stack everyday.
English

Token prices(USD/1M tokens)

USD / 1M tokens
ModelInputOutputCached inputSource
gpt-6-astraOpenAI $10.00$50.00$1.00Source Oct 10
gpt-6.1-solOpenAI $2.00$10.00$0.10Source Oct 10
gpt-6-lunaOpenAI $0.10$0.50$0.01Source Oct 10
gpt-5.6-solOpenAI $4.00$20.00$0.40Source Oct 10
Claude Fable 5.1Anthropic $10.00$50.00$0.25Source Oct 10
Claude Opus 5.5Anthropic $4.00$20.00$0.20Source Oct 10
Claude Sonnet 5.5Anthropic $2.00$10.00$0.10Source Oct 10
Claude Haiku 5.5Anthropic $0.10$0.50$0.01Source Oct 10
Claude Mythos 5.1Anthropic $10.00$50.00$0.25Source Oct 10
Claude Fable 5Anthropic $10.00$50.00$1.00Source Oct 10
Claude Mythos 5Anthropic $10.00$50.00$1.00Source Oct 10
Claude Opus 5Anthropic $5.00$25.00$0.50Source Oct 10
Claude Opus 4.8Anthropic $5.00$25.00$0.50Source Oct 10
Claude Opus 4.7Anthropic $5.00$25.00$0.50Source Oct 10
Claude Opus 4.6Anthropic $5.00$25.00$0.50Source Oct 10
Claude Opus 4.5Anthropic $5.00$25.00$0.50Source Oct 10
Claude Opus 4.1Anthropic $15.00$75.00$1.50Source Oct 10
Claude Opus 4Anthropic $15.00$75.00$1.50Source Oct 10
Claude Sonnet 5Anthropic $2.00$10.00$0.20Source Oct 10
Claude Sonnet 4.6Anthropic $3.00$15.00$0.30Source Oct 10
Claude Sonnet 4.5Anthropic $3.00$15.00$0.30Source Oct 10
Claude Sonnet 4Anthropic $3.00$15.00$0.30Source Oct 10
Claude Haiku 4.5Anthropic $1.00$5.00$0.10Source Oct 10
Claude Haiku 3.5Anthropic $0.80$4.00$0.08Source Oct 10
grok-4.7xAI $2.00$6.00$0.50Source Oct 10
grok-build-0.1xAI $1.00$2.00$0.20Source Oct 10
grok-4.6xAI $2.00$6.00$0.50Source Oct 10
grok-4.5xAI $2.00$6.00$0.30Source Oct 10
grok-4.3xAI $1.25$2.50$0.20Source Oct 10
grok-4.20-multi-agent-0309xAI $1.25$2.50$0.20Source Oct 10
grok-4.20-0309-reasoningxAI $1.25$2.50$0.20Source Oct 10
grok-4.20-0309-non-reasoningxAI $1.25$2.50$0.20Source Oct 10
gemini-3.8-flashGoogle $0.75$3.75$0.075Source Oct 10
gemini-3.6-flashGoogle $0.75$3.75$0.075Source Oct 10
gemini-3.5-flash-liteGoogle $0.30$2.50$0.03Source Oct 10
gemini-3.1-flash-liteGoogle $0.25$1.50$0.025Source Oct 10
gemini-3.1-pro-previewGoogle $2.00$12.00$0.20Source Oct 10
gemini-3.1-pro-preview-customtoolsGoogle $2.00$12.00$0.20Source Oct 10
gemini-3-flash-previewGoogle $0.50$3.00$0.05Source Oct 10
gemini-2.5-proGoogle $1.25$10.00$0.125Source Oct 10
gemini-2.5-flashGoogle $0.30$2.50$0.03Source Oct 10
gemini-2.5-flash-liteGoogle $0.10$0.40$0.01Source Oct 10
gemini-robotics-er-2-previewGoogle $1.00$5.00$0.10Source Oct 10
deepseek-flashDeepSeek $0.30$1.20$0.006Source Oct 10
deepseek-v4-proDeepSeek $1.32$3.96$0.044Source Oct 10
kimi-k3Kimi $3.00$15.00$0.30Source Oct 10
kimi-k2.7-codeKimi $0.95$4.00$0.19Source Oct 10
kimi-k2.7-code-highspeedKimi $1.90$8.00$0.38Source Oct 10
kimi-k2.6Kimi $0.95$4.00$0.16Source Oct 10

Standard API rates. Taxes, tools and subscriptions excluded.

Context

gpt-6-astra · Short-context, standard tier; consult source for thresholds.

gpt-6.1-sol · Short-context, standard tier; consult source for thresholds.

gpt-6-luna · Short-context, standard tier; consult source for thresholds.

gpt-5.6-sol · Short-context, standard tier; consult source for thresholds.

Claude Fable 5.1 · Base API rate; context-dependent rows are excluded.

Claude Opus 5.5 · Base API rate; context-dependent rows are excluded.

Claude Sonnet 5.5 · Base API rate; context-dependent rows are excluded.

Claude Haiku 5.5 · Base API rate; context-dependent rows are excluded.

Claude Mythos 5.1 · Base API rate; context-dependent rows are excluded.

Claude Fable 5 · Base API rate; context-dependent rows are excluded.

Claude Mythos 5 · Base API rate; context-dependent rows are excluded.

Claude Opus 5 · Base API rate; context-dependent rows are excluded.

Claude Opus 4.8 · Base API rate; context-dependent rows are excluded.

Claude Opus 4.7 · Base API rate; context-dependent rows are excluded.

Claude Opus 4.6 · Base API rate; context-dependent rows are excluded.

Claude Opus 4.5 · Base API rate; context-dependent rows are excluded.

Claude Opus 4.1 · Base API rate; context-dependent rows are excluded.

Claude Opus 4 · Base API rate; context-dependent rows are excluded.

Claude Sonnet 5 · Base API rate; context-dependent rows are excluded.

Claude Sonnet 4.6 · Base API rate; context-dependent rows are excluded.

Claude Sonnet 4.5 · Base API rate; context-dependent rows are excluded.

Claude Sonnet 4 · Base API rate; context-dependent rows are excluded.

Claude Haiku 4.5 · Base API rate; context-dependent rows are excluded.

Claude Haiku 3.5 · Base API rate; context-dependent rows are excluded.

grok-4.7 · Global endpoint, below 200k prompt tokens.

grok-build-0.1 · Global endpoint, below 200k prompt tokens.

grok-4.6 · Global endpoint, below 200k prompt tokens.

grok-4.5 · Global endpoint, below 200k prompt tokens.

grok-4.3 · Global endpoint, below 200k prompt tokens.

grok-4.20-multi-agent-0309 · Global endpoint, below 200k prompt tokens.

grok-4.20-0309-reasoning · Global endpoint, below 200k prompt tokens.

grok-4.20-0309-non-reasoning · Global endpoint, below 200k prompt tokens.

gemini-3.8-flash · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage. input: $0.75 through December 31, 2026. $1.50 starting January 1, 2027. output: $3.75 through December 31, 2026. $7.50 starting January 1, 2027. cachedInput: $0.075 through December 31, 2026. $0.15 starting January 1, 2027.

gemini-3.6-flash · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage. input: $0.75 through December 31, 2026. $1.50 starting January 1, 2027. output: $3.75 through December 31, 2026. $7.50 starting January 1, 2027. cachedInput: $0.075 through December 31, 2026. $0.15 starting January 1, 2027.

gemini-3.5-flash-lite · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage.

gemini-3.1-flash-lite · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage.

gemini-3.1-pro-preview · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage. Base prices apply to prompts <= 200,000 tokens; long prices apply to prompts > 200,000 tokens.

gemini-3.1-pro-preview-customtools · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage. Base prices apply to prompts <= 200,000 tokens; long prices apply to prompts > 200,000 tokens.

gemini-3-flash-preview · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage.

gemini-2.5-pro · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage. Base prices apply to prompts <= 200,000 tokens; long prices apply to prompts > 200,000 tokens.

gemini-2.5-flash · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage.

gemini-2.5-flash-lite · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage.

gemini-robotics-er-2-preview · Standard paid text rates, USD per 1M tokens. Output includes thinking tokens; excludes audio rates, tools and cache storage. input: $1.00 (text / image / video / audio) through December 31, 2026. $2.00 (text / image / video / audio) starting January 1, 2027. output: $5.00 through December 31, 2026. $10.00 starting January 1, 2027. cachedInput: $0.10 through December 31, 2026. $0.20 starting January 1, 2027.

deepseek-flash · Peak-hour rate. Off-peak rates are half these rates; see official UTC hours.

deepseek-v4-pro · Peak-hour rate. Off-peak rates are half these rates; see official UTC hours.

kimi-k3 · Standard API price excluding taxes, cache writes and tools.

kimi-k2.7-code · Standard API price excluding taxes, cache writes and tools.

kimi-k2.7-code-highspeed · Standard API price excluding taxes, cache writes and tools.

kimi-k2.6 · Standard API price excluding taxes, cache writes and tools.

Estimate token cost

Estimated cost—

Token-only estimate, not an actual task bill. Extra tool calls and retries are excluded.

Value for money →

Frequently asked questions

More
What unit are AI token prices quoted in?

Prices are US dollars per one million tokens. Input, output and cached input are separate rates. These are API prices, not ChatGPT, Claude or Grok subscription fees.

How is an API request cost calculated?

Multiply each token count by its matching rate, add the amounts, then divide by one million. Cached input replaces part of the input count; it is not counted twice. The calculator uses verified rates and shows unknown when a required rate is unavailable.

Does changing a model change the table order?

On the home comparison table, selecting a model updates only that provider row. Click an input or output column arrow to sort explicitly. A low input price does not necessarily mean a low total cost.

Can I assume every input token is billed at the cached price?

No. A listed cached rate does not guarantee a cache hit. Use cached billing only for input covered by the provider’s cache rules. The calculator requires cached input to be no greater than total input and does not assume a discount when its rate is unknown.

Can the token price change for a long context?

Some published pricing conditions distinguish context lengths or other request settings. Check the context notes and source for the selected model. The calculator uses a recorded long-context rate when available; it does not invent a missing rate.

Is the model with the cheapest input always cheapest overall?

No. Total cost depends on input, output and applicable cached tokens. A model with cheap input but expensive output may cost more for a long answer. Enter your expected token counts in the calculator and compare the rates separately.