Models & pricing
Inferel serves 60+ models across frontier labs and leading open-source families, including:
| Family | Examples |
|---|---|
| Anthropic | anthropic/claude-opus-4.8, anthropic/claude-sonnet-4.6, anthropic/claude-haiku-4.5 |
| OpenAI | openai/gpt-5.5, openai/gpt-5.4-pro, openai/gpt-5.4-mini |
google/gemini-3.5-flash, google/gemini-3.1-pro-preview, google/gemma-4-31b-it | |
| DeepSeek | deepseek-ai/DeepSeek-V4-Pro, deepseek-ai/DeepSeek-V3.2, deepseek-ai/DeepSeek-R1-0528 |
| Qwen | Qwen/Qwen3.7-Max, Qwen/Qwen3.6-Plus, Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 |
| Moonshot | moonshotai/Kimi-K2.6, moonshotai/kimi-k2.7-code |
| Others | zai-org/GLM-5.1-FP8, MiniMaxAI/MiniMax-M3, grok-4-fast-reasoning, nvidia/nemotron-3-ultra-550b-a55b |
The authoritative, always-current list is GET /v1/models — the
catalog evolves as capacity and providers are added, and a model is listed only while it
has healthy serving capacity.
Pricing
Section titled “Pricing”LLM usage is priced per 1,000,000 tokens, with separate rates for input (prompt) and
output (completion) tokens — displayed in the console as,
for example, $3 / $15 per 1M tokens. Where the underlying model supports prompt
caching, cache reads and cache writes are priced at their own (typically discounted)
per-1M-token rates.
The cost of each request is computed from the exact token counts in the response’s
usage object and deducted from your organization’s prepaid credit balance — see
Billing & credits.
Current per-model prices are listed on the Models page of the console. Per-organization discounts and coupon codes, when applied, are reflected automatically in billing.
Choosing a pool
Section titled “Choosing a pool”Some models are available through multiple vendor pools with different price/performance trade-offs — see Resource groups for how to select one explicitly.