LLMs with discounted batch processing
OpenAI: gpt-oss-20b is the cheapest option at $0.018 per million input tokens. Batch tiers trade latency for a large discount on work that does not need an answer now - backfills, evaluations, bulk classification.
71 models qualify
Ranked by blended cost - input weighted 75%, output 25%.
| # | Model | Blended / 1M | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|---|---|
| 1 | gpt-oss-20b OpenAI | $0.036 | $0.018 | $0.090 | 131K | ReasoningToolsOpen weights |
| 2 | GLM 5.3 Flash Z.ai | $0.053 | $0.046 | $0.074 | 1.0M | ReasoningToolsVisionOpen weights |
| 3 | GPT-5 Nano OpenAI | $0.137 | $0.050 | $0.400 | 400K | ReasoningToolsVision |
| 4 | DeepSeek V4.1 Flash DeepSeek | $0.159 | $0.045 | $0.500 | 1.0M | ReasoningToolsVisionOpen weights |
| 5 | GPT-4.1 Nano OpenAI | $0.175 | $0.100 | $0.400 | 1.0M | ToolsVision |
| 6 | Claude Haiku 5.5 Anthropic | $0.200 | $0.100 | $0.500 | 1M | ReasoningToolsVision |
| 7 | GPT-6 Luna Pro OpenAI | $0.200 | $0.100 | $0.500 | 1.1M | ReasoningToolsVision |
| 8 | GPT-6 Luna OpenAI | $0.200 | $0.100 | $0.500 | 1.1M | ReasoningToolsVision |
| 9 | gpt-oss-120b OpenAI | $0.262 | $0.150 | $0.600 | 131K | ReasoningToolsOpen weights |
| 10 | GPT-4o-mini OpenAI | $0.262 | $0.150 | $0.600 | 128K | ToolsVision |
| 11 | GLM 5.3 Z.ai | $0.402 | $0.070 | $1.40 | 1.0M | ReasoningToolsOpen weights |
| 12 | GPT-5.6 Luna Pro OpenAI | $0.450 | $0.200 | $1.20 | 1.1M | ReasoningToolsVision |
| 13 | GPT-5.6 Luna OpenAI | $0.450 | $0.200 | $1.20 | 1.1M | ReasoningToolsVision |
| 14 | GPT-5.4 Nano OpenAI | $0.463 | $0.200 | $1.25 | 400K | ReasoningToolsVision |
| 15 | Qwen3.7 Plus Qwen | $0.560 | $0.320 | $1.28 | 1M | ReasoningToolsVision |
| 16 | Gemini 3.1 Flash Lite | $0.563 | $0.250 | $1.50 | 1.0M | ReasoningToolsVision |
| 17 | GPT-5 Mini OpenAI | $0.688 | $0.250 | $2.00 | 400K | ReasoningToolsVision |
| 18 | GPT-4.1 Mini OpenAI | $0.700 | $0.400 | $1.60 | 1.0M | ToolsVision |
| 19 | Gemini 3.5 Flash Lite | $0.850 | $0.300 | $2.50 | 1.0M | ReasoningToolsVision |
| 20 | o4 Mini (batch) OpenAI | $0.963 | $0.550 | $2.20 | 200K | ReasoningToolsVision |
| 21 | o3 Mini (batch) OpenAI | $0.963 | $0.550 | $2.20 | 200K | ReasoningTools |
| 22 | Gemini 3 Flash Preview | $1.13 | $0.500 | $3.00 | 1.0M | ReasoningToolsVision |
| 23 | Gemini 3.7 Flash | $1.50 | $0.750 | $3.75 | 1.0M | ReasoningToolsVision |
| 24 | Gemini 3.6 Flash | $1.50 | $0.750 | $3.75 | 1.0M | ReasoningToolsVision |
| 25 | Grok 4.3 xAI | $1.56 | $1.25 | $2.50 | 1M | ReasoningToolsVision |
Frequently asked
What is the cheapest LLM for asynchronous batch jobs?
OpenAI: gpt-oss-20b at $0.018 per million input tokens and $0.090 per million output tokens, with a 131K token context window.
How many models qualify for asynchronous batch jobs?
71 of the 359 models tracked here meet the criteria for this list.
How much do prices vary within this category?
By roughly 1,900×, from gpt-oss-20b at the bottom to GPT-5.4 Pro at the top.