LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS

LLM pricing at a glance

Compare price, capability and every provider's quote for mainstream LLMs in one place

The data here is each provider's published API pricing and specs, with prices normalized to one million tokens and quoted in US dollars, switchable to a local currency at the latest exchange rate. Filter by capability, context window or budget, or open any model to compare its quote across every provider, with quality and speed benchmarks where available.

1,444 models · 326 providers · 10,118 quotes · synced 2026-11-20

⌕

Filters

Model type

Type is derived from family + output modality. Chat models only by default.

Capability

Input modality

Weights

Context window

Any

Min input price (USD/1M)

Any

Lifecycle

Labs (0)

Providers (0)

GLM-5.3
GLM-5.3IQ 31.7OpenBETAHas free channel
Input modality: TextImagezhipuai/glm-5.3
Official
$1.40
$0.22
$4.40
$0.70
$0.26
$0.042
1M
hosts 131K–5M
170 hosts
18.9× spread
↓ Ezkielyna
GLM-5.3IQ 31.7OpenBETAHas free channel
zhipuai/glm-5.3
Official$1.40→$4.40
Lowest$0.22→$0.70↓ Ezkielyna
Input modality: TextImage1M ctxReasoningTools170 hosts18.9×
GLM-5.3-Flash
GLM-5.3-FlashIQ 27.8NEWOpenBETAHas free channel
Input modality: TextImagePDFVideozhipuai/glm-5.3-flash
Official
$0.15
$0.04
$0.50
$0.078
$0.03
$0.03
1M
hosts 131K–1.05M
167 hosts
21.1× spread
↓ OpenRouter
GLM-5.3-FlashIQ 27.8NEWOpenBETAHas free channel
zhipuai/glm-5.3-flash
Official$0.15→$0.50
Lowest$0.04→$0.078↓ OpenRouter
Input modality: TextImagePDFVideo1M ctxReasoningTools167 hosts21.1×
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017IQ 32.6NEWOpenBETAHas free channel
Input modality: TextImagePDFdeepseek/deepseek-v4.1-flash-1017
Official
$0.15
$0.03
$0.60
$0.12
$0.003
$0.006
1.05M
hosts 200K–1.05M
146 hosts
72× spread
↓ engy
DeepSeek V4.1 Flash 1017IQ 32.6NEWOpenBETAHas free channel
deepseek/deepseek-v4.1-flash-1017
Official$0.15→$0.60
Lowest$0.03→$0.12↓ engy
Input modality: TextImagePDF1.05M ctxReasoningTools146 hosts72×
GLM-5.2
GLM-5.2OpenBETAHas free channel
Input modality: TextImagezhipuai/glm-5.2
Official
$1.40
$0.42
$4.40
$1.32
$0.26
$0.078
1M
hosts 96K–1.05M
135 hosts
15.8× spread
↓ NanoGPT
GLM-5.2OpenBETAHas free channel
zhipuai/glm-5.2
Official$1.40→$4.40
Lowest$0.42→$1.32↓ NanoGPT
Input modality: TextImage1M ctxReasoningTools135 hosts15.8×
Kimi K3
Kimi K3IQ 17.4OpenBETAHas free channel
Input modality: TextImagePDFVideomoonshotai/kimi-k3
Official
$3.00
$0.90
$15.00
$4.50
$0.30
$0.12
1.05M
hosts 262K–1.11M
131 hosts
31.3× spread
↓ UplinkSwitch
Kimi K3IQ 17.4OpenBETAHas free channel
moonshotai/kimi-k3
Official$3.00→$15.00
Lowest$0.90→$4.50↓ UplinkSwitch
Input modality: TextImagePDFVideo1.05M ctxReasoningTools131 hosts31.3×
DeepSeek V4.1 Flash
DeepSeek V4.1 FlashNEWOpenBETAHas free channel
Input modality: TextImagePDFdeepseek/deepseek-v4.1-flash
Official
—
$0.03
—
$0.12
—
$0.006
500K
hosts 256K–5M
124 hosts
33.3× spread
↓ engy
DeepSeek V4.1 FlashNEWOpenBETAHas free channel
deepseek/deepseek-v4.1-flash
Official—→—
Lowest$0.03→$0.12↓ engy
Input modality: TextImagePDF500K ctxReasoningTools124 hosts33.3×
GPT OSS 120B
GPT OSS 120BIQ 3.8OpenHas free channel
Input modality: TextImageopenai/gpt-oss-120b
Official
—
$0.029
—
$0.15
—
$0.0044
131K
hosts 33K–131K
109 hosts
100.3× spread
↓ LLM Gateway
GPT OSS 120BIQ 3.8OpenHas free channel
openai/gpt-oss-120b
Official—→—
Lowest$0.029→$0.15↓ LLM Gateway
Input modality: TextImage131K ctxReasoningTools109 hosts100.3×
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731OpenBETAHas free channel
Input modality: Textdeepseek/deepseek-v4-flash-0731
Official
—
$0.04
—
$0.079
—
—
524K
hosts 200K–1.05M
92 hosts
14.8× spread
↓ SAGG
DeepSeek V4 Flash 0731OpenBETAHas free channel
deepseek/deepseek-v4-flash-0731
Official—→—
Lowest$0.04→$0.079↓ SAGG
Input modality: Text524K ctxReasoningTools92 hosts14.8×

Explore models

Browse 1,444 large language models by intelligence, price, context window and availability. Open any model for its full pricing across every provider.

Highest intelligence

  • Claude Fable 5.2AA 64.6
  • GPT-6.2 AstraAA 62.1
  • Gemini 4 NeonAA 61.4
  • Gemini 4 CarbonAA 60
  • Claude Opus 5.5AA 59.1
  • GPT-6.2 SolAA 57.3
  • GPT-6 AstraAA 56.9
  • GPT-6.1 SolAA 54.6
  • Claude Sonnet 5.5AA 54.5
  • Gemini 4 HydrogenAA 53.9
  • GPT-6.1 TerraAA 51.3
  • Gemini 4 ArgonAA 50.4

Lowest blended price

  • Llama 3.2 1B Instruct$0.01
  • GPT OSS 20B$0.018
  • Llama 3.2 3B Instruct$0.02
  • Llama-3.1-8B-Instruct$0.023
  • Ling 3.0 Tiny$0.023
  • Mistral Nemo$0.025
  • GPT-5.6 Luna$0.028
  • ScaleDown: Summarize$0.03
  • Ling 3.0 Flash$0.032
  • MiniMax-M3.1-Flash$0.035
  • LightOnOCR 2 1B$0.036
  • MinerU2.5 2509 1.2B$0.036

Largest context window

  • Grok 4.1 Fast2M
  • X-Ai/Grok-4-Fast-Non-Reasoning2M
  • X-Ai/Grok-4-Fast-Reasoning2M
  • Grok 4.202M
  • GPT-5.6 Sol1.05M
  • GPT-5.6 Luna1.05M
  • GPT-5.6 Terra1.05M
  • GPT-6 Astra1.05M
  • GPT-5.51.05M
  • GPT-6.1 Sol1.05M
  • GPT-6 Luna1.05M
  • GPT-5.41.05M

Most providers

  • GLM-5.3170 hosts
  • GLM-5.3-Flash167 hosts
  • DeepSeek V4.1 Flash 1017146 hosts
  • GLM-5.2135 hosts
  • Kimi K3131 hosts
  • DeepSeek V4.1 Flash124 hosts
  • GPT OSS 120B109 hosts
  • DeepSeek V4 Flash 073192 hosts
  • Kimi K3.1 Pro87 hosts
  • DeepSeek V4 Pro83 hosts
  • Qwen3.8 27B81 hosts
  • GPT-5.6 Sol80 hosts

Latest articles

All articles →
  • ExplainerAI modelsOpen weights

    What are DeepSeek Uncensored models?

    A comparison of a 510 GB DeepSeek weight edit and a compact Qwen student model: lineage, refusal tests, hosted prices, local hardware and evidence limits.

    Nov 9, 2026·2,115 words·8 min readRead the article→
  • ExplainerAI agentsSubscriptions

    Always-on AI agents explained: Claude Duet, Grok Bot, Muse, dots and Gemini Spark

    Agents that run on their own cloud computer, keep working after you close the app and ask before they act. What the five main products do, where they differ and what each costs to start.

    Oct 22, 2026·1,792 words·7 min readRead the article→

How this comparison works

Every figure here is the per-token API rate published by each provider, normalized to one million tokens and quoted in US dollars. Other currencies are converted from that dollar figure at a daily exchange rate, so they are reference values rather than what the provider publishes. When a model is hosted by several providers, the table keeps each provider's own quote instead of averaging them, because the same model often differs in price, context window and capability flags from one host to the next.

The blended price ranks models on one number: input price times 0.75 plus output price times 0.25, matching a 3-to-1 input-to-output usage assumption. The lowest paid channel excludes $0 tiers, since free access usually carries rate limits and no service-level guarantee. Quality scores, where shown, come from Artificial Analysis; most models have no independent quality data, so those rows show pricing only.

Pricing and capability data is aggregated from models.dev, and quality and speed data from Artificial Analysis. Figures are indicative and can change, so the official provider page is the final authority before you commit to a channel.

Frequently asked questions

What is the cheapest LLM API in 2026?
Based on our comparison of 1444+ models, Llama 3.2 1B Instruct from Inference offers the lowest blended price at about $0.010 per 1M tokens.
How do I estimate LLM API costs?
Multiply your input tokens by the model's input price per 1M tokens, do the same for output tokens, then add them. Use the built-in cost calculator to estimate totals for any model and provider.
Which LLM has the largest context window?
Grok 4.1 Fast from xai claims the largest context window, up to 2,000,000 tokens. Its hosts report different limits, from 128,000 to 2,000,000 tokens, so the usable window depends on the provider you pick.
Which providers and models are compared here?
This site compares 1444+ models across providers like Alibaba, Google, OpenAI, DeepSeek, Mistral, Zhipu AI, with input, output and cache pricing per 1M tokens plus quality leaderboards.