LLM API pricing / Long prompts

The cheapest LLM APIs when the prompt is long

One request with a 300,000-token prompt and a 2,000-token answer costs $0.0308 on Gemini 2.5 Flash-Lite and $6.64 on GPT-5.2 Pro, across the 64 current models with a verified price that can take it. 22 of them charge a higher rate above a prompt length and are priced at that rate here. Prices verified between September 28, 2026 and November 17, 2026.

How the cost is computed

cost = 300,000 / 1,000,000 × input price + 2,000 / 1,000,000 × output price, with each model's price per 1M tokens. When a model records a long-prompt tier whose condition a 300,000-token prompt meets, the tier's input and output prices replace the base prices for the whole request; with several tiers, the highest one the prompt reaches. Cached input, batch and other price lists are not used: this is one uncached request at the list price. A model whose context window is smaller than 302,000 tokens cannot take the request and is listed apart; so is a model whose context window AI Signal has not recorded.

Ranking

#ModelCost of the requestInput / output $ per 1M appliedContext
1 Gemini 2.5 Flash-Lite Google $0.0308 $0.10 / $0.40 1,048,576
2 Qwen3.8-Flash Alibaba $0.0459 $0.15 / $0.47 1,000,000
2 Qwen3.8-Omni-Flash Alibaba $0.0459 $0.15 / $0.47 1,000,000
4 GLM 5.3 Flash Mistral $0.0460 $0.15 / $0.50 1,000,000
5 GPT-6 Luna OpenAI $0.0615 $0.20 / $0.75 · tier over 272,000 tokens 1,050,000
6 Qwen3.7-Flash Alibaba $0.0616 $0.20 / $0.80 · tier over 256,000 tokens 1,000,000
7 DeepSeek V4.1 Flash DeepSeek $0.0924 $0.30 / $1.20 1,000,000
7 DeepSeek V4.1 Flash 1017 Mistral $0.0924 $0.30 / $1.20 1,000,000
9 Muse Ember Meta $0.0930 $0.30 / $1.50 · tier over 200,000 tokens 1,048,576
10 Gemini 3.5 Flash-Lite Google $0.0950 $0.30 / $2.50 1,048,576
11 GPT-5.6 Luna OpenAI $0.124 $0.40 / $1.80 · tier over 272,000 tokens 1,050,000
12 Claude Haiku 5.5 Anthropic $0.155 $0.50 / $2.50 · tier over 100,000 tokens 1,000,000
13 Mistral Large 4 Mistral $0.214 $0.70 / $2.10 1,000,000
14 Gemini 3.6 Flash Google promo $0.233 $0.75 / $3.75 1,048,576
14 Gemini 3.8 Flash Google promo $0.233 $0.75 / $3.75 1,048,576
16 GPT-5.4 Mini OpenAI $0.234 $0.75 / $4.50 400,000
17 Qwen3.7-Plus Alibaba $0.370 $1.20 / $4.80 · tier over 256,000 tokens 1,000,000
18 Muse Spark 1.1 Meta $0.384 $1.25 / $4.25 1,048,576
18 Muse Spark 1.2 Meta $0.384 $1.25 / $4.25 1,048,576
18 Muse Spark 1.3 Meta $0.384 $1.25 / $4.25 1,048,576
21 DeepSeek V4 Pro DeepSeek $0.404 $1.32 / $3.96 1,000,000
22 GLM 5.3 Mistral $0.429 $1.40 / $4.40 1,000,000
23 Qwen4-Max Alibaba $0.459 $1.50 / $4.50 1,000,000
24 Gemini 4 Hydrogen Google $0.465 $1.50 / $7.50 1,048,576
25 GPT-5.2 OpenAI $0.553 $1.75 / $14.00 400,000
26 Qwen3.8-Max Alibaba $0.612 $2.00 / $6.00 1,000,000
27 GPT-6.1 Terra OpenAI $0.615 $2.00 / $7.50 · tier over 272,000 tokens 1,050,000
28 Claude Sonnet 5 Anthropic $0.620 $2.00 / $10.00 1,000,000
28 Claude Sonnet 5.5 Anthropic $0.620 $2.00 / $10.00 1,000,000
28 Gemini 4 Argon Google promo $0.620 $2.00 / $10.00 1,048,576
28 Gemini 4 Carbon Google promo $0.620 $2.00 / $10.00 1,048,576
32 Grok 4.20 (non-reasoning) xAI $0.760 $2.50 / $5.00 · tier of 200,000 tokens or more 1,000,000
32 Grok 4.20 (reasoning) xAI $0.760 $2.50 / $5.00 · tier of 200,000 tokens or more 1,000,000
32 Grok 4.20 Multi-agent xAI $0.760 $2.50 / $5.00 · tier of 200,000 tokens or more 1,000,000
32 Grok 4.3 xAI $0.760 $2.50 / $5.00 · tier of 200,000 tokens or more 1,000,000
36 Qwen3.7-Max Alibaba $0.765 $2.50 / $7.50 1,000,000
37 Claude Sonnet 4.6 Anthropic $0.930 $3.00 / $15.00 1,000,000
38 Grok 4.5 xAI $1.22 $4.00 / $12.00 · tier of 200,000 tokens or more 500,000
38 Grok 4.6 xAI $1.22 $4.00 / $12.00 · tier of 200,000 tokens or more 500,000
38 Grok 4.7 xAI $1.22 $4.00 / $12.00 · tier of 200,000 tokens or more 500,000
41 GPT-6 Sol OpenAI $1.23 $4.00 / $15.00 · tier over 272,000 tokens 1,050,000
41 GPT-6.1 Sol OpenAI $1.23 $4.00 / $15.00 · tier over 272,000 tokens 1,050,000
41 GPT-6.2 Sol OpenAI $1.23 $4.00 / $15.00 · tier over 272,000 tokens 1,050,000
44 Gemini 3.1 Pro Preview Google $1.24 $4.00 / $18.00 · tier over 200,000 tokens 1,048,576
44 GPT-5.6 Terra OpenAI $1.24 $4.00 / $18.00 · tier over 272,000 tokens 1,050,000
46 Claude Opus 5.5 Anthropic $1.24 $4.00 / $20.00 1,000,000
46 Muse Wonder Meta $1.24 $4.00 / $20.00 1,048,576
48 Claude Opus 4.6 Anthropic $1.55 $5.00 / $25.00 1,000,000
48 Claude Opus 4.7 Anthropic $1.55 $5.00 / $25.00 1,000,000
48 Claude Opus 4.8 Anthropic $1.55 $5.00 / $25.00 1,000,000
48 Claude Opus 5 Anthropic $1.55 $5.00 / $25.00 1,000,000
52 ChatGPT (chat-latest) OpenAI $1.56 $5.00 / $30.00 400,000
53 GPT-5.6 Sol OpenAI promo $2.46 $8.00 / $30.00 · tier over 272,000 tokens 1,050,000
54 Claude Fable 5.2 Anthropic $2.48 $8.00 / $40.00 1,000,000
54 Claude Mythos 5.2 Anthropic $2.48 $8.00 / $40.00 1,000,000
56 Claude Fable 5 Anthropic $3.10 $10.00 / $50.00 1,000,000
56 Claude Fable 5.1 Anthropic $3.10 $10.00 / $50.00 1,000,000
56 Claude Mythos 5 Anthropic $3.10 $10.00 / $50.00 1,000,000
56 Claude Mythos 5.1 Anthropic $3.10 $10.00 / $50.00 1,000,000
60 GPT-5.6 Cyber OpenAI $3.90 $12.50 / $75.00 400,000
61 GPT-6.2 Astra OpenAI $4.92 $16.00 / $60.00 · tier over 272,000 tokens 1,050,000
62 GPT-6 Astra OpenAI $6.15 $20.00 / $75.00 · tier over 272,000 tokens 1,050,000
63 GPT-6 Cyber OpenAI $6.20 $20.00 / $100.00 1,050,000
64 GPT-5.2 Pro OpenAI $6.64 $21.00 / $168.00 400,000

Promotional prices: Gemini 3.6 Flash (until December 31, 2026), Gemini 3.8 Flash (until December 31, 2026), Gemini 4 Argon (until November 30, 2026), Gemini 4 Carbon (until November 30, 2026), GPT-5.6 Sol (until November 30, 2026). The cost above uses the promotional price; what each maker publishes for after the promotion, if anything, is on the model's page.

The Alibaba rows use its Singapore (International) prices. For all of them the base input price in Beijing and Global is lower; each model page shows both.

DeepSeek V4.1 Flash is ranked at its list (peak) price; off-peak, 133 of the 168 hours of the week, the same request costs $0.0462. DeepSeek V4 Pro is ranked at its list (peak) price; off-peak, 133 of the 168 hours of the week, the same request costs $0.202.

Models that cannot take a 300,000-token prompt

Context window under 302,000 tokens: Claude Haiku 4.5 (200,000), Claude Opus 4.5 (200,000), Gemini Robotics ER 2 Preview (131,072), Gemini Robotics ER 2 Streaming Preview (131,072), Grok Build 0.1 (256,000), Mistral Small 4 (256,000), Codestral (128,000), Ministral 3 3B (256,000), Ministral 3 8B (256,000), Ministral 3 14B (256,000), Command A (256,000), Command R7B (128,000), Command R (08-2024) (128,000), Command R+ (08-2024) (128,000).

No context window recorded on AI Signal, so not ranked: GPT-Rosalind, GPT-Rosalind Discovery, GPT-6 Rosalind, GPT-5 Search API.

All current prices, with cached input and sources: LLM API pricing. Your own volume: cost calculator. How every figure is checked: methodology.