ASCA06
MODEL DECISION PAGE

AI MODEL ATLAS · DECISION PAGE

Lowest-cost models among OpenRouter's top 100 coding order

Paid models in the first 100 positions of OpenRouter's coding-high-to-low response.

OBJECT IDasca:openrouter-model-page-budget-coding-models@2026-08-31.v1
FETCHED
STATUSREPRODUCIBLE SNAPSHOT

Lowest-cost models among OpenRouter's top 100 coding order

Keep coding rank <= 100 and positive prompt/completion prices; sort by prompt + completion USD per 1M text tokens.

OBSERVED MODELS · 10 SHOWN

Comparable fields from one dated catalog snapshot

RANK ≠ QUALITY
Rank / orderModelInput / 1MOutput / 1MRequestContextToolsStructuredDerived cost / basis
78Ling-3.0-flash$0.021$0.063$0.00262.14KYesNo$0.084 · $ per 1M input + 1M output text tokens
25Upstage: Solar Pro 4$0.03$0.12$0.00524.29KYesYes$0.15 · $ per 1M input + 1M output text tokens
1DeepSeek: DeepSeek V4 Flash 0731$0.065$0.18$0.001.31MYesYes$0.245 · $ per 1M input + 1M output text tokens
7DeepSeek: DeepSeek V4 Flash 0423$0.0886$0.1772$0.001.05MYesYes$0.2658 · $ per 1M input + 1M output text tokens
5Z.ai: GLM 5.3 Flash$0.075$0.25$0.001.31MYesYes$0.325 · $ per 1M input + 1M output text tokens
309DeepSeek: DeepSeek V4 Flash 0731 (batch)$0.14$0.28$0.001.05MYesYes$0.42 · $ per 1M input + 1M output text tokens
2Xiaomi: MiMo-V2.5$0.14$0.28$0.001.05MYesYes$0.42 · $ per 1M input + 1M output text tokens
39Google: Gemma 4 31B$0.09$0.34$0.00262.14KYesYes$0.43 · $ per 1M input + 1M output text tokens
302Z.ai: GLM 5.3 Flash (batch)$0.15$0.50$0.001.05MYesYes$0.65 · $ per 1M input + 1M output text tokens
33DeepSeek: DeepSeek V3.2$0.269$0.40$0.00163.84KYesYes$0.669 · $ 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: 93 matching catalog records; 10 shown.
  • Bias: OpenRouter catalog, ordering, and listed-price bias.
  • Limitation: Coding order is not a benchmark score; low listed token cost does not prove coding quality or availability.
  • Confidence: medium for the recorded response and stated transformation.

DOWNLOAD · VERIFY · CITE

Keep the snapshot and object ID with the decision.

Parent model atlas

Keep coding rank <= 100 and positive prompt/completion prices; sort by prompt + completion USD per 1M text tokens.asca:openrouter-model-page-budget-coding-models@2026-08-31.v1