Original research · Official price pages · CC BY 4.0

State of LLM API Pricing 2026: what a support chat really costs

On this page

The short answer

  • A support chat costs between $0.0002 and $0.39 at list price. Same 4-turn conversation, 81 models, 9 providers: a 1,718x spread. The median model costs $100 per 10,000 conversations.
  • $2 in / $10 out is the 2026 mid-tier price point. 6 models from 3 providers (Anthropic, Google, OpenAI) list exactly $2 / $10 per million tokens.
  • Input is most of the bill. Because every turn resends the system prompt and history, input is 76% of the cost on a $2 / $10 model in our default conversation. Caching and shorter system prompts matter more than output length.
  • Several prices change soon. Google lists Gemini 4 Carbon and Argon doubling to $4 / $20 on 1 Dec 2026, and OpenAI's gpt-5.6-sol promotional price ends on 30 Nov 2026.

Key numbers

  • List prices across 81 models from 9 providers run from $0.017/$0.112 (granite-4.0-h-micro) to $30/$180 (gpt-5.5-pro) per 1M input/output tokens. (State of LLM API Pricing 2026, 12 Nov 2026)
  • From 1 Dec 2026, Gemini API requests to gemini-2.5-pro route to gemini-3.8-flash and are billed at its rates. (Gemini API deprecations, 13 Nov 2026)

Price-per-million-tokens tables don't tell you what a customer conversation costs, because chat apps resend the system prompt and history every turn. We read every price from the provider's own pricing or model page on 12 Nov 2026, then priced the same support conversation on all 81 models. Change the assumptions in the calculator and the whole table updates.

Key findings

  1. The cheapest and priciest models are 1,718x apart. granite-4.0-h-micro (Cloudflare Workers AI) costs $2.29 per 10,000 conversations. gpt-5.5-pro (OpenAI) costs $3,930 (Cloudflare, OpenAI).
  2. Flagship prices fell, then started rising again. Anthropic's page lists Opus 4 / 4.1 at $15 / $75, Opus 4.5 to 5 at $5 / $25 and Opus 5.5 at $4 / $20 (Anthropic pricing). Google's page lists Gemini 4 Carbon and Argon going from $2 / $10 to $4 / $20 on 1 Dec 2026 (Gemini pricing).
  3. Cached-input prices are common but not universal. 9 of 81 rows list a cached-input price on the page we used. In 8 of those 9, the cached price is a tenth of the normal input price or less, so a long, stable system prompt is much cheaper to resend.
  4. Open-weight models are cheapest on hosted platforms. gpt-oss-120b costs $0.15 / $0.60 on Groq and Together AI and $0.35 / $0.75 on Cloudflare Workers AI (Groq, Together, Workers AI).
  5. Price pages don't always agree with themselves. Mistral's pricing FAQ says Mistral Large costs $0.5 / $1.5, while the Mistral Large 4 model page says $0.7 / $2.1. We use the model page and flag the gap (Mistral docs).

Cost-per-conversation calculator

Defaults: a 2,000-token system prompt, 4 turns, 60 tokens per customer message and 150 per reply. That's 9,500 input and 600 output tokens per conversation.

Per conversation: 9,500 input and 600 output tokens. Cheapest in the table: granite-4.0-h-micro ($0.0002). Priciest: gpt-5.5-pro ($0.39).

Formula: input for turn k = system prompt + k customer messages + (k-1) bot replies, because each turn resends the history. Output = turns x reply tokens. Cost = input x input price + output x output price, per million tokens. No retrieval context, tool calls, reasoning tokens, batch discounts or taxes. Your real numbers will differ, so measure your own token counts.

Price table

81 models, list price in USD per 1 million tokens, standard tier, read 12 Nov 2026. Cost columns update with the calculator above.
Official source and notes
gpt-5.5-proOpenAI$30$180Not disclosed$0.39$3,930developers.openai.comStandard tier
gpt-6-astraOpenAI$10$50$1$0.12$1,250developers.openai.comStandard tier, short context (<=272K input)
gpt-5.5OpenAI$5$30Not disclosed$0.066$655developers.openai.comStandard tier
gpt-5.6-solOpenAI$4$20Not disclosed$0.050$500developers.openai.comPromotional pricing available until November 30, 2026 (per page)
gpt-5.4OpenAI$2.50$15Not disclosed$0.033$328developers.openai.comStandard tier
gpt-4oOpenAI$2.50$10Not disclosed$0.030$298developers.openai.comStandard tier
gpt-6.1-solOpenAI$2$10$0.10$0.025$250developers.openai.comStandard tier, short context
gpt-6-solOpenAI$2$10$0.20$0.025$250developers.openai.comStandard tier, short context
gpt-5.6-terraOpenAI$2$12Not disclosed$0.026$262developers.openai.comStandard tier
gpt-4.1OpenAI$2$8Not disclosed$0.024$238developers.openai.comStandard tier
o3OpenAI$2$8Not disclosed$0.024$238developers.openai.comStandard tier
gpt-5.2OpenAI$1.75$14Not disclosed$0.025$250developers.openai.comStandard tier
gpt-5.1OpenAI$1.25$10Not disclosed$0.018$179developers.openai.comStandard tier
gpt-5OpenAI$1.25$10Not disclosed$0.018$179developers.openai.comStandard tier
gpt-6.1-terraOpenAI$1$5$0.05$0.013$125developers.openai.comStandard tier, short context
gpt-5.4-miniOpenAI$0.75$4.50Not disclosed$0.010$98.25developers.openai.comStandard tier
gpt-4.1-miniOpenAI$0.40$1.60Not disclosed$0.005$47.60developers.openai.comStandard tier
gpt-5-miniOpenAI$0.25$2Not disclosed$0.004$35.75developers.openai.comStandard tier
gpt-5.6-lunaOpenAI$0.20$1.20Not disclosed$0.003$26.20developers.openai.comStandard tier
gpt-5.4-nanoOpenAI$0.20$1.25Not disclosed$0.003$26.50developers.openai.comStandard tier
gpt-4o-miniOpenAI$0.15$0.60Not disclosed$0.002$17.85developers.openai.comStandard tier
gpt-6-lunaOpenAI$0.10$0.50$0.01$0.001$12.50developers.openai.comStandard tier, short context
gpt-5-nanoOpenAI$0.05$0.40Not disclosed$0.0007$7.15developers.openai.comStandard tier
Claude Opus 4.1Anthropic$15$75Not disclosed$0.19$1,875platform.claude.comListed as retired
Claude Fable 5.1Anthropic$10$50Not disclosed$0.12$1,250platform.claude.comBase input / output
Claude Fable 5.2Anthropic$8$40Not disclosed$0.10$1,000platform.claude.comBase input / output (same price listed for Mythos 5.2)
Claude Opus 5Anthropic$5$25Not disclosed$0.062$625platform.claude.comBase input / output (same as Opus 4.5-4.8)
Claude Opus 4.5Anthropic$5$25Not disclosed$0.062$625platform.claude.comBase input / output
Claude Opus 5.5Anthropic$4$20Not disclosed$0.050$500platform.claude.comBase input / output
Claude Sonnet 4.6Anthropic$3$15Not disclosed$0.037$375platform.claude.comBase input / output (same as Sonnet 4.5 and 4)
Claude Sonnet 5.5Anthropic$2$10Not disclosed$0.025$250platform.claude.comBase input / output
Claude Sonnet 5Anthropic$2$10Not disclosed$0.025$250platform.claude.comIntroductory price made standard; planned rise to $3/$15 on Sep 1, 2026 will not occur
Claude Haiku 4.5Anthropic$1$5Not disclosed$0.013$125platform.claude.comBase input / output
Claude Haiku 5.5Anthropic$0.10$0.50Not disclosed$0.001$12.50platform.claude.comPrompts <=100k tokens; $0.50/$2.50 above 100k
Gemini 4 CarbonGoogle$2$10Not disclosed$0.025$250ai.google.devPaid tier through Nov 30, 2026; $4/$20 from Dec 1, 2026
Gemini 4 ArgonGoogle$2$10Not disclosed$0.025$250ai.google.devPaid tier through Nov 30, 2026; $4/$20 from Dec 1, 2026
Gemini 3.1 Pro PreviewGoogle$2$12Not disclosed$0.026$262ai.google.devPrompts <=200k; $4/$18 above 200k
Gemini 4 HydrogenGoogle$1.50$7.50Not disclosed$0.019$188ai.google.devPaid tier
Gemini 2.5 ProGoogle$1.25$10Not disclosed$0.018$179ai.google.devPrompts <=200k
Gemini 3.8 FlashGoogle$0.75$3.75Not disclosed$0.009$93.75ai.google.devThrough Dec 31, 2026; $1.50/$7.50 from Jan 1, 2027
Gemini 3.6 FlashGoogle$0.75$3.75Not disclosed$0.009$93.75ai.google.devThrough Dec 31, 2026; $1.50/$7.50 from Jan 1, 2027
Gemini 3 Flash PreviewGoogle$0.50$3Not disclosed$0.007$65.50ai.google.devPaid tier
Gemini 3.5 Flash-LiteGoogle$0.30$2.50Not disclosed$0.004$43.50ai.google.devPaid tier
Gemini 2.5 FlashGoogle$0.30$2.50Not disclosed$0.004$43.50ai.google.devPaid tier
Gemini 3.1 Flash-LiteGoogle$0.25$1.50Not disclosed$0.003$32.75ai.google.devPaid tier
Gemini 2.5 Flash-LiteGoogle$0.10$0.40Not disclosed$0.001$11.90ai.google.devPaid tier
deepseek-v4-pro (V4-Pro)DeepSeek$1.32$3.96$0.044$0.015$149api-docs.deepseek.comPeak hours (cache miss); off-peak $0.66/$1.98
deepseek-flash (V4.1-Flash)DeepSeek$0.30$1.20$0.006$0.004$35.70api-docs.deepseek.comPeak hours (cache miss); off-peak is half: $0.15/$0.60
grok-4.7xAI$2$6$0.50$0.023$226docs.x.aiPrompts <200k tokens; prices double at 200k+
grok-4.6xAI$2$6Not disclosed$0.023$226docs.x.aiPer page
grok-4.5xAI$2$6Not disclosed$0.023$226docs.x.aiPer page
grok-4.3xAI$1.25$2.50Not disclosed$0.013$134docs.x.aiPer page
grok-4.20-0309xAI$1.25$2.50Not disclosed$0.013$134docs.x.aiReasoning and non-reasoning
grok-build-0.1xAI$1$2Not disclosed$0.011$107docs.x.aiPer page
Mistral Large 4Mistral$0.70$2.10$0.07$0.008$79.10docs.mistral.aiModel page; note mistral.ai/pricing FAQ states $0.5 in / $1.5 out for Mistral Large
Ministral 3 14BMistral$0.20$0.20Not disclosed$0.002$20.20docs.mistral.aiModel page
Mistral Small 4Mistral$0.15$0.60Not disclosed$0.002$17.85docs.mistral.aiModel page shows $0.15 /M and $0.6 /M; labels are tooltips, read as input then output
Ministral 3 8BMistral$0.15$0.15Not disclosed$0.002$15.15docs.mistral.aiModel page
Ministral 3 3BMistral$0.10$0.10Not disclosed$0.001$10.10docs.mistral.aiModel page
kimi-k2.5Cloudflare Workers AI$0.60$3Not disclosed$0.007$75.00developers.cloudflare.comNeuron-based billing
nemotron-3-120bCloudflare Workers AI$0.50$1.50Not disclosed$0.006$56.50developers.cloudflare.comNeuron-based billing
mistral-small-3.1-24bCloudflare Workers AI$0.351$0.555Not disclosed$0.004$36.68developers.cloudflare.comNeuron-based billing
gpt-oss-120bCloudflare Workers AI$0.35$0.75Not disclosed$0.004$37.75developers.cloudflare.comNeuron-based billing
deepseek-v4.1-flash-1017Cloudflare Workers AI$0.30$1.20Not disclosed$0.004$35.70developers.cloudflare.comNeuron-based billing
llama-3.3-70b-instruct-fp8-fastCloudflare Workers AI$0.293$2.253Not disclosed$0.004$41.35developers.cloudflare.comNeuron-based billing
llama-4-scout-17b-16e-instructCloudflare Workers AI$0.27$0.85Not disclosed$0.003$30.75developers.cloudflare.comNeuron-based billing
gpt-oss-20bCloudflare Workers AI$0.20$0.30Not disclosed$0.002$20.80developers.cloudflare.comNeuron-based billing
gemma-4-26b-a4b-itCloudflare Workers AI$0.10$0.30Not disclosed$0.001$11.30developers.cloudflare.comNeuron-based billing
glm-4.7-flashCloudflare Workers AI$0.06$0.40Not disclosed$0.0008$8.10developers.cloudflare.comNeuron-based billing
qwen3-30b-a3b-fp8Cloudflare Workers AI$0.051$0.335Not disclosed$0.0007$6.86developers.cloudflare.comNeuron-based billing
llama-3.1-8b-instruct-fp8-fastCloudflare Workers AI$0.045$0.384Not disclosed$0.0007$6.58developers.cloudflare.com$0.011 per 1,000 neurons; 10,000 neurons/day free
llama-3.2-1bCloudflare Workers AI$0.027$0.201Not disclosed$0.0004$3.77developers.cloudflare.comNeuron-based billing
granite-4.0-h-microCloudflare Workers AI$0.017$0.112Not disclosed$0.0002$2.29developers.cloudflare.comNeuron-based billing
qwen3.8-27bGroq$0.80$4Not disclosed$0.010$100console.groq.comOn-demand
gpt-oss-120bGroq$0.15$0.60Not disclosed$0.002$17.85console.groq.comOn-demand
gpt-oss-20bGroq$0.075$0.30Not disclosed$0.0009$8.92console.groq.comOn-demand
Kimi K3Together AI$3$15Not disclosed$0.037$375together.aiServerless
Qwen3.7-MaxTogether AI$2.50$7.50Not disclosed$0.028$282together.aiServerless
GLM-5.3Together AI$1.40$4.40Not disclosed$0.016$159together.aiServerless
DeepSeek V4.1 FlashTogether AI$0.30$1.20Not disclosed$0.004$35.70together.aiServerless
gpt-oss-120BTogether AI$0.15$0.60Not disclosed$0.002$17.85together.aiServerless

Cost per 10,000 support conversations

Cost of 10,000 support conversations, by model (log scale)Cheapest: granite-4.0-h-micro (Cloudflare Workers AI): $2.29; gpt-5-nano (OpenAI): $7.15; deepseek-flash (V4.1-Flash) (DeepSeek): $35.70; gpt-5-mini (OpenAI): $35.75; Median of all 81 models: $100; Claude Haiku 4.5 (Anthropic): $125; gpt-6.1-sol (OpenAI): $250; Gemini 4 Carbon (Google): $250; Priciest: gpt-5.5-pro (OpenAI): $3,930Cheapest: granite-4.0-h-micro (Cloudflare Workers AI)$2.29gpt-5-nano (OpenAI)$7.15deepseek-flash (V4.1-Flash) (DeepSeek)$35.70gpt-5-mini (OpenAI)$35.75Median of all 81 models$100Claude Haiku 4.5 (Anthropic)$125gpt-6.1-sol (OpenAI)$250Gemini 4 Carbon (Google)$250Priciest: gpt-5.5-pro (OpenAI)$3,930
Cost of 10,000 four-turn support conversations at list price (9,500 input + 600 output tokens each). Log scale.
Anthropic Opus list price per 1M input tokens, by generationOpus 4 / 4.1: $15 in / $75 out; Opus 4.5 to 5: $5 in / $25 out; Opus 5.5: $4 in / $20 outClaude Opus 4 / 4.1$15 in / $75 outClaude Opus 4.5 to 5$5 in / $25 outClaude Opus 5.5$4 in / $20 out
Claude Opus list price per 1M tokens by generation, as listed on Anthropic's pricing page

Price changes

We only list changes the provider's own page states (scheduled increases, promotions ending, renamed tiers). We don't reconstruct history from third-party sites.

Price changes stated on the official pricing pages (we list only changes the provider itself states).
ModelBeforeAfterSource
30 Jul 2026OpenAIAll models (Priority processing)Tier renamedPriority processingRenamed Fast modedevelopers.openai.com
1 Sep 2026AnthropicClaude Sonnet 5Planned increase cancelled$2 / $10 (introductory)$2 / $10 (now standard; planned $3 / $15 cancelled)platform.claude.com
30 Nov 2026OpenAIgpt-5.6-solPromotion ends$4 / $20 (promotional)Not disclosed on the pagedevelopers.openai.com
1 Dec 2026GoogleGemini 4 Carbon / Gemini 4 ArgonScheduled increase$2.00 / $10.00$4.00 / $20.00ai.google.dev
1 Jan 2027GoogleGemini 3.8 Flash / Gemini 3.6 FlashScheduled increase$0.75 / $3.75$1.50 / $7.50ai.google.dev
OngoingDeepSeekdeepseek-flash, deepseek-v4-proTime-of-day pricingPeak price50% off outside peak hours (01:00-04:00 and 06:00-10:00 UTC, Mon-Fri are peak)api-docs.deepseek.com

Methodology

Provider notes from the official pages:

Limitations

Download the data

Licensed under CC BY 4.0. Credit "Litmiq, State of LLM API Pricing 2026" and link to this page.

Cite this

Text

Litmiq (2026). State of LLM API Pricing 2026 [Data set]. Sources read 12 Nov 2026. https://litmiq.com/llm-api-pricing. License: CC BY 4.0.

BibTeX

@misc{litmiq_llm_api_pricing_2026,
  title        = {State of LLM API Pricing 2026},
  author       = {{Litmiq}},
  year         = {2026},
  month        = nov,
  note         = {Official list prices for 81 LLM API models from 9 providers. Sources read 2026-11-12. License: CC BY 4.0},
  howpublished = {\url{https://litmiq.com/llm-api-pricing}}
}

Link

<a href="https://litmiq.com/llm-api-pricing">State of LLM API Pricing 2026</a>

FAQ

What is the cheapest LLM API in 2026?

Among the 81 models we read on 12 Nov 2026, the lowest list price for our 4-turn support conversation was granite-4.0-h-micro on Cloudflare Workers AI, at $2.29 per 10,000 conversations. Price isn't quality, though: run your own test cases before you switch.

How much does an AI customer support conversation cost?

With our default assumptions (2,000-token system prompt, 4 turns, 9,500 input and 600 output tokens), list-price cost ranges from $0.0002 to $0.39 per conversation across 81 models. The median is $0.010. Use the calculator with your own token counts.

Why does input cost more than output in a chatbot?

Every turn resends the system prompt and the conversation so far, so input tokens add up fast. On a $2 / $10 model, input is 76% of the bill in our default conversation, even though output is 5 times the price per token. Shorter system prompts and prompt caching cut cost the most.

Are these prices official?

Yes. Each row links to the provider's own pricing or model page, read on 12 Nov 2026. Where a page does not list a cached-input price, we show "Not disclosed", not zero. Prices change; check the source before you buy.

Which LLM prices are changing soon?

Google's pricing page lists increases for Gemini 4 Carbon and Argon (to $4 / $20 from 1 Dec 2026) and Gemini 3.8 / 3.6 Flash (to $1.50 / $7.50 from 1 Jan 2027). OpenAI's page says gpt-5.6-sol promotional pricing ends 30 Nov 2026.

Can I reuse this data?

Yes, under CC BY 4.0. Credit "Litmiq, State of LLM API Pricing 2026" and link to this page.

Get model deprecation alerts

We email you when OpenAI, Anthropic or Google publish a new shutdown date for a model on our tracker. Sent by hand from hello@litmiq.com, a few times a month at most. Unsubscribe by replying.

We store only your email, through our form provider. See the privacy policy.

Test the cheaper model before you switch

Run your own support prompt on real test cases and compare replies side by side. Free, in your browser.

  • Free, no signup
  • Runs in your browser
  • Your OpenAI key, sent only to OpenAI

Follow Litmiq on LinkedIn