OctoML (Deprecated) Models — Pricing & Benchmarks
7 models available · OctoML
Last refreshed 2026-06-01. Next refresh: weekly.
OctoML (Deprecated) hosts 7 AI models in this catalog. The lowest listed input price is OctoML Gemma-2B-it at $0.1/1M input tokens. LLM Reference compares these models across all 97 providers.
| Model | Input (per 1M) | Output (per 1M) | Context | |
|---|---|---|---|---|
| OctoML Gemma-2B-it | $0.1 | $0.15 | 8k | |
| Mistral 7B Instruct v0.2 | $0.15 | $0.2 | 32k | |
| OctoML Gemma-7B-it | $0.15 | $0.2 | 8k | |
| Mixtral 8x7B Instruct v0.1 | $0.4 | $0.6 | 33k | |
| OctoML CodeLlama-70b-Instruct | $0.4 | $0.6 | 100k | |
| OctoML Llama-2-70b-chat | $0.4 | $0.6 | 4k | |
| OctoML Nous-Hermes-2-Mixtral-8x7B-DPO | $0.4 | $0.6 | 33k |
Where else to run this
OctoML Gemma-2B-it on OctoML (Deprecated)
Provider setup and pricing
OctoML Gemma-7B-it on OctoML (Deprecated)
Provider setup and pricing
Mistral 7B Instruct v0.2 on OctoML (Deprecated)
Provider setup and pricing
Mistral 7B Instruct v0.2 on Cloudflare Workers AI
Alternative host
Mixtral 8x7B Instruct v0.1 on Together AI
Alternative host
Fireworks AI model catalog
225 tracked models
Pricing Overview
Cheapest$0.10/1M
Most expensive$0.40/1M