ASCA06
MODEL DECISION PAGE

AI MODEL ATLAS · DECISION PAGE

Cheapest paid LLM API models

OpenRouter catalog models with positive prompt and completion prices.

OBJECT IDasca:openrouter-model-page-cheapest-llm-api@2026-08-27.v1
FETCHED
STATUSREPRODUCIBLE SNAPSHOT

Cheapest paid LLM API models

Sort by derived_cost_usd = prompt + completion USD per 1M text tokens; free/zero rows excluded; request price is reported separately and excluded.

OBSERVED MODELS · 10 SHOWN

Comparable fields from one dated catalog snapshot

RANK ≠ QUALITY
Rank / orderModelInput / 1MOutput / 1MRequestContextToolsStructuredDerived cost / basis
49Mistral: Mistral Nemo$0.019$0.03$0.00131.07KYesYes$0.049 · $ per 1M input + 1M output text tokens
73Ling-3.0-flash$0.021$0.063$0.00262.14KYesNo$0.084 · $ per 1M input + 1M output text tokens
159Sao10K: Llama 3 8B Lunaris$0.04$0.05$0.008.19KNoYes$0.09 · $ per 1M input + 1M output text tokens
388DeepSeek V4 Flash Latest$0.03$0.075$0.001.31MYesYes$0.105 · $ per 1M input + 1M output text tokens
255MythoMax 13B$0.06$0.06$0.008.19KNoYes$0.12 · $ per 1M input + 1M output text tokens
140Nex AGI: Nex-N2-Mini$0.025$0.10$0.00262.14KYesYes$0.125 · $ per 1M input + 1M output text tokens
249IBM: Granite 4.0 Micro$0.017$0.112$0.00131KNoNo$0.129 · $ per 1M input + 1M output text tokens
74Meta: Llama 3.1 8B Instruct$0.05$0.08$0.00131.07KYesYes$0.13 · $ per 1M input + 1M output text tokens
138Mistral: Mistral Small 3$0.05$0.08$0.0032.77KNoYes$0.13 · $ per 1M input + 1M output text tokens
204Google: Gemma 3 4B$0.05$0.10$0.00131.07KNoYes$0.15 · $ per 1M input + 1M output text tokens

Prices are listed USD per token converted to USD per 1M tokens. Request fee is a separate listed field; it is not included in derived text-token cost. A free listing means zero listed token price in this snapshot, not unlimited access.

  • Observed range: 392 matching catalog records; 10 shown.
  • Bias: Catalog and listed-price selection bias.
  • Limitation: Listed OpenRouter prices are not provider-direct prices or guaranteed availability.
  • Confidence: high for the recorded response and stated transformation.

DOWNLOAD · VERIFY · CITE

Keep the snapshot and object ID with the decision.

Parent model atlas

Sort by derived_cost_usd = prompt + completion USD per 1M text tokens; free/zero rows excluded; request price is reported separately and excluded.asca:openrouter-model-page-cheapest-llm-api@2026-08-27.v1