Python 88.3%
TypeScript 7.6%
Shell 4.1%
1# Anthropic pricing (Claude API)23**Status:** `DOCUMENTED` (prices are not verifiable by API; the 5 minimal live calls of this run are consistent with the documented `usage` shape). All prices USD. 4**Sources:** https://platform.claude.com/docs/en/about-claude/pricing · models/overview · models/*/overview · build-with-claude/fast-mode · build-with-claude/prompt-caching · manage-claude/data-residency · agents-and-tools/tool-use/{web-search-tool,web-fetch-tool,code-execution-tool} · api/service-tiers · release-notes/overview (retrieved 2026-09-18). 5**Last verified:** 2026-09-18 · Machine-readable: `generated/fragments/pricing/anthropic-pricing.json`.67## 1. Model token prices (per MTok)89| Model | Base input | 5m cache write (1.25x) | 1h cache write (2x) | Cache read | Output | Batch in / out (50%) |10|---|---|---|---|---|---|---|11| Claude Fable 5.1 | 10 | 12.50 | 20 | **0.25** (0.025x) | 50 | 5 / 25 |12| Claude Mythos 5.1 (invite only) | 10 | 12.50 | 20 | **0.25** (0.025x) | 50 | 5 / 25 |13| Claude Fable 5 | 10 | 12.50 | 20 | 1.00 | 50 | 5 / 25 |14| Claude Mythos 5 (invite only) | 10 | 12.50 | 20 | 1.00 | 50 | 5 / 25 |15| Claude Opus 5 | 5 | 6.25 | 10 | 0.50 | 25 | 2.50 / 12.50 |16| Claude Opus 4.8 | 5 | 6.25 | 10 | 0.50 | 25 | 2.50 / 12.50 |17| Claude Opus 4.7 | 5 | 6.25 | 10 | 0.50 | 25 | 2.50 / 12.50 |18| Claude Opus 4.6 | 5 | 6.25 | 10 | 0.50 | 25 | 2.50 / 12.50 |19| Claude Opus 4.5 | 5 | 6.25 | 10 | 0.50 | 25 | 2.50 / 12.50 |20| Claude Opus 4.1 (retired; Bedrock/Google Cloud only) | 15 | 18.75 | 30 | 1.50 | 75 | 7.50 / 37.50 |21| Claude Opus 4 (retired; Google Cloud only) | 15 | 18.75 | 30 | 1.50 | 75 | 7.50 / 37.50 |22| Claude Sonnet 5 | **2** | 2.50 | 4 | 0.20 | **10** | 1 / 5 |23| Claude Sonnet 4.6 | 3 | 3.75 | 6 | 0.30 | 15 | 1.50 / 7.50 |24| Claude Sonnet 4.5 | 3 | 3.75 | 6 | 0.30 | 15 | 1.50 / 7.50 |25| Claude Sonnet 4 (retired; Bedrock/Google Cloud) | 3 | 3.75 | 6 | 0.30 | 15 | 1.50 / 7.50 |26| Claude Haiku 4.5 | 1 | 1.25 | 2 | 0.10 | 5 | 0.50 / 2.50 |27| Claude Haiku 3.5 (retired; Bedrock/Google Cloud) | 0.80 | 1.00 | 1.60 | 0.08 | 4 | 0.40 / 2 |2829Notes30- Sonnet 5's introductory $2/$10 became the standard price on 2026-08-10 (the planned $3/$15 increase on 2026-09-01 was cancelled).31- Cache reads: 0.1x base input on every model except Fable 5.1 / Mythos 5.1 (0.025x since 2026-09-01). Caching pays off after 1 read (5m) or 2 reads (1h).32- Claude Mythos Preview and Claude 3.x models are not on the current pricing page (no price recorded).33- Tokenizer: Claude 4.7+ and Mythos Preview produce ~30% more tokens for the same text than Sonnet 4.6 and earlier — same per-token price, higher token count.3435## 2. Long context, data residency, clouds3637| Item | Price | Notes |38|---|---|---|39| 1M context (>200k input) | standard per-token price | Claude 4.6+ and Mythos Preview; no long-context premium; caching and batch discounts apply across the window. Pre-4.6 models are 200k. |40| `inference_geo: "us"` | ×1.1 on all token dimensions | Claude 4.6+ only (400 on earlier models); `"global"` = ×1.0. Also Foundry "US Data Zone Standard". |41| Bedrock / Vertex regional & multi-region endpoints | +10% over global endpoints | Sonnet 4.5, Haiku 4.5, Opus 4.5 and later; provider invoices. |42| Claude Platform on AWS / Microsoft Foundry | CCU at $0.01 (100 CCU = $1 of list price after discounts) | hourly metering to the marketplace; postpaid; same per-model rates. |4344## 3. Fast mode (research preview, Claude API only)4546| Model | Input | Output | Notes |47|---|---|---|---|48| Claude Opus 5, Claude Opus 4.8 | 10 | 50 | `speed: "fast"` + `anthropic-beta: fast-mode-2026-02-01`; applies across the full context window; caching (1.25x/2x/0.1x) and `inference_geo` (1.1x) multipliers stack on top; not available on Batch or on any cloud. |49| Claude Opus 4.7 | — | — | removed 2026-07-24: `speed: "fast"` → error |50| Claude Opus 4.6 | — | — | removed 2026-06-29: runs at standard speed and standard price; `usage.speed` = `"standard"` |5152## 4. Service tiers5354| Tier | Price effect | Notes |55|---|---|---|56| standard | list price | default |57| batch | 50% off input and output | Message Batches API; 24h window; stacks with caching |58| priority | same token price; capacity commitment | no longer sold; burndown of committed TPM: cache read 0.1, 5m write 1.25, 1h write 2.0, `inference_geo: us` 1.1 |59| fast | premium table above | Opus 5 / Opus 4.8 |6061## 5. Tools and features6263| Item | Price | Unit | Notes |64|---|---|---|---|65| Web search | 10 | per 1,000 searches | + tokens for results (counted as input in the turn and later turns); errors not billed; 1 search = 1 use regardless of results |66| Web fetch | 0 | — | only tokens of fetched content (~2,500 tok per 10 kB page, ~25k per 100 kB, ~125k per 500 kB PDF); cap with `max_content_tokens` |67| Code execution with `web_search_20260209+` / `web_fetch_20260209+` in the request | 0 | — | free (tokens only), since 2026-02-17 |68| Code execution standalone | 0.05 | per hour per container | after 1,550 free hours / org / month; 5-minute minimum; billed even if the tool isn't called when files are preloaded; `usage.server_tool_use.code_execution_requests` |69| Managed Agents session runtime | 0.08 | per session-hour | metered per ms while `running`; replaces container-hour billing; tokens at model rates; no batch discount; fast mode premium if `model.speed: fast`; ×1.1 if `model.inference_geo: us` |70| Token counting | 0 | — | own RPM limits |71| Files API | no storage price documented | — | ~500 RPM; optional `expires_in_seconds` |72| Claude Code | not on the platform pricing page | — | |7374### Token overheads (input tokens added per request)7576| Overhead | Tokens | Applies to |77|---|---|---|78| Tool-use system prompt, `tool_choice` auto/none → any/tool | Opus 5 286→406 · Opus 4.8 290→410 · Opus 4.7 675→804 · Opus 4.6 497→589 · Opus 4.5 496→588 · Opus 4.1/Opus 4/Sonnet 4 313→315 · Sonnet 5 354→474 · Sonnet 4.6 497→589 · Sonnet 4.5 496→588 · Haiku 4.5 496→588 · Haiku 3.5 264→355 | any request with ≥1 tool (`none` with no tools = 0) |79| `bash_20250124` definition | 325 (Opus 5/4.8/4.7) · 244 (Opus 4.6, Sonnet 4.6 and earlier) | + command output tokens |80| `text_editor_20250429` (Claude 4.x) | 700 | |81| `computer_toolset_20260801` (default members) | ~4,500 (~4,520 Fable 5/Mythos 5/Opus 5/Opus 4.8; ~4,590 Sonnet 5); −~410 if `zoom` disabled | screenshots/zoom images billed as image input |82| `computer_20251124` / `computer_20250124` | ~735 per definition + 466–499 system prompt | |83| `browser_toolset_20260801` | ~6,600 (~6,610 / ~6,670 Sonnet 5); +~880 with all 4 optional members | |8485## 6. Billing facts86- Billing on actual monthly usage, USD, credit card or invoicing; small free credits for new users; volume/enterprise discounts negotiated.87- Spend caps per usage tier: Start $500, Build $1,000, Scale $200,000, Custom none (see rate-limits doc).88- Refusals: since 2026-06-02 a request that returns `stop_reason: "refusal"` before any output is not billed; `fallbacks` re-runs are billed at the fallback model's rate.89- Discounts stack: batch × caching × (fast) × data residency.90