The Atlas · column D ($0.30–1) · row 3 (128–256K)
GRIDD3 Models at $0.30–1 per 1M input with 128–256K tokens of context
11 models · 6 creatorsChecked 10 Oct 2026
11 models cost between $0.30 and $0.70 per 1M input tokens and hold 128–256K tokens of context. The cheapest on input is Codestral 2508 at , tied with 4 others; Llama 3.1 70B Instruct has the lowest output price at $0.40. A request that fills each model’s window costs $0.04–$0.12 here, because windows differ within a square.
$0.30
observed We measured
- Source
- Our catalogue
- Retrieved
- 17 Aug 2026
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
Cite
Cite this page
ModelsAtlas. “Models at $0.30–1 per 1M input with 128–256K tokens of context”. Retrieved 10 Oct 2026. https://modelsatlas.com/atlas/d3
Models in D3
Cheapest available standard-tier offer · USD per 1M tokens
| Model | Input | Output | Context | Listed | |
|---|---|---|---|---|---|
| Codestral 2508Mistral AI | $0.30 | $0.90 | 256,000 | batch | Alternatives |
| Command A+Cohere | $0.30 | $1.50 | 192,000 | — | Alternatives |
| MiniMax M2MiniMax | $0.30 | $1.20 | 204,800 | — | Alternatives |
| MiniMax M2.1MiniMax | $0.30 | $1.20 | 204,800 | — | Alternatives |
| Muse Glimmer 30BMeta | $0.30 | $1.20 | 131,072 | — | Alternatives |
| DeepSeek V3DeepSeek | $0.32 | $0.89 | 163,840 | — | Alternatives |
| Llama 3.1 70B InstructMeta | $0.40 | $0.40 | 131,072 | — | Alternatives |
| Mistral Medium 3Mistral AI | $0.40 | $2.00 | 131,072 | — | Alternatives |
| Mistral Medium 3.1Mistral AI | $0.40 | $2.00 | 131,072 | batch | Alternatives |
| Nano Banana 2 (Gemini 3.1 Flash Image)Google | $0.50 | $3.00 | 131,072 | — | Alternatives |
| R1 0528DeepSeek | $0.70 | $2.50 | 163,840 | — | Alternatives |
What a window-filling request costs here
One prompt that fills the model’s context window plus up to 4,000 output tokens · Σ derived
Arithmetic from the listed standard-tier rates, not a quote; the cheapest list price is not always the cheapest full-window request.
Neighbouring squares
One step cheaper, pricier, smaller or larger
← cheaper10GRIDC3$0.10–0.30 per 1M input, 128–256K context: Ministral 3 3B 2512, Llama Guard 4 12B and 8 more.pricier →8GRIDE3$1–3 per 1M input, 128–256K context: Claude Haiku 4.5, Grok Build 0.1 and 6 more.↓ smaller7GRIDD2$0.30–1 per 1M input, 32–128K context: MiniMax M2-her, Nano Banana (Gemini 2.5 Flash Image) and 5 more.↑ larger4GRIDD4$0.30–1 per 1M input, 256K–1M context: Qwen3 Coder 480B A35B, Qwen3.6 27B and 2 more.
Questions about square D3
What is the cheapest AI model with 128–256K tokens of context at $0.30–1 input?
Codestral 2508 at $0.30 per 1M input tokens and $0.90 output, tied with 4 others. The other 10 in D3: Command A+, MiniMax M2, MiniMax M2.1, Muse Glimmer 30B, DeepSeek V3 and 5 more.
Which D3 model is cheapest for a request that fills its context window?
Muse Glimmer 30B, at about $0.04 for a prompt that fills its 131K window plus its output. The dearest of the 11 is R1 0528 at $0.12. The cheapest list price is not always the cheapest full-window request, because windows differ within a square.
Are any D3 models open-weight?
None of the 11 is marked open-weight in our records.
What does grid reference D3 mean?
D is the price column ($0.30–1 per 1M input tokens) and 3 is the context row (128–256K). Models in the same square are like-for-like on price and context only; the grid says nothing about quality.
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What is the cheapest AI model with 128–256K tokens of context at $0.30–1 input?
- Which D3 model is cheapest for a request that fills its context window?
- Are any D3 models open-weight?