (groq): third_party; Mancer 2 (mancer): third_party; Near AI (near-ai): third_party; Nebius (nebius): third_party; Parasail (parasail): third_party; Phala (phala): third_party; PrimeIntellect (primeintellect): third_party; Sail Research (sail-research): third_party; SambaNova (sambanova): third_party; SiliconFlow (siliconflow): third_party; Together (together): third_party; Venice (venice): third_party Archived copy
Current prices
Per million input tokens1
| Variant | USD | Platform’s own wording | Since |
|---|---|---|---|
| Standard | $0.15/M in | prompt: 0.00000015 / token |
Per million output tokens1
| Variant | USD | Platform’s own wording | Since |
|---|---|---|---|
| Standard | $0.6/M out | completion: 0.0000006 / token |
Per million cached input tokens (read)1
| Variant | USD | Platform’s own wording | Since |
|---|---|---|---|
| Standard | $0.075/M cache read | input_cache_read: 0.000000075 / token |
Change log
| When | Model · what it covers | Change |
|---|---|---|
| 2026-11-09 14:03 UTC | Price changedFlaggedCache read | $0.023/M cache read → $0.075/M cache read+226%input_cache_read: 0.000000023 / token → input_cache_read: 0.000000075 / token |
| 2026-11-09 14:03 UTC | Price changedFlagged | $0.094/M out → $0.6/M out+538%completion: 0.000000094 / token → completion: 0.0000006 / token |
| 2026-11-09 14:03 UTC | Price changedFlagged | $0.025/M in → $0.15/M in+500%prompt: 0.000000025 / token → prompt: 0.00000015 / token |
| 2026-11-08 14:03 UTC | Price changedFlaggedCache read | $0.016/M cache read → $0.023/M cache read+44%input_cache_read: 0.000000016 / token → input_cache_read: 0.000000023 / token |
| 2026-11-08 14:03 UTC | Price changedFlagged | $0.067/M out → $0.094/M out+40%completion: 0.000000067 / token → completion: 0.000000094 / token |
| 2026-11-08 14:03 UTC | Price changedFlagged | $0.018/M in → $0.025/M in+39%prompt: 0.000000018 / token → prompt: 0.000000025 / token |
Earlier versions
| Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|
| $0.018/M in | prompt: 0.000000018 / token | 2026-11-07 13:53 UTC → 2026-11-08 14:03 UTC | |
| $0.025/M in | prompt: 0.000000025 / token | 2026-11-08 14:03 UTC → 2026-11-09 14:03 UTC | |
| $0.067/M out | completion: 0.000000067 / token | 2026-11-07 13:53 UTC → 2026-11-08 14:03 UTC | |
| $0.094/M out | completion: 0.000000094 / token | 2026-11-08 14:03 UTC → 2026-11-09 14:03 UTC | |
| Cache read | $0.016/M cache read | input_cache_read: 0.000000016 / token | 2026-11-07 13:53 UTC → 2026-11-08 14:03 UTC |
| Cache read | $0.023/M cache read | input_cache_read: 0.000000023 / token | 2026-11-08 14:03 UTC → 2026-11-09 14:03 UTC |
Where these prices come from
Read from the platform’s public pages and APIs. Every read is archived, so any price here can be checked against what the platform showed at the time.
- openrouter.ai/api/v1/models/openai/gpt-oss-120b/endpointsLast read 28 h ago1 readsArchived copy
- openrouter.ai/api/v1/modelsLast read 2 days ago3 readsArchived copy