AI GateGet access

Anthropic

  • anthropic dialect
  • 11 models
  • San Francisco, USA

Anthropic builds the Claude family of models. Its Messages API is one of the handful of first-party dialects in the world — requests use a `system` field separate from `messages`, content blocks rather than plain strings, and a server-sent event stream of typed deltas. The gateway translates OpenAI-shaped requests into it and the response stream back out, byte by byte.

Docs ↗Status ↗Pricing ↗

  • 11models
  • $1cheapest / 1M in
  • 1Mlargest context
  • 122.70Btokens, 4 weeks

Anthropic tokens processed Sample data

Daily totals, 26 Apr 2026 – 24 Jul 2026

Chart requires JavaScript. The figures are in the table below.

  • Claude Sonnet 5
  • Claude Opus 5
  • Claude Haiku 4.5
  • Claude Sonnet 4.6
  • Claude Opus 4.8
  • Claude Fable 5
  • 5 more
Sample data. The gateway has not served production traffic yet, so these volumes are illustrative — the chart shows the shape the event-stream rollup will fill in. The final bar is hatched because that day is still in progress.
View as table
Daily tokens processed by Anthropic model
Model26 Apr27 Apr28 Apr29 Apr30 Apr1 May2 May3 May4 May5 May6 May7 May8 May9 May10 May11 May12 May13 May14 May15 May16 May17 May18 May19 May20 May21 May22 May23 May24 May25 May26 May27 May28 May29 May30 May31 May1 Jun2 Jun3 Jun4 Jun5 Jun6 Jun7 Jun8 Jun9 Jun10 Jun11 Jun12 Jun13 Jun14 Jun15 Jun16 Jun17 Jun18 Jun19 Jun20 Jun21 Jun22 Jun23 Jun24 Jun25 Jun26 Jun27 Jun28 Jun29 Jun30 Jun1 Jul2 Jul3 Jul4 Jul5 Jul6 Jul7 Jul8 Jul9 Jul10 Jul11 Jul12 Jul13 Jul14 Jul15 Jul16 Jul17 Jul18 Jul19 Jul20 Jul21 Jul22 Jul23 Jul24 Jul
Claude Sonnet 5235M344M392M435M444M414M266M250M367M418M463M472M438M281M265M390M444M491M499M463M297M280M413M469M519M526M487M312M295M436M496M547M553M511M328M310M459M522M575M580M535M343M325M482M548M603M607M559M359M340M505M574M631M634M583M374M355M528M601M659M661M607M389M370M552M627M687M687M630M404M386M575M654M715M714M654M419M401M599M681M743M740M677M434M416M623M708M771M767M266M
Claude Opus 5197M248M223M220M243M277M214M209M263M237M234M259M294M227M221M278M251M248M275M312M240M234M293M264M262M290M330M253M246M308M278M276M306M347M267M258M323M292M290M322M365M280M270M338M305M305M338M383M293M282M352M319M319M355M401M306M294M367M332M333M371M419M319M306M382M346M347M387M437M332M318M396M359M362M403M455M345M330M411M373M376M420M473M358M342M425M386M390M436M187M
Claude Haiku 4.5149M221M213M192M174M175M140M159M235M226M204M185M186M149M169M249M240M215M195M197M158M179M263M253M227M206M208M167M189M277M266M238M217M219M176M199M291M278M249M227M230M185M209M305M291M261M238M241M194M219M319M304M272M248M252M204M229M333M317M283M259M263M213M239M347M330M294M269M275M222M249M361M342M305M279M286M231M259M375M355M316M290M297M241M270M389M367M327M300M117M
Claude Sonnet 4.663M99M107M106M96M86M61M67M106M114M112M102M91M65M71M112M121M119M107M97M68M75M119M128M125M113M102M72M80M126M135M131M119M107M76M84M132M141M138M124M112M80M88M139M148M144M130M117M84M92M146M155M150M135M122M87M97M152M162M157M141M127M91M101M159M169M163M146M132M95M105M166M176M169M152M137M99M110M172M182M176M157M142M103M114M179M189M182M163M56M
Claude Opus 4.837M57M65M68M65M59M39M39M61M69M73M69M62M41M42M65M73M77M73M65M43M44M69M78M81M77M69M45M47M73M82M85M81M72M48M49M77M86M90M85M76M50M51M81M90M94M89M79M52M54M85M95M98M92M82M55M56M88M99M102M96M86M57M59M92M103M106M100M89M59M61M96M108M111M104M92M62M64M100M112M115M108M96M64M66M104M116M119M111M38M
Claude Fable 528M35M33M36M41M45M33M30M37M36M38M44M48M35M32M39M38M40M46M51M37M34M42M40M43M49M53M39M35M44M42M45M51M56M40M37M46M44M48M54M59M42M39M48M46M50M57M62M44M40M50M48M52M60M65M46M42M52M50M55M62M68M48M44M54M53M57M65M70M50M46M57M55M60M68M73M52M47M59M57M62M70M76M54M49M61M59M64M73M30M
5 more37M50M49M49M50M53M39M39M53M52M52M54M56M42M42M56M55M55M57M59M44M44M60M58M58M60M63M46M46M63M61M61M63M66M49M49M66M64M64M66M69M51M51M69M67M67M69M73M54M53M72M70M70M73M76M56M56M75M73M73M76M79M58M58M78M76M76M79M82M61M60M81M79M79M82M86M63M63M85M82M83M85M89M66M65M88M85M86M89M35M

Anthropic models

Prices and limits are the provider's published figures

  • Claude Opus 5

    • Text
    • Image
    10.30B tokens

    Claude Opus 5 is Anthropic's flagship model for complex agentic coding and enterprise work — a step change over Opus 4.8 on deep reasoning, long-horizon autonomy and test-time compute scaling, at the same price. Thinking is on by default and the full effort ladder runs from low through max, so you tune depth per request rather than per model. It holds a 1M-token context window and writes up to 128K tokens in a single response.

    by Anthropic1M context$5/M in$25/M out

  • Claude Sonnet 5

    • Text
    • Image
    16.93B tokens

    Claude Sonnet 5 is the workhorse: near-Opus quality on coding and agentic work at a third of the price, with adaptive thinking on by default and the full low-to-max effort range. It is the first Sonnet-tier model with high-resolution vision and xhigh effort. Introductory pricing of $2 in / $10 out per million tokens applies through 31 August 2026.

    by Anthropic1M context$3/M in$15/M out

  • Claude Haiku 4.5

    • Text
    • Image
    10.42B tokens

    Claude Haiku 4.5 is the cheapest and quickest model in the catalog — a dollar per million input tokens, with a 200K context window and a 64K output cap. It uses the older extended-thinking parameter rather than adaptive thinking, which makes it predictable to budget for. Built for the calls you make thousands of times an hour.

    by Anthropic1 Oct 2025200K context$1/M in$5/M out

  • Claude Fable 5

    • Text
    • Image
    1.48B tokens

    Claude Fable 5 is Anthropic's most capable widely released model, aimed at the most demanding reasoning and long-horizon agentic work. Thinking is always on — there is no way to disable it — and the raw chain of thought is never returned, only a summary. Single requests on hard tasks can run for many minutes, so plan for streaming and asynchronous check-ins rather than blocking calls.

    by Anthropic9 Jun 20261M context$10/M in$50/M out

  • Claude Opus 4.8

    • Text
    • Image
    2.79B tokens

    Claude Opus 4.8 is the previous Opus flagship — highly autonomous, strong on long-horizon agentic work, knowledge work and memory, with a noticeably warmer and less hedged writing voice than 4.7. Same request surface as Opus 5 minus the two Opus 5 breaking changes, which makes it the usual fallback target when a newer model declines a request.

    by Anthropic1M context$5/M in$25/M out

  • Claude Opus 4.7

    • Text
    • Image
    1.21B tokens

    Claude Opus 4.7 introduced the tokenizer, the xhigh effort level and the 2576-pixel high-resolution vision path that the newer models inherit. It follows instructions more literally than 4.6 and reaches for tools less often by default. Still callable and still strong on long-horizon agentic work.

    by Anthropic1M context$5/M in$25/M out

  • Claude Opus 4.6

    • Text
    • Image
    698.0M tokens

    Claude Opus 4.6 is the oldest Opus still in the current line. It is the last one that accepts temperature, top_p and top_k, and the last that still honours a manual thinking budget alongside adaptive thinking — useful if you need a hard ceiling on thinking spend while you migrate. 1M context, 128K output.

    by Anthropic1M context$5/M in$25/M out

  • Claude Sonnet 4.6

    • Text
    • Image
    5.45B tokens

    Claude Sonnet 4.6 keeps a 1M-token context window and a 128K output cap at $3 in / $15 out, with adaptive thinking and the older tokenizer. Because the Sonnet 5 tokenizer counts roughly 30% more tokens for the same text, 4.6 is still the cheaper option for some long-context workloads even at identical sticker prices.

    by Anthropic1M context$3/M in$15/M out

  • Claude Opus 4.5

    • Text
    • Image
    310.0M tokens

    Claude Opus 4.5 is a legacy model that remains callable. It predates adaptive thinking, so it uses an explicit thinking budget, and it caps at a 200K context window with 64K of output. It was the first model to ship the effort parameter, limited to low, medium and high.

    by Anthropic1 Nov 2025200K context$5/M in$25/M out

  • Claude Sonnet 4.5

    • Text
    • Image
    565.0M tokens

    Claude Sonnet 4.5 is a legacy model that remains callable, with a 200K context window, 64K output cap and manual extended thinking. It has no effort parameter — asking for one is an error — so depth is controlled purely by the thinking budget you set.

    by Anthropic29 Sept 2025200K context$3/M in$15/M out

  • Claude Opus 4.1

    • Text
    • Image
    • Retiring
    125.0M tokens

    Claude Opus 4.1 is deprecated and will stop answering on 5 August 2026. It is also the most expensive model in the catalog at $15 in / $75 out per million tokens — three times the price of Opus 5 for a 200K context window and a 32K output cap. Migrate to Claude Opus 5 before the retirement date.

    by Anthropic5 Aug 2025200K context$15/M in$75/M out

Compare against the whole catalog on all models, or see what gets used in the rankings.