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=2026-09-16 03:02Z
meta/llama-3.3-70b-instruct
Vendor: meta. Tracked by 2 of 5 sources.
What each source reports
| Source | ID | Context | Max out | In $/Mtok | Out $/Mtok | Sunset |
|---|---|---|---|---|---|---|
| litellm | azure_ai/Llama-3.3-70B-Instruct | 128,000 | 2,048 | $0.71 | $0.71 | — |
| openrouter | meta-llama/llama-3.3-70b-instruct | 131,072 | 16,384 | $0.1 | $0.32 | — |
Change history
| Severity | Change | What | Detected |
|---|---|---|---|
| low | modified | nebius/meta-llama/Llama-3.3-70B-Instruct: context_tokens raised 128,000 to 131,072 | 2026-09-06 |
| low | modified | nebius/meta-llama/Llama-3.3-70B-Instruct: max_output_tokens raised 128,000 to 131,072 | 2026-09-06 |
| low | added | new model openrouter/meta-llama/llama-3.3-70b-instruct (131,072 ctx) | 2026-09-06 |
| high | modified | meta-llama/llama-3.3-70b-instruct: max_output_tokens cut 115,200 to 16,384 | 2026-09-03 |
| info | repriced | meta-llama/llama-3.3-70b-instruct: input_price_per_mtok $0.71/Mtok to $0.10/Mtok | 2026-09-03 |
| info | repriced | meta-llama/llama-3.3-70b-instruct: output_price_per_mtok $0.71/Mtok to $0.32/Mtok | 2026-09-03 |
| info | repriced | meta-llama/llama-3.3-70b-instruct: cache_read_price_per_mtok $0.71/Mtok to n/a | 2026-09-03 |
| high | modified | novita/meta-llama/llama-3.3-70b-instruct: context_tokens cut 131,072 to 12,288 | 2026-08-28 |
| high | modified | novita/meta-llama/llama-3.3-70b-instruct: max_output_tokens cut 120,000 to 12,288 | 2026-08-28 |
| low | modified | novita/meta-llama/llama-3.3-70b-instruct: capabilities gained response_schema | 2026-08-28 |
| info | repriced | wandb/meta-llama/Llama-3.3-70B-Instruct: input_price_per_mtok $71,000.00/Mtok to $0.71/Mtok | 2026-08-28 |
| info | repriced | wandb/meta-llama/Llama-3.3-70B-Instruct: output_price_per_mtok $71,000.00/Mtok to $0.71/Mtok | 2026-08-28 |
| medium | repriced | meta-llama/llama-3.3-70b-instruct: input_price_per_mtok $0.10/Mtok to $0.71/Mtok | 2026-08-26 |
| medium | repriced | meta-llama/llama-3.3-70b-instruct: output_price_per_mtok $0.32/Mtok to $0.71/Mtok | 2026-08-26 |
| low | modified | meta-llama/llama-3.3-70b-instruct: max_output_tokens raised 16,384 to 115,200 | 2026-08-26 |
| info | repriced | meta-llama/llama-3.3-70b-instruct: cache_read_price_per_mtok n/a to $0.71/Mtok | 2026-08-26 |
| high | modified | meta-llama/llama-3.3-70b-instruct: max_output_tokens cut 128,000 to 16,384 | 2026-08-04 |
| info | repriced | meta-llama/llama-3.3-70b-instruct: input_price_per_mtok $0.13/Mtok to $0.10/Mtok | 2026-08-04 |
| info | repriced | meta-llama/llama-3.3-70b-instruct: output_price_per_mtok $0.40/Mtok to $0.32/Mtok | 2026-08-04 |
| low | added | new model scaleway/meta/llama-3.3-70b-instruct (128,000 ctx) | 2026-06-12 |