Provider

inferenceapis

24 Models · 24 Prices · Cheapest on 5 · Uptime — · updated 2026-10-15 19:16 UTC

Trust signals · SLA · model-version transparency · pricing stability · quantization-degradation · incident response · data privacy — measured by TKX probe (activating).

Models served

Model$ in /1M$ out /1MCheapestRouter / SourceEvidence
gpt-oss-20b $0.040$0.190 — Pricebook (LiteLLM) ↗ Official list
Qwen3.8-Flash $0.150$0.500 — Pricebook (LiteLLM) ↗ Official list
DeepSeek-V3 $0.190$0.380 — Pricebook (LiteLLM) ↗ Official list
DeepSeek-V4-Flash $0.190$0.380 — Pricebook (LiteLLM) ↗ Official list
DeepSeek-V4-Flash-0731 $0.190$0.380 — Pricebook (LiteLLM) ↗ Official list
deepseek-chat $0.190$0.380 — Pricebook (LiteLLM) ↗ TKX probe
deepseek-reasoner $0.190$0.380 — Pricebook (LiteLLM) ↗ Official list
llama-3.1-8b-instant $0.200$0.500 ✓ Pricebook (LiteLLM) ↗ Official list
llama-3.3-70b $0.200$0.500 ✓ Pricebook (LiteLLM) ↗ Official list
llama-3.3-70b-instruct $0.200$0.500 — Pricebook (LiteLLM) ↗ Official list
llama-3.3-70b-versatile $0.200$0.500 ✓ Pricebook (LiteLLM) ↗ Official list
Llama-3.3-70B-Instruct-Turbo $0.200$0.500 — Pricebook (LiteLLM) ↗ Official list
glm-5.3-flash $0.200$0.660 — Pricebook (LiteLLM) ↗ Official list
gpt-oss-120b $0.200$0.800 — Pricebook (LiteLLM) ↗ Official list
Qwen3-VL-235B-A22B-Instruct $0.260$1.15 — Pricebook (LiteLLM) ↗ Official list
qwen3-vl $0.260$1.15 ✓ Pricebook (LiteLLM) ↗ Official list
qwen3-vl-235b $0.260$1.15 ✓ Pricebook (LiteLLM) ↗ Official list
minimax-m3 $0.390$1.56 — Pricebook (LiteLLM) ↗ Official list
DeepSeek-V4.1-Flash $0.400$1.60 — Pricebook (LiteLLM) ↗ Official list
deepseek-flash $0.400$1.60 — Pricebook (LiteLLM) ↗ Official list
kimi-k2.7-code $0.890$4.42 — Pricebook (LiteLLM) ↗ Official list
DeepSeek-V4-Pro $1.72$5.15 — Pricebook (LiteLLM) ↗ Official list
DeepSeek-V4-Pro-0813 $1.72$5.15 — Pricebook (LiteLLM) ↗ Official list
glm-5.3 $1.82$5.72 — Pricebook (LiteLLM) ↗ Official list

Related analysis

← All providers