AI model pricing

Current $/million-token pricing for every popular LLM, timestamped and sourced. Refreshed daily where a provider’s page can be parsed safely; otherwise checked by hand and left to age visibly rather than guessed.

Anthropic

Model	Input $/Mtok	Output $/Mtok	Verified	Source
`Claude Fable 5`	$10.00	$50.00	verified 2026-07-22	source
`Claude Opus 4.8`	$5.00	$25.00	verified 2026-07-22	source
`Claude Sonnet 5`	$2.00	$10.00	verified 2026-07-22	source
`Claude Haiku 4.5`	$1.00	$5.00	verified 2026-07-22	source

Claude Fable 5: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.19 — a Reelier replay of the same workflow: $0.00

Claude Opus 4.8: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.10 — a Reelier replay of the same workflow: $0.00

Claude Sonnet 5: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.04 — a Reelier replay of the same workflow: $0.00 (Introductory pricing in effect through 2026-08-31; standard pricing ($3/$15) takes over 2026-09-01.)

Claude Haiku 4.5: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.02 — a Reelier replay of the same workflow: $0.00

OpenAI

Model	Input $/Mtok	Output $/Mtok	Verified	Source
`GPT-5.6 Sol`	$5.00	$30.00	verified 2026-07-22	source
`GPT-5.6 Terra`	$2.50	$15.00	verified 2026-07-22	source
`GPT-5.6 Luna`	$1.00	$6.00	verified 2026-07-22	source

GPT-5.6 Sol: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.10 — a Reelier replay of the same workflow: $0.00

GPT-5.6 Terra: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.05 — a Reelier replay of the same workflow: $0.00

GPT-5.6 Luna: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.02 — a Reelier replay of the same workflow: $0.00

Google

Model	Input $/Mtok	Output $/Mtok	Verified	Source
`Gemini 3.1 Pro`	$2.00	$12.00	verified 2026-07-22	source
`Gemini 3.6 Flash`	$1.50	$7.50	verified 2026-07-22	source
`Gemini 3.5 Flash-Lite`	$0.30	$2.50	verified 2026-07-22	source

Gemini 3.1 Pro: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.04 — a Reelier replay of the same workflow: $0.00 (Tiered by prompt size; rate shown is the <=200k input-token tier (>200k is $4/$18).)

Gemini 3.6 Flash: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.03 — a Reelier replay of the same workflow: $0.00

Gemini 3.5 Flash-Lite: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.01 — a Reelier replay of the same workflow: $0.00

xAI

Model	Input $/Mtok	Output $/Mtok	Verified	Source
`Grok 4.5`	$2.00	$6.00	verified 2026-07-22	source

Grok 4.5: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.04 — a Reelier replay of the same workflow: $0.00 (Tiered by prompt size; rate shown is the <200k input-token tier (>=200k is $4/$12).)

Moonshot (Kimi)

Model	Input $/Mtok	Output $/Mtok	Verified	Source
`Kimi K3`	$3.00	$15.00	verified 2026-07-22	source
`Kimi K2.6`	$0.95	$4.00	verified 2026-07-22	source

Kimi K3: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.06 — a Reelier replay of the same workflow: $0.00 (Cache-miss input rate shown; cache-hit input is $0.30/Mtok.)

Kimi K2.6: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.02 — a Reelier replay of the same workflow: $0.00 (Cache-miss input rate shown; cache-hit input is $0.16/Mtok.)

DeepSeek

Model	Input $/Mtok	Output $/Mtok	Verified	Source
`DeepSeek V4 Pro`	$0.435	$0.87	verified 2026-07-22	source
`DeepSeek V4 Flash`	$0.14	$0.28	verified 2026-07-22	source

DeepSeek V4 Pro: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.01 — a Reelier replay of the same workflow: $0.00 (Cache-miss input rate shown; cache-hit input is $0.003625/Mtok.)

DeepSeek V4 Flash: a typical agent workflow (~18k tokens, the README benchmark) ≈ < $0.01 — a Reelier replay of the same workflow: $0.00 (Cache-miss input rate shown; cache-hit input is $0.0028/Mtok.)

Mistral

Model	Input $/Mtok	Output $/Mtok	Verified	Source
`Mistral Large 3`	$0.50	$1.50	verified 2026-07-22	source
`Mistral Medium 3.5`	$1.50	$7.50	verified 2026-07-22	source
`Mistral Small 4`	$0.15	$0.60	verified 2026-07-22	source

Mistral Large 3: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.01 — a Reelier replay of the same workflow: $0.00

Mistral Medium 3.5: a typical agent workflow (~18k tokens, the README benchmark) ≈ $0.03 — a Reelier replay of the same workflow: $0.00

Mistral Small 4: a typical agent workflow (~18k tokens, the README benchmark) ≈ < $0.01 — a Reelier replay of the same workflow: $0.00

Method

Every row is checked against the provider’s own pricing page, cited in the Source column. A daily cron re-fetches the pages with a reliable, defensively-parsed extractor (Anthropic and OpenAI today) and applies a guardrail before trusting a new number: a parse failure, or a parsed price more than 50% away from the currently stored price, leaves the number untouched and marks the row stale rather than writing a guess. Every other provider’s page doesn’t have a reliable-enough shape to auto-parse yet and is checked by hand — its “verified” date simply ages until the next manual check, which is the honest signal rather than a fabricated freshness.

The per-model cost is computed against one fixed assumption, stated once here: a benchmark agent run of 18,390 input tokens + 136 output tokens — the measured average from a real npm-registry agent workflow (N=10), the same number the cost calculator uses. Your workflows may be bigger or smaller; use the calculator to plug in your own numbers.

The $0.00 replay column isn’t a discount — Level-0 replay re-executes the recorded tool calls and never constructs an LLM client, so it spends 0 tokens by construction, verified from the run record on every replay (llmInputTokens === 0). See Level-0 (zero-token) replay.

Stop re-paying for the same run

npm i -g reelier && reelier init— record the run once, replay it on a schedule, keep the receipt.

Browse real replayable skills · Run your own numbers in the cost calculator