AI MODEL ATLAS · DECISION PAGE
Lowest-cost models among OpenRouter's top 100 agentic order
Paid models in the first 100 positions of OpenRouter's agentic-high-to-low response.
OBJECT ID
asca:openrouter-model-page-budget-agentic-models@2026-09-01.v1FETCHED
STATUSREPRODUCIBLE SNAPSHOT
QUESTION · METHOD
Lowest-cost models among OpenRouter's top 100 agentic order
Keep agentic 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 / order | Model | Input / 1M | Output / 1M | Request | Context | Tools | Structured | Derived cost / basis |
|---|---|---|---|---|---|---|---|---|
| 76 | Ling-3.0-flash | $0.021 | $0.063 | $0.00 | 262.14K | Yes | No | $0.084 · $ per 1M input + 1M output text tokens |
| 25 | Upstage: Solar Pro 4 | $0.03 | $0.12 | $0.00 | 524.29K | Yes | Yes | $0.15 · $ per 1M input + 1M output text tokens |
| 6 | DeepSeek: DeepSeek V4 Flash 0423 | $0.0809 | $0.1618 | $0.00 | 1.05M | Yes | Yes | $0.2428 · $ per 1M input + 1M output text tokens |
| 1 | DeepSeek: DeepSeek V4 Flash 0731 | $0.065 | $0.18 | $0.00 | 1.31M | Yes | Yes | $0.245 · $ per 1M input + 1M output text tokens |
| 3 | Z.ai: GLM 5.3 Flash | $0.075 | $0.25 | $0.00 | 1.31M | Yes | Yes | $0.325 · $ per 1M input + 1M output text tokens |
| 310 | DeepSeek: DeepSeek V4 Flash 0731 (batch) | $0.14 | $0.28 | $0.00 | 1.05M | Yes | Yes | $0.42 · $ per 1M input + 1M output text tokens |
| 4 | Xiaomi: MiMo-V2.5 | $0.14 | $0.28 | $0.00 | 1.05M | Yes | Yes | $0.42 · $ per 1M input + 1M output text tokens |
| 289 | Z.ai: GLM 5.3 Flash (batch) | $0.15 | $0.50 | $0.00 | 1.05M | Yes | Yes | $0.65 · $ per 1M input + 1M output text tokens |
| 177 | OpenAI: GPT-5.6 Luna (batch) | $0.10 | $0.60 | $0.00 | 1.05M | Yes | Yes | $0.70 · $ per 1M input + 1M output text tokens |
| 364 | OpenAI: GPT-5.4 Nano (batch) | $0.10 | $0.625 | $0.00 | 400K | Yes | Yes | $0.725 · $ 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.
RANGE · BIAS · LIMIT · CONFIDENCE
- Observed range: 94 matching catalog records; 10 shown.
- Bias: OpenRouter catalog, ordering, and listed-price bias.
- Limitation: Agentic order is not actual machine consumption or task success; low listed cost does not prove autonomy or availability.
- Confidence: medium for the recorded response and stated transformation.
DOWNLOAD · VERIFY · CITE
Keep the snapshot and object ID with the decision.
“Keep agentic rank <= 100 and positive prompt/completion prices; sort by prompt + completion USD per 1M text tokens.”— asca:openrouter-model-page-budget-agentic-models@2026-09-01.v1
RELATED DECISION PAGES
- Cheapest paid LLM API models
- Long-context LLMs for a 128K + 4K workload
- Tool-calling compatible models
- Structured-output compatible models
- Vision-language models
- Free LLM API models
- Most popular AI models by OpenRouter weekly order
- Fastest LLM API models by OpenRouter order
- Coding AI models by OpenRouter order
- Agentic AI models by OpenRouter order
- Lowest-cost models among OpenRouter's top 100 coding order
- Lowest-cost models among OpenRouter's top 100 agentic order
- Tool-calling models with at least one million context tokens
- Image-input models with tool-calling support
- Models declaring both tools and structured outputs