OctoML (Deprecated)
Researched 174d agoInference PlatformTier deprecatedOctoML
OctoML (Deprecated) offers 7 tracked models (7 with output token pricing). This catalog covers general LLM work; open any model detail page for benchmarks, batch tiers, and migration prompts.
Covers 0 workload areas across 7 tracked models; last verified 2026-05-11.
Use it for
- Teams comparing token and batch pricing across this provider's models
Do not use it for
- Final benchmark picks without opening the relevant model detail page
Tracked models
7
Models available through this provider
Priced output routes
7
Models with output token pricing tracked
Cheapest output
Unknown
Output pricing not yet tracked
Batch-ready models
0
No batch pricing tracked
Latest model release
Unknown
Release date of the newest tracked model
Freshness
2026-05-11
Researched 174d ago
Information
OctoML is an optimized inference platform for foundation models, offering serverless and dedicated deployment with performance tuning for production AI workloads.
Links
WebsiteWhere this host wins
Not enough capability or benchmark coverage yet to call strengths for this provider.
Getting started
Platform Overview
Optimized inference platform for foundation models
Available Models(7)
View all →All models available as Serverless
| Model | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OctoML Gemma-2B-it | $0.1 | $0.15 |
| OctoML Gemma-7B-it | $0.15 | $0.2 |
| CodeLlama 70B Instruct | $0.4 | $0.6 |
| Nous Hermes 2 Mixtral 8x7B | $0.4 | $0.6 |
| Mistral 7B Instruct v0.2 | $0.15 | $0.2 |
| Mixtral 8x7B Instruct v0.1 | $0.4 | $0.6 |
| Llama 2 70B Chat | $0.4 | $0.6 |