Headline USD token rates per 1M; other currencies and units remain native. Original rates are below. Unknown means no unambiguous headline; inspect all rates and conditions below.
Raw SHA-256: 9722d1130261fe9667b226c4817976e42d0087d11cf1eb7b948cecdeb7988f25; original collector novita-model-catalog-1. Pinned parse-failure recovery preserves original dates; no new acquisition.
USD/scale interpretation reviewed against Novita official pricing and its MiniMax M3 pricing explanation; exact original/decimal/integer values retained privately.
Three curated hosted listings only. No verified checkpoint/developer/license/weight-access link; availability remains unknown because numeric status semantics are undocumented.
Raw SHA-256: acc4f454b718542639c70d944823c178ff10a82f34a7fc196c93790aa91b8803; collector novita-model-catalog-1; daily collection independently replayed with zero source requests.
USD/scale interpretation reviewed against Novita official pricing and its MiniMax M3 pricing explanation (#102); exact original/decimal/integer values retained privately.
Curated hosted listings priced here: 2. No verified checkpoint/developer/license/weight-access link; availability remains unknown because numeric status semantics are undocumented.
Llama 3.3 70B Instruct
Service ID: meta-llama/llama-3.3-70b-instruct · Context window: Unknown · Listing status: active
Raw SHA-256: 9722d1130261fe9667b226c4817976e42d0087d11cf1eb7b948cecdeb7988f25; original collector novita-model-catalog-1. Pinned parse-failure recovery preserves original dates; no new acquisition.
USD/scale interpretation reviewed against Novita official pricing and its MiniMax M3 pricing explanation; exact original/decimal/integer values retained privately.
Three curated hosted listings only. No verified checkpoint/developer/license/weight-access link; availability remains unknown because numeric status semantics are undocumented.
Raw SHA-256: acc4f454b718542639c70d944823c178ff10a82f34a7fc196c93790aa91b8803; collector novita-model-catalog-1; daily collection independently replayed with zero source requests.
USD/scale interpretation reviewed against Novita official pricing and its MiniMax M3 pricing explanation (#102); exact original/decimal/integer values retained privately.
Curated hosted listings priced here: 2. No verified checkpoint/developer/license/weight-access link; availability remains unknown because numeric status semantics are undocumented.
MiniMax M2
Service ID: minimax/minimax-m2 · Context window: Unknown · Listing status: no longer listed
No longer listed by provider · last observed price 2026-09-27
Raw SHA-256: 9722d1130261fe9667b226c4817976e42d0087d11cf1eb7b948cecdeb7988f25; original collector novita-model-catalog-1. Pinned parse-failure recovery preserves original dates; no new acquisition.
USD/scale interpretation reviewed against Novita official pricing and its MiniMax M3 pricing explanation; exact original/decimal/integer values retained privately.
Three curated hosted listings only. No verified checkpoint/developer/license/weight-access link; availability remains unknown because numeric status semantics are undocumented.
Novita's official model-list API returned 95 models and no minimax/minimax-m2 entry. Its MiniMax listings are minimax/minimax-m2.5, minimax/minimax-m2.7, minimax/minimax-m2.7-highspeed, minimax/minimax-m3 and minimaxai/minimax-m1-80k. Llama 3.3 70B Instruct and GLM 5 are still listed at their published prices.
Raw response SHA-256 acc4f454b718542639c70d944823c178ff10a82f34a7fc196c93790aa91b8803 (retrieved 2026-10-14T01:44:28Z).
The model was listed and priced in the collection behind the published prices (pricing evidence retrieved 2026-09-27T06:32:08.821Z). The prices shown are the last observed listed prices (2026-09-27), not current prices.
No host deprecation notice was reviewed; this record rests only on the model-list snapshot. Availability stays unknown: absence from the model list means Novita no longer offers it there, but whether requests to the old model ID still succeed was not tested. No retirement date is recorded, because the listing ended at an unknown time between 2026-09-27 and 2026-10-14.
About capability scores (Epoch AI)
Capability scores: Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource], epoch.ai/benchmarks. Accessed 2026-10-14. Licensed CC BY 4.0; values here are rounded to one decimal place and grouped into bands.
The Epoch Capabilities Index (ECI) combines many benchmarks on a scale where Claude 3.5 Sonnet is 130 and GPT-5 is 150. Bands, on the displayed one-decimal score: Frontier 160+, Strong 150–159.9, Capable 140–149.9, Entry below 140. Each score has a 90% range; a range that crosses a band boundary is flagged. Models are not ranked: neighbouring scores often overlap.
A benchmark is not your workload. Epoch's scores mostly reflect runs at the highest reasoning effort, which use more output tokens than default settings. Scores are dated and can shift between Epoch releases. A score belongs to the developer's model; a host listing shows the same model's score, but hosts may serve different versions or quantizations.
How headline rates are chosen
Headline rates use the directory's shared rule: the rate a buyer meets by default, chosen by billing, tier and context dimensions and never by price. Context caps, the bracket starting at zero and short-context variants are labeled; unverified availability is flagged and is not a service guarantee. Batch, off-peak and other variants remain in the details; ambiguous headlines stay unknown.
No currency conversion is performed. Missing cache prices are unknown, not zero. Equal units do not establish equivalent models or service conditions. See the methodology and source register.