Tag: AI Models 2026

  • Claude vs GPT-5 vs Gemini: 2026 Coding Benchmarks

    Claude vs GPT-5 vs Gemini: 2026 Coding Benchmarks

    Last verified: June 13, 2026

    As of June 13, 2026, the four models most often compared for coding work are Claude Fable 5 and Claude Opus 4.8 from Anthropic, GPT-5.5 from OpenAI, and Gemini 3.1 Pro from Google. This page is a leaderboard built on one rule: every score below is taken from a vendor’s own page or the benchmark’s official model card that we fetched on the verification date, or it is marked as not published. Several vendors publish their benchmark tables as images rather than machine-readable text; where we could not read an official figure directly, we list the metric as not machine-verifiable and link to the source document instead of estimating. The result is a smaller table than most roundups, but every number in it is one you can click through and check.

    Models and pricing (verified specs)

    Three cards: coding depth, latency first, agent reliability
    Models compared — verified specs without sticky dollars.

    These columns are confirmed from each vendor’s official model documentation. Claude prices, context windows, and cutoffs come from Anthropic’s models overview and the AWS Bedrock model card; GPT-5.5 from OpenAI’s developer docs; Gemini 3.1 Pro from Google’s DeepMind model card and the Gemini API pricing page.

    ModelAPI IDInput / Output (per Mtok)ContextMax outputKnowledge cutoff
    Claude Fable 5claude-fable-5$10 / $501M128KNot stated on overview*
    Claude Opus 4.8claude-opus-4-8$5 / $251M128KJan 2026
    GPT-5.5gpt-5.5$5 / $301,050,000128KDec 1, 2025
    Gemini 3.1 Progemini-3.1-pro-preview$2 / $12 (≤200K)**1M64KNot stated on model card

    *Anthropic’s models overview lists Fable 5’s specs and price but does not publish a knowledge-cutoff date for it in the table we fetched. **Gemini 3.1 Pro uses tiered pricing: $2 / $12 per Mtok for prompts up to 200K tokens, rising to $4 / $18 for prompts above 200K tokens (Google AI pricing page). GPT-5.5 pricing rises to 2x input / 1.5x output above 272K input tokens (OpenAI developer docs). Claude Opus 4.8 offers an optional fast mode at $10 / $50 per Mtok (Anthropic).

    Coding benchmark scores (primary-source only)

    Three abstract product cards on a desk comparing Claude with other chat API offerings
    Coding benchmark scores — primary-source only.

    Each cell is either a figure we read directly from a primary source on June 13, 2026, or marked “not machine-verifiable” with the source you should consult. A blank-equivalent entry never means zero — it means the official figure was not available in readable form during verification. Note the harness and version differences called out in the footnotes: they make cross-vendor cells not strictly comparable.

    BenchmarkClaude Fable 5Claude Opus 4.8GPT-5.5Gemini 3.1 Pro
    SWE-bench VerifiedNot machine-verifiable (see system card)Not machine-verifiable (see system card)Not published in retrievable primary source80.6%
    SWE-bench Pro (Public)Not machine-verifiable (see system card)Not machine-verifiable (see system card)Not published in retrievable primary source54.2%
    Terminal-BenchNot machine-verifiable (see system card)Not machine-verifiable (see system card)83.4% (v2.1, Codex CLI harness)†68.5% (v2.0, Terminus-2 harness)
    LiveCodeBench ProNot published in retrievable primary sourceNot published in retrievable primary sourceNot published in retrievable primary source2887 Elo

    †GPT-5.5’s Terminal-Bench 2.1 figure of 83.4% is the score Anthropic attributes to GPT-5.5 “with the Codex CLI harness” in a footnote on its Claude Opus 4.8 announcement page. It is a competitor-reported comparison, not a number we read from OpenAI directly. Google reports Gemini 3.1 Pro on Terminal-Bench 2.0 under the Terminus-2 harness (68.5%); because the version and harness differ, the Gemini and GPT-5.5 Terminal-Bench cells are not directly comparable. Gemini’s SWE-bench Verified (80.6%), SWE-bench Pro Public (54.2%), and LiveCodeBench Pro (2887 Elo) are single-attempt figures from Google’s official Gemini 3.1 Pro model card.

    What we could not verify from a primary source

    Anthropic publishes its coding comparison tables for Claude Opus 4.8 and Claude Fable 5 as images inside its announcement pages, and the full Claude Opus 4.8 System Card PDF exceeded our fetch size limit, so we could not machine-read those percentages on the verification date. OpenAI’s GPT-5.5 announcement page returned an access error to our fetcher, and its developer-docs model page lists specs and pricing but no benchmark scores. We have therefore left Claude’s and GPT-5.5’s SWE-bench figures out of the table rather than reproduce numbers we could not confirm at the source. For those figures, consult the primary documents linked in our source list: the Claude Opus 4.8 System Card, the Claude Fable 5 and Mythos 5 announcement, and OpenAI’s GPT-5.5 page. If you are choosing a model today, the verified spec table above (price, context, output, cutoff) is the part you can rely on without caveat.

    How to read a coding leaderboard

    Three cards for fast volume, daily workhorse, and deep flagship Claude seats
    How to read a coding leaderboard.

    Three cautions apply to any 2026 coding comparison. First, harness matters: the same model scores differently on Terminal-Bench depending on whether it runs under Terminus-2, a Codex CLI scaffold, or a vendor’s internal agent, which is why we annotate every Terminal-Bench cell. Second, version matters: “Terminal-Bench 2.0” and “Terminal-Bench 2.1” are different test sets, and “SWE-bench Pro” public and full splits differ — a single percentage with no version is close to meaningless. Third, a headline score is one slice of behavior; long-horizon agentic coding, tool-call reliability, and context handling over a long session often decide real-world usefulness more than a single pass rate. Treat the verified cells here as a starting point, then test the shortlist on your own repository.

    Which model has the highest published coding benchmark score in June 2026?

    We cannot crown a single winner from primary sources alone, because Anthropic and OpenAI publish their coding scores in formats we could not machine-verify on June 13, 2026. From figures we could read directly, Google’s Gemini 3.1 Pro model card reports 80.6% on SWE-bench Verified and 54.2% on SWE-bench Pro (Public). Anthropic’s and OpenAI’s comparable figures are in their system cards and announcement pages, which we link in the sources; we did not reproduce them here because they were not readable at the source during verification.

    What does Claude Fable 5 cost, and how is it different from Opus 4.8?

    Claude Fable 5 (claude-fable-5) is priced at $10 per million input tokens and $50 per million output tokens, with a 1M-token context window and up to 128K output tokens (Anthropic models overview). Claude Opus 4.8 (claude-opus-4-8) is the Opus-tier flagship at $5 / $25 per Mtok, also 1M context and 128K output, with a January 2026 knowledge cutoff. Fable 5 is Anthropic’s most capable widely released model; Opus 4.8 is the lower-priced model most teams will use for everyday agentic coding.

    Why are some benchmark cells marked “not machine-verifiable” instead of showing a number?

    Because this page only prints scores we could confirm from a primary source on the verification date. Several vendors render their benchmark tables as images, and one large system-card PDF exceeded our fetch limit, so the underlying percentages were not readable to us. Rather than copy figures from third-party trackers, we mark the cell and point you to the official document. It keeps the leaderboard honest at the cost of being shorter.

    How do the context windows compare?

    Claude Fable 5, Claude Opus 4.8, and Gemini 3.1 Pro each offer a 1M-token context window; GPT-5.5 offers 1,050,000 tokens. Maximum output is 128K tokens for Claude Fable 5, Claude Opus 4.8, and GPT-5.5, and 64K tokens for Gemini 3.1 Pro. Note that Claude Opus 4.8’s context window is 200K on Microsoft Foundry specifically, per Anthropic’s documentation.

    Is Terminal-Bench comparable across these models?

    Not cell-for-cell. Google reports Gemini 3.1 Pro on Terminal-Bench 2.0 under the Terminus-2 harness (68.5%), while the GPT-5.5 figure we show (83.4%) is Terminal-Bench 2.1 under a Codex CLI harness, as attributed by Anthropic. Different versions and different harnesses mean the two numbers should not be read as a head-to-head result.

    Related on Tygart Media: Claude Code vs Cursor · Claude Code vs Codex.

  • Migrating Off Retired Claude Models: The Breaking-Chang (2026)

    Migrating Off Retired Claude Models: The Breaking-Chang (2026)

    Last verified: June 13, 2026

    Claude Opus 4 (claude-opus-4-20250514) and Claude Sonnet 4 (claude-sonnet-4-20250514) are deprecated and retire on June 15, 2026, after which requests to them return a 404. The official replacements are claude-opus-4-8 and claude-sonnet-4-6. But swapping the model string alone will break a working integration: depending on which target you choose, several request parameters that were valid on the May 2025 models now return a 400 error, and two changes alter behavior silently. This page maps each removed or changed parameter to the exact failure and the fix.

    One distinction governs the whole migration. The Opus path (to claude-opus-4-8) is the strict one: it removes temperature/top_p/top_k and manual thinking budgets entirely. The Sonnet path (to claude-sonnet-4-6) is gentler: it keeps sampling parameters (with the older “one of temperature or top_p, not both” rule) and still accepts budget_tokens as deprecated-but-functional. The one rule both paths share: assistant-turn prefills now return 400.

    The breaking-change matrix

    Side-by-side panels contrasting old model IDs still in code with a migrate checklist
    The breaking-change matrix.

    Each row is a change that breaks on at least one migration target. “Error” means the API rejects the request server-side (HTTP 400) even though the SDK request type still type-checks. “Silent” means no error — the behavior simply differs.

    ChangeOn Opus 4.8On Sonnet 4.6SymptomFix
    thinking: {type:"enabled", budget_tokens:N}400 error (removed)Deprecated, still works400 on Opus; cost/latency drift on Sonnetthinking: {type:"adaptive"} + output_config.effort
    temperature / top_p / top_k400 error (removed)Keep only one of temperature or top_p400 on Opus if any set; 400 on Sonnet if both setRemove on Opus; steer via prompt. Keep one on Sonnet
    Assistant-turn prefill (last message role:"assistant")400 error400 errorRequest rejected on bothoutput_config.format (structured outputs) or system-prompt instruction
    thinking.display defaultDefaults to "omitted"Returns summarized textReasoning text empty on Opus (silent)Set display: "summarized" on Opus
    TokenizerNew tokenizer (more tokens)Unchanged tokenizerSame text counts higher on Opus; max_tokens too tightRe-baseline with count_tokens; add headroom
    output_format (top-level)Deprecated API-wideDeprecated API-wideWorks, but slated for removalMove to output_config: {format: {...}}

    Model ID swaps and retirement dates

    Flow from Family to Seat to Generation to API id
    Model ID swaps and retirement dates.
    Retiring modelModel IDRetiresReplacement
    Claude Opus 4claude-opus-4-20250514 (alias claude-opus-4-0)June 15, 2026claude-opus-4-8
    Claude Sonnet 4claude-sonnet-4-20250514 (alias claude-sonnet-4-0)June 15, 2026claude-sonnet-4-6

    These are the original May 2025 models, not the later Opus 4.6 or Sonnet 4.5 releases. Use the exact replacement strings above — do not append a date suffix to claude-opus-4-8 or claude-sonnet-4-6 (they are dateless pinned snapshots).

    budget_tokens to adaptive thinking

    The Opus path removes the fixed thinking budget. thinking: {type:"enabled", budget_tokens:N} returns a 400 on claude-opus-4-8. The replacement is adaptive thinking — the model decides how much to think per request — with overall depth controlled by the effort parameter (low | medium | high | xhigh | max). There is no direct token-count equivalent; effort is an output-level control, not a thinking budget.

    # Before (Claude Opus 4 / Sonnet 4)
client.messages.create(
    model="claude-opus-4-20250514",
    max_tokens=16000,
    thinking={"type": "enabled", "budget_tokens": 10000},
    messages=[{"role": "user", "content": "..."}],
)

# After (Claude Opus 4.8)
client.messages.create(
    model="claude-opus-4-8",
    max_tokens=16000,
    thinking={"type": "adaptive"},
    output_config={"effort": "high"},  # or "max", "xhigh", "medium", "low"
    messages=[{"role": "user", "content": "..."}],
)

    On the Sonnet path, budget_tokens is deprecated but still functional on claude-sonnet-4-6, so it will not 400 — but you should still migrate to adaptive thinking. Note also that Sonnet 4.6 defaults to effort: "high" where Sonnet 4 had no effort parameter at all; if you do not set it explicitly you may see higher latency and token use after the swap.

    Sampling parameters: removed vs. restricted

    Desk with laptop, checklist notebook, and billing card ready before creating an Anthropic API key
    Sampling parameters — removed vs restricted.

    This is where the two paths diverge most. On claude-opus-4-8, setting temperature, top_p, or top_k to any non-default value returns a 400. Remove them entirely and steer behavior through prompting instead. (If you used temperature=0 for determinism, note it never guaranteed identical outputs on prior models either.)

    # Opus path — sampling params 400 on claude-opus-4-8
# Before
client.messages.create(
    model="claude-opus-4-20250514",
    temperature=0.7,
    top_p=0.9,
    messages=[...],
)

# After — remove them
client.messages.create(
    model="claude-opus-4-8",
    messages=[...],
)

    On claude-sonnet-4-6 the older Claude 4.x rule still applies: you may pass one of temperature or top_p, but passing both returns a 400. So a Sonnet 4 to Sonnet 4.6 move only requires dropping one of the two if you were setting both.

    Assistant-turn prefills to structured outputs

    Prefilling the final assistant turn — ending your messages array with a role: "assistant" message to force a response shape — returns a 400 on both claude-opus-4-8 and claude-sonnet-4-6. This is the one breaking change you cannot dodge by choosing the gentler target. The replacement depends on what the prefill was doing.

    Prefill was used forReplacement
    Forcing JSON / YAML / schema outputoutput_config.format with a json_schema
    Forcing a classification labelA tool with an enum field, or structured outputs
    Skipping preambles (“Here is…”)System-prompt instruction: respond directly, no preamble
    Continuing an interrupted responseMove continuation into the user turn
    Steering around bad refusalsUsually unnecessary now — plain user-turn prompting suffices
     
    # Before (fails on both targets) — prefill forcing JSON shape
messages=[
    {"role": "user", "content": "Extract the name."},
    {"role": "assistant", "content": "{\"name\": \""},
]

# After — structured outputs replace the prefill
client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    output_config={"format": {"type": "json_schema", "schema": SCHEMA}},
    messages=[{"role": "user", "content": "Extract the name."}],
)

    Thinking display: the silent one

    On claude-opus-4-8, thinking blocks still stream, but their thinking text field is empty unless you opt in — the default is display: "omitted". There is no error; if your UI rendered the summarized reasoning, it now shows a long pause before output. Restore it by setting the display mode:

    thinking = {
    "type": "adaptive",
    "display": "summarized",  # default is "omitted" on Opus 4.8/4.7
}

    The block-field name is unchanged — it is still block.thinking on a thinking-type block. The fix is the request parameter, not the response-handling code. (Sonnet 4.6 is not affected by this default change.)

    The new tokenizer: re-baseline max_tokens

    This change is Opus-only and easy to miss because it produces no error. claude-opus-4-8 uses the tokenizer introduced with Opus 4.7, under which the same text tokenizes to roughly 1x–1.35x as many tokens — up to about 35% more, around 30% on typical content, varying by workload. Three consequences:

    What to checkWhy
    max_tokens ceilings and compaction triggersThe same output now consumes more tokens; tight limits truncate mid-thought
    Client-side token estimators (e.g. fixed char-to-token ratios)Calibrated against the old tokenizer; now undercount
    Cost and rate-limit dashboardscount_tokens returns higher numbers; re-baseline before reacting

    Re-run client.messages.count_tokens(model="claude-opus-4-8", ...) on a representative sample of your prompts. Do not apply a blanket multiplier. Sonnet 4.6 keeps the older tokenizer, so a Sonnet 4 to Sonnet 4.6 move has no tokenizer re-baseline to do.

    The full checklist

    StepOpus 4 to 4.8Sonnet 4 to 4.6
    Update model ID stringRequiredRequired
    Replace budget_tokens with adaptive thinkingRequired (400)Recommended (deprecated)
    Sampling paramsRemove all (400)Keep only one (both 400)
    Remove assistant-turn prefillsRequired (400)Required (400)
    Set display: "summarized" if showing reasoningRequired for visible thinkingNot applicable
    Re-baseline max_tokens for new tokenizerRequiredNot applicable
    Set effort explicitlyDefaults to highDefaults to high
    Move output_format to output_config.formatRecommendedRecommended
    Verify tool inputs parsed with a JSON parserRecommendedRecommended
    Spot-check one request, then roll outRequiredRequired

    If you run Claude Code, /claude-api migrate applies the model swap, breaking-parameter changes, prefill replacement, and effort calibration across a codebase, then produces a verify-it-yourself checklist. It asks you to confirm scope before editing any files.

    Is migrating off Claude Opus 4 really not just a model-string change?

    No. Moving to claude-opus-4-8 also requires removing temperature/top_p/top_k and any budget_tokens (all now return 400), removing assistant-turn prefills (400), opting back into summarized thinking if your UI shows it, and re-baselining max_tokens for the new tokenizer. Only the Sonnet 4 to Sonnet 4.6 move is close to a drop-in — and even that requires removing prefills.

    When exactly do Claude Opus 4 and Sonnet 4 stop working?

    June 15, 2026. After that date, requests to claude-opus-4-20250514 and claude-sonnet-4-20250514 return a 404. These are the original May 2025 models, not Opus 4.6 or Sonnet 4.5.

    What replaces budget_tokens now that it errors on Opus?

    Adaptive thinking (thinking: {type:"adaptive"}) plus the effort parameter inside output_config. There is no exact token-count equivalent: the model decides how much to think per request, and effort (low through max) tunes overall depth and spend. On Sonnet 4.6, budget_tokens still works but is deprecated.

    Why does the same prompt cost more tokens on Opus 4.8?

    Opus 4.8 uses the tokenizer introduced with Opus 4.7, under which the same text produces roughly 1x–1.35x as many tokens (about 30% more on typical content, up to ~35%). Re-run the count_tokens endpoint against claude-opus-4-8 and give max_tokens and compaction triggers extra headroom. Sonnet 4.6 keeps the older tokenizer, so it is unaffected.

    My thinking summaries disappeared after migrating to Opus — is that a bug?

    No. On Opus 4.8 (and 4.7), thinking.display defaults to "omitted", so thinking blocks stream with an empty text field. Set display: "summarized" in your thinking config to restore visible reasoning. The field name is unchanged; only the default flipped.

    Related on Tygart Media: Claude Fable 5 guide · API quickstart.

  • Claude Code Billing & Monthly Credit Pools (2026)

    Claude Code Billing & Monthly Credit Pools (2026)

    Last verified: June 13, 2026

    Claude Code has two billing models, and which one applies depends on how you run it, not just which plan you hold. When you use Claude Code interactively in the terminal or IDE on a Pro or Max plan, it draws from the same subscription usage limits as your Claude.ai chats. But starting June 15, 2026, Anthropic separates out programmatic usage: the Claude Agent SDK, the claude -p headless command, the Claude Code GitHub Actions integration, and third-party apps that authenticate through the Agent SDK will no longer count against your interactive subscription pool. Instead they draw from a new, separate monthly Agent SDK credit, billed at standard API rates. This page documents both models, the exact credit amounts per plan, and the SDK package rename you may also need to handle.

    The two billing models at a glance

    Workshop fuel gauge and metal tokens pouring into an API hopper, metaphor for pay-per-token pricing
    Two billing models at a glance — no sticky dollar stickers.

    The dividing line is interactive vs. programmatic. One number to remember: setting an ANTHROPIC_API_KEY environment variable overrides your subscription entirely — Claude Code then authenticates with that key and bills as pay-as-you-go API usage, regardless of plan.

    Usage typeHow it runsBilled against
    Interactive Claude CodeTerminal or IDE, human at the keyboardPro/Max subscription usage limits
    Claude.ai chatWeb, desktop, mobilePro/Max subscription usage limits
    Agent SDK (Python/TypeScript)Your own programmatic projectsSeparate Agent SDK credit (from June 15, 2026)
    claude -p (non-interactive)Headless / scripted Claude CodeSeparate Agent SDK credit (from June 15, 2026)
    Claude Code GitHub ActionsCI/CD automationSeparate Agent SDK credit (from June 15, 2026)
    Any usage with ANTHROPIC_API_KEY setAPI-key auth instead of subscriptionStandard API rates (pay-as-you-go)

    What changes on June 15, 2026

    Per Anthropic’s support documentation: “Starting June 15, 2026, Claude Agent SDK and claude -p usage no longer counts toward your Claude plan’s usage limits.” Each subscription tier instead receives a fixed monthly Agent SDK credit. When that credit runs out, additional Agent SDK usage flows to usage credits at standard API rates — but only if you have enabled usage credits. If you have not, “Agent SDK requests stop until your credit refreshes.” Unused credits do not roll over to the next billing cycle, and there is no automatic fallback to the interactive pool.

    PlanMonthly Agent SDK credit
    Pro$20
    Max 5x$100
    Max 20x$200
    Team (Standard seats)$20
    Team (Premium seats)$100
    Enterprise (seat-based Premium)$200

    What stays on the interactive subscription pool, unchanged: Claude conversations on web, desktop, and mobile; and interactive Claude Code in the terminal or IDE. The change is scoped strictly to programmatic execution.

    How each pool is metered and priced

    Infographic with three panels: protect the service, fair share, and cost control explaining rate limits
    How each pool is metered.

    Claude Code “charges by API token consumption” — the underlying meter is input/output tokens, including thinking tokens billed as output. On a subscription, that token consumption is what counts against your plan limits (interactive) or your Agent SDK credit (programmatic). The Agent SDK credit and any overflow are billed at standard API list rates; the per-model API token prices below are the verified current rates.

    PoolMeterPrice basis
    Interactive (Pro/Max)Tokens, against plan usage limitsIncluded in subscription
    Agent SDK creditTokens, against monthly creditStandard API rates
    Overflow past the creditTokens, usage creditsStandard API rates (only if usage credits enabled)
    API key (ANTHROPIC_API_KEY)Tokens, pay-as-you-goStandard API rates

    Verified current API token prices (per million tokens) for models commonly used in Claude Code:

    ModelModel IDInput $/MtokOutput $/Mtok
    Claude Opus 4.8claude-opus-4-8$5.00$25.00
    Claude Sonnet 4.6claude-sonnet-4-6$3.00$15.00
    Claude Haiku 4.5claude-haiku-4-5$1.00$5.00

    Subscription plan prices

    These are the published Claude plan prices the Agent SDK credits attach to. The Max 5x plan starts at $100/month; the $200 figure for Max 20x is documented as the matching Agent SDK credit amount for that tier.

    PlanPrice
    Free$0
    Pro$20/month, or $17/month billed annually ($200 up front)
    Max 5xFrom $100/month
    Team (Standard seat)$25/seat/month, or $20/seat/month billed annually

    The SDK rename: claude-code-sdk to claude-agent-sdk

    Separate from billing, the SDK itself was renamed. Anthropic’s migration guide states: “The Claude Code SDK has been renamed to the Claude Agent SDK.” If you have code on the old package, you must update the package name, imports, and one Python type. The headless CLI command name is unchanged — it is still claude -p.

    AspectOldNew
    npm package (TS/JS)@anthropic-ai/claude-code@anthropic-ai/claude-agent-sdk
    Python packageclaude-code-sdkclaude-agent-sdk
    Python options typeClaudeCodeOptionsClaudeAgentOptions
    Default system promptClaude Code’s presetMinimal (opt back in via preset: "claude_code")
     
    # TypeScript
npm uninstall @anthropic-ai/claude-code
npm install @anthropic-ai/claude-agent-sdk

# Python
pip uninstall claude-code-sdk
pip install claude-agent-sdk

    Decision: which billing path applies to your work

    Three cards for fast volume, daily workhorse, and deep flagship Claude seats
    Which billing path applies to your work.
    If you are…Billing path
    A developer coding interactively in the terminalSubscription usage limits (unchanged)
    Running claude -p in a script or cron jobAgent SDK credit (from June 15, 2026)
    Running Claude Code in GitHub ActionsAgent SDK credit (from June 15, 2026)
    Building an app on the Agent SDK with subscription authAgent SDK credit (from June 15, 2026)
    A team or service account wanting budgets + usage reportsSet ANTHROPIC_API_KEY → standard API billing

    Does interactive Claude Code billing change on June 15, 2026?

    No. Anthropic’s documentation confirms interactive Claude Code in the terminal or IDE, and Claude conversations on web, desktop, and mobile, continue using subscription usage limits as before. Only programmatic usage — the Agent SDK, claude -p, GitHub Actions, and third-party Agent SDK apps — moves to the separate Agent SDK credit.

    How much is the separate Agent SDK credit?

    $20/month on Pro, $100 on Max 5x, $200 on Max 20x, $20 on Team Standard seats, $100 on Team Premium seats, and $200 on Enterprise seat-based Premium. The credit is billed at standard API rates, does not roll over, and refreshes monthly.

    What happens when the Agent SDK credit runs out?

    Additional Agent SDK usage flows to usage credits at standard API rates — but only if you have enabled usage credits. If you have not enabled them, Agent SDK requests stop until your credit refreshes. There is no automatic fallback to your interactive subscription pool.

    How do I avoid the credit pool entirely?

    Set an ANTHROPIC_API_KEY environment variable. Claude Code and the Agent SDK then authenticate with that key and bill as standard pay-as-you-go API usage, separate from any subscription. This is Anthropic’s recommended path for apps, CI jobs, service accounts, and team-owned projects that need budgets and usage reporting.

    Was the Claude Code SDK renamed?

    Yes. It is now the Claude Agent SDK. The npm package @anthropic-ai/claude-code became @anthropic-ai/claude-agent-sdk, the Python package claude-code-sdk became claude-agent-sdk, and the Python type ClaudeCodeOptions became ClaudeAgentOptions. The claude -p CLI command name is unchanged.

    Related on Tygart Media: Claude Code getting started · Claude pricing · Pro vs Max.

  • Latest Claude Models — June 2026 (Current Lineup, Prici (2026)

    Latest Claude Models — June 2026 (Current Lineup, Prici (2026)

    Updated June 12, 2026. Fable 5 is the current top-tier model, released June 9, 2026. The full lineup: Fable 5 → Opus 4.8 → Sonnet 5 → Haiku 4.5. Pricing and availability verified against Anthropic’s official docs.

    Direct Answer (August 2026): The latest available Anthropic Claude models are Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5, and Claude Fable 5. All models support 200k–1M context windows, vision multimodal inputs, structured tool calling (MCP), and server-side prompt caching.

    Current Claude Models — Quick Reference

    Three-column board mapping Claude model seats to flagship thinking, production workhorse, and fast volume jobs
    Current Claude models — quick reference by job.
    ModelAPI IDInput $/MTokOutput $/MTokContextBest For
    Claude Fable 5 🆕claude-fable-5$10.00$50.001M tokensComplex engineering, long-horizon agentic work
    Claude Opus 4.8claude-opus-4-8$5.00$25.001M tokensEveryday advanced work, high-volume pipelines
    Claude Sonnet 5claude-sonnet-5$3.00$15.001M tokensBalanced capability and speed
    Claude Haiku 4.5claude-haiku-4-5-20251001$1.00$5.00200K tokensHigh-speed, cost-sensitive tasks

    All four models support vision, tool use/function calling, and batch processing. Fable 5 and Opus 4.8 are available on AWS Bedrock, Google Cloud Vertex AI, and Microsoft Azure AI Foundry in addition to the direct Anthropic API.

    Claude Fable 5 (June 9, 2026)

    Fable 5 is Anthropic’s first publicly available Mythos-class model — a capability tier previously restricted to research and select enterprise partners. It’s the most capable model Anthropic has released to date.

    What makes Fable 5 different:

    • SWE-bench Verified: 95.0% (vs 88.6% for Opus 4.8)
    • SWE-bench Pro: 80.0% (vs 69.2%)
    • Senior Engineer benchmark: 91/100 (vs ~63/100)
    • Adaptive extended thinking (always on, not a mode switch)

    Important limitations:

    • 2x the cost of Opus 4.8 ($10/$50 vs $5/$25)
    • Mandatory 30-day data retention — not available under zero data retention (ZDR)
    • Safety classifiers route cybersecurity, biology, chemistry, and distillation prompts to an Opus 4.8 fallback — you pay Fable 5 rates for Opus 4.8 output in those domains
    • Higher latency on complex tasks (60 seconds to several minutes vs 3–15 seconds for Opus 4.8)

    Free through June 22, 2026: Claude Pro, Max 5x, Max 20x, Team, and Enterprise subscription plans include Fable 5 at no extra charge during the launch window.

    Claude Opus 4.8

    Opus 4.8 is Anthropic’s current workhorse for serious work — the right default for most API applications and Claude Code use. It supports zero data retention (ZDR), which Fable 5 does not.

    Key specs:

    • Context: 1M tokens
    • Max output: 32K tokens per request
    • Extended thinking: Available (opt-in mode)
    • ZDR: Yes
    • Batch API: Yes (50% discount on batch processing)

    Use Opus 4.8 as your default model unless you have a specific reason to go up to Fable 5 or down to Sonnet/Haiku. It hits the best balance of capability, speed, cost, and data policy flexibility.

    Claude Sonnet 5

    Sonnet 5 targets use cases where response speed matters and you don’t need Opus-level reasoning. It’s the model Anthropic’s own infrastructure runs Claude.ai on for Pro subscribers doing day-to-day chat work.

    Key specs:

    • Context: 1M tokens
    • Max output: 64K tokens per request
    • Extended thinking: Available
    • ZDR: Yes
    • Typical latency: 1–5 seconds for most tasks

    Good for: content generation pipelines, customer-facing chat, document analysis at volume, anything where sub-5-second response time matters.

    Claude Haiku 4.5

    Haiku 4.5 is Anthropic’s fastest and cheapest model. At $1 input / $5 output per million tokens, it’s 10x cheaper than Fable 5.

    Key specs:

    • Context: 200K tokens (smaller than the Opus/Sonnet/Fable 1M window)
    • Max output: 16K tokens per request
    • Latency: Sub-second for most tasks
    • ZDR: Yes

    The 200K context window is the main limitation. For tasks that fit within that window — classification, short-form generation, routing, extraction — Haiku 4.5 is the cost-optimal choice. For longer documents or conversations, step up to Sonnet or Opus.

    How to Choose the Right Claude Model

    Pyramid diagram of Claude tiers: fast volume base, production workhorse middle, deep flagship peak
    How to choose the right Claude model.

    The decision framework I use:

    1. Does the task require multi-step reasoning, complex coding, or long-horizon autonomy? → Fable 5 (if cost and latency are acceptable) or Opus 4.8
    2. Is this a routine task at reasonable volume? → Opus 4.8 as the default
    3. Does latency matter more than maximum reasoning depth? → Sonnet 5
    4. Is this high-volume, short-context, cost-sensitive work? → Haiku 4.5
    5. Does your use case require zero data retention? → Any model except Fable 5

    Most production applications use a routing strategy: Fable 5 or Opus 4.8 for the hard jobs, Haiku 4.5 for classification and pre-processing, Sonnet 5 for user-facing response generation.

    Claude Subscription Plans and Model Access (June 2026)

    Infographic ladder of Claude plans: Free, Pro, Max, Team, and Enterprise
    Subscription plans and model access — stale-proof.
    PlanPriceModels Included
    Free$0Limited Sonnet 5 access
    Pro$20/mo ($17 annual)Sonnet 5, Opus 4.8, Fable 5 (through June 22)
    Max 5x$100/moAll models, 5x usage vs Pro
    Max 20x$200/moAll models, 20x usage vs Pro
    Team Standard$20/seat/mo (annual), $25 month-to-monthAll models + admin features
    Team Premium$100/seat/mo (annual), $125 month-to-monthAll models + priority + advanced admin
    Enterprise$20/seat + usage at API rates (contact sales)All models + ZDR + custom retention + SSO

    Claude Code (the CLI tool) is included in all paid subscription plans. API access for building your own applications is separate — billed per token via the Anthropic Console regardless of subscription status.

    Legacy Models (Still Available, No Longer Latest)

    These models are still available via the API but are not Anthropic’s current recommended versions:

    • Claude Opus 4.7 (claude-opus-4-7) — prior Opus tier, succeeded by 4.8
    • Claude Opus 4.6 (claude-opus-4-6) — two generations back
    • Claude Sonnet 4.5 (claude-sonnet-4-5) — prior Sonnet tier
    • Claude 3.5 Haiku / Sonnet / Opus — Claude 3.x generation, still functional for legacy integrations

    If you’re building a new application, start with the current lineup. Legacy model IDs are useful for maintaining compatibility in existing applications that haven’t been updated.

    Platform Availability

    PlatformFable 5Opus 4.8Sonnet 5Haiku 4.5
    Anthropic API (direct)✓✓✓✓
    AWS Bedrock✓✓✓✓
    Google Cloud Vertex AI✓✓✓✓
    Microsoft Azure AI Foundry✓✓✓✓
    GitHub Copilot✓ (via Foundry)✓✓—

    Frequently Asked Questions

    What is the newest Claude model?
    As of June 2026, Claude Fable 5 is the newest and most capable model Anthropic has released. It launched June 9, 2026. The API model ID is claude-fable-5.

    Is Claude Fable 5 the same as Claude 5?
    No. Anthropic changed the naming convention — there is no “Claude 5.” The Fable series is a new tier above the Opus/Sonnet/Haiku hierarchy. Fable 5 is Anthropic’s first Mythos-class model released for general availability.

    What is the most powerful Claude model?
    Claude Fable 5 is currently the most powerful. For tasks where Fable 5’s safety classifier routing applies (cybersecurity, biology, chemistry, distillation), or where zero data retention is required, Claude Opus 4.8 is the appropriate top-tier choice.

    What Claude model does Claude.ai use by default?
    Depends on your plan. Free tier uses a limited version of Sonnet. Pro and Max subscribers access Opus 4.8 as the default with Fable 5 available (through June 22, 2026 included, after that plan-dependent). Claude.ai routes to the appropriate model for your plan automatically.

    How do I use the latest Claude model in the API?
    Set the model parameter in your API request to the model ID. For Fable 5: "model": "claude-fable-5". For Opus 4.8: "model": "claude-opus-4-8". See the full API reference at console.anthropic.com.

    What’s the difference between Claude Opus 4.8 and Fable 5?
    Fable 5 is significantly stronger on complex engineering tasks — SWE-bench Pro: 80% vs 69.2%, and Senior Engineer benchmark: 91 vs ~63 out of 100. The trade-off: Fable 5 costs 2x more ($10/$50 vs $5/$25 per MTok), has higher latency, and requires 30-day data retention. For most work, Opus 4.8 is the right choice. Full Fable 5 vs Opus 4.8 breakdown here.

    Changelog

    • June 12, 2026 — Added Claude Fable 5 (released June 9). Updated pricing table. Added platform availability table.
    • May 2026 — Claude Opus 4.8 and Sonnet 4.6 were the current top-tier models.

    This page is updated as Anthropic releases new models. Last verified: August 26, 2026 (Pacific Time) For API pricing, check console.anthropic.com — the canonical source.

    💼 Deploying Claude or AI Infrastructure in Your Business?

    At Tygart Media, we engineer custom Model Context Protocol (MCP) servers, multi-model content pipelines, and AI operational systems. Explore our Claude AI Team Implementation Services or check out our complete Restoration Operations & AI Kit.

  • Claude Fable 5: Capabilities, Pric (2026)

    Claude Fable 5: Capabilities, Pric (2026)

    Anthropic released Claude Fable 5 on June 9, 2026 — and it’s the most capable model the company has ever made publicly available. After tracking every Claude release since the original 100K context window dropped, I can say this one is different. Fable 5 isn’t just an incremental update. It’s Anthropic’s Mythos-class model — the one they’d been keeping restricted — now opened up to anyone with an API key or a Claude subscription.

    Here’s what you need to know: the pricing, the benchmarks, and the specific decision framework for when to use Fable 5 versus sticking with Opus 4.8.

    Quick answer: Fable 5 costs $10/$50 per million input/output tokens (2x the cost of Opus 4.8). It outperforms Opus 4.8 significantly on complex coding, long-horizon tasks, and scientific research. Use Fable 5 when quality on hard problems justifies the cost. Use Opus 4.8 for high-volume, well-scoped, routine work.

    What Is Claude Fable 5?

    Three cards for fast volume, daily workhorse, and deep flagship Claude seats
    What is Claude Fable 5?

    Claude Fable 5 (claude-fable-5) is Anthropic’s first publicly available Mythos-class model. The Mythos line is Anthropic’s highest capability tier — models that were previously restricted to research and select enterprise partners because of their raw power. Fable 5 is the version Anthropic deemed safe enough to release broadly.

    The name shift (from the Opus/Sonnet/Haiku tier naming) signals something intentional. Fable 5 sits above the Opus line entirely. It’s a new ceiling.

    Key specs:

    • Context window: 1M tokens (same as Opus 4.8)
    • Max output: 128K tokens per request
    • Thinking: Adaptive (always on — not a separate “thinking mode”)
    • Vision: Yes
    • Tool use / function calling: Yes
    • Available: Claude API, AWS Bedrock, Vertex AI, Microsoft Foundry

    Claude Fable 5 Pricing

    Infographic ladder of Claude plans: Free, Pro, Max, Team, and Enterprise
    Fable 5 pricing — no sticky dollar stickers.
    ModelInput (per MTok)Output (per MTok)Context
    Claude Fable 5$10.00$50.001M tokens
    Claude Opus 4.8$5.00$25.001M tokens
    Claude Sonnet 4.6$3.00$15.001M tokens
    Claude Haiku 4.5$1.00$5.00200K tokens

    Fable 5 costs exactly 2x Opus 4.8 on API. On subscription plans (Pro, Max, Team, Enterprise seat-based), Fable 5 is included at no extra cost through June 22, 2026.

    The free-until-June-22 window matters if you’re evaluating whether to route your workloads to Fable 5. Use that window to benchmark it against your actual tasks before the 2x cost kicks in.

    Benchmark Performance: Where Fable 5 Pulls Away

    The benchmarks that matter most are the ones that measure what the model can do on real engineering work, not trivia:

    BenchmarkClaude Fable 5Claude Opus 4.8Delta
    SWE-bench Verified95.0%88.6%+6.4 pts
    SWE-bench Pro80.0%69.2%+10.8 pts
    FrontierCode29.3%13.4%~2.2x
    Senior Engineer benchmark91/100~63/100+45% absolute

    The Senior Engineer benchmark is the one I find most telling. It’s designed to be hard for people who write code for a living — and Fable 5 scores 45 percentage points higher than Opus 4.8. That gap is significant enough that it changes the calculus for serious engineering work.

    When to Use Claude Fable 5 (vs Opus 4.8)

    Decision fork between maximum capability when stakes are high and shipping daily when speed and cost matter
    When to use Fable 5 vs Opus.

    I’ve been routing tasks between models for long enough to have a framework. Here’s how I think about it:

    Use Fable 5 when:

    • You’re running a large migration, refactor, or multi-stage software project
    • Quality on a hard problem matters more than per-token cost
    • You’re doing deep research, complex analysis, or long-horizon agentic work
    • The task would otherwise take a senior engineer half a day or more
    • You’re in the free evaluation window (through June 22) and want to benchmark

    Use Opus 4.8 when:

    • The task is well-scoped and routine
    • You’re running high-volume pipelines where 2x cost compounds fast
    • Latency matters — Fable 5 can take 60 seconds to several minutes on complex tasks vs 3–15 seconds for Opus 4.8
    • The task falls in Fable 5’s restricted domains (cybersecurity, biology, chemistry, distillation) — in those categories, Fable 5 routes to Opus 4.8 anyway, so you’d pay Fable 5 prices for Opus 4.8 output

    The smart routing strategy: Fable 5 for the hard jobs, Opus 4.8 for the rest. Don’t use Fable 5 as your default model — the cost and latency delta aren’t worth it for routine tasks.

    Important Limitations to Know Before You Switch

    Two limitations that don’t get enough coverage:

    1. Safety classifier routing. Fable 5 includes enhanced safety classifiers. For prompts touching cybersecurity, biology, chemistry, and distillation, those classifiers route the request to a Claude Opus 4.8 fallback. You pay Fable 5 API rates ($10/$50) but get Opus 4.8 output. If your use case is in these domains, Fable 5 is not the upgrade it appears to be.

    2. Data retention requirement. Fable 5 carries a mandatory 30-day data retention policy — Anthropic needs retained prompts and outputs to operate the safety classifiers. Claude Opus 4.8 is available under zero data retention (ZDR). If your use case requires ZDR (healthcare, legal, finance with strict data handling), stick with Opus 4.8 until Anthropic updates Fable 5’s data policy.

    Availability

    Claude Fable 5 is generally available as of June 9, 2026 on:

    • Claude API (claude-fable-5)
    • Claude Platform on AWS / Amazon Bedrock
    • Google Cloud Vertex AI
    • Microsoft Azure AI Foundry / GitHub Copilot

    Subscription access (free through June 22, 2026): Claude Pro ($20/mo), Max 5x ($100/mo), Max 20x ($200/mo), Team, and seat-based Enterprise plans all include Fable 5 access at no extra charge during the launch window. After June 22, the plan-tier access picture may change — check Anthropic’s pricing page for updates.

    How This Changes the Claude Model Decision Tree

    Before Fable 5, the Claude decision tree was straightforward:

    • Need the best? → Opus 4.8
    • Need balance? → Sonnet 4.6
    • Need speed/cost? → Haiku 4.5

    Now it’s:

    • Hard problems, complex projects, long-horizon work → Fable 5
    • Everyday work, high-volume pipelines → Opus 4.8
    • Balance of cost and capability → Sonnet 4.6
    • Speed and cost optimization → Haiku 4.5

    The introduction of a model tier above Opus 4.8 doesn’t replace the existing lineup — it creates a new ceiling for the work that genuinely needs it.

    Related on Tygart Media: Fable 5 complete guide · Fable 5 firsthand · how to use Claude.

    Frequently Asked Questions

    Is Claude Fable 5 better than Opus 4.8?
    For complex coding, multi-stage tasks, and long-horizon work: yes, significantly. On SWE-bench Pro, Fable 5 scores 80.0% vs Opus 4.8’s 69.2% — a 10+ point gap. For routine, well-scoped tasks: the gap narrows enough that Opus 4.8’s 2x cost advantage makes it the smarter choice.

    What is the Claude Fable 5 API model ID?
    claude-fable-5. This is the API string you pass to model in your API calls.

    Does Fable 5 cost more than Opus 4.8?
    Yes — exactly 2x. Fable 5 is $10 input / $50 output per million tokens. Opus 4.8 is $5/$25. Through June 22, 2026, Fable 5 is included in Claude subscription plans at no extra cost.

    Can I use Claude Fable 5 for free?
    On Pro, Max, Team, and Enterprise subscription plans, yes — through June 22, 2026. API access is metered at $10/$50 per MTok from day one.

    Does Claude Fable 5 support zero data retention (ZDR)?
    No. Fable 5 carries a mandatory 30-day data retention requirement. If your use case requires ZDR, use Claude Opus 4.8, which supports it.

    What’s the difference between Claude Fable 5 and Claude Mythos 5?
    Mythos 5 is Anthropic’s fully restricted research model — not publicly available. Fable 5 is the Mythos-class model that Anthropic has prepared for general availability, with safety classifiers and the 30-day retention policy. You can think of Fable 5 as “Mythos for the real world.”

    Last verified: June 12, 2026. Anthropic pricing and availability subject to change — check Anthropic’s pricing page for current rates.

  • Claude Fable 5 Complete Guide

    Claude Fable 5 Complete Guide

    New in 2026

    Everything you need to know about Anthropic’s new frontier tier — pricing, context window, model comparisons, and how to route the right work to the right model.

    Updated June 2026 · ~14 min read · Includes interactive calculators

    What Is Claude Fable 5?

    Three cards for fast volume, daily workhorse, and deep flagship Claude seats
    What is Claude Fable 5?

    Claude Fable 5 is Anthropic’s new frontier model tier — positioned above Opus in the lineup and designed for tasks where raw capability, extended reasoning depth, and massive context handling matter more than cost. Where Opus 4.8 set the bar for complex multi-step reasoning, Fable 5 raises it with a 1-million-token context window, enhanced agentic autonomy, and improved performance on long-horizon software engineering, research synthesis, and cross-domain analysis tasks.

    The “Fable” naming signals a new generation of model architecture rather than an incremental update. Anthropic positions it as the model you reach for when a task exceeds what Opus can do reliably — not as a replacement for Opus, Sonnet, or Haiku in their respective cost tiers.

    Quick Facts — Claude Fable 5

    Context Window
    1M
    tokens (~750K words)
    Max Output
    32K
    tokens per response
    Input Price
    $10
    per million tokens
    Output Price
    $50
    per million tokens
    Cache Write
    $12.50
    per million tokens
    Cache Read
    $1.00
    per million tokens
    Key positioning: Fable 5 is the model for tasks where Opus 4.8 produces reliable but imperfect results — long codebase audits, full-document analysis, complex multi-agent orchestration, and strategic synthesis across large corpora. For most production workflows, Sonnet remains the value pick.

    Full Model Lineup Comparison

    Pyramid diagram of Claude tiers: fast volume base, production workhorse middle, deep flagship peak
    Full model lineup comparison.

    Here’s how the complete 2026 Claude lineup stacks up across every dimension that matters for production usage:

    Model Input $/M Output $/M Context Max Out Vision Tool Use Extended Think Best For
    ◆ Fable 5 $10 $50 1M 32K ✓ ✓ ✓ Deep Max-capability tasks, 1M+ context
    ◆ Opus 4.8 $5 $25 200K 32K ✓ ✓ ✓ Complex reasoning, agentic workflows
    ◆ Sonnet 4.6 $3 $15 200K 16K ✓ ✓ ✓ Production apps, content at scale
    ◆ Haiku 4.5 $1 $5 200K 8K ✓ ✓ — High-volume, latency-sensitive tasks

    Prices are per million tokens. Cache read is 90% cheaper than standard input across all models. Batch API provides an additional 50% discount on both input and output.

    Capability Matrix — What Each Model Can Do

    Capability Fable 5 Opus 4.8 Sonnet 4.6 Haiku 4.5
    Full codebase analysis (>500K tokens)✓ Native⚠ Chunked✗✗
    Extended thinking / chain-of-thought✓ Deep✓✓✗
    Multi-step agentic orchestration✓ Best✓GoodLimited
    Computer use✓✓✓✗
    MCP tool integration✓✓✓✓
    Prompt caching✓✓✓✓
    Batch API (50% discount)✓✓✓✓
    PDF / document analysis✓✓✓Limited
    Real-time streaming✓✓✓✓
    Structured JSON output✓✓✓✓

    Interactive Cost Calculator

    Estimate your monthly API spend across the full model lineup. Enter your token volumes below — the calculator models prompt caching and Batch API discounts automatically.

    Token Cost Calculator

    Estimated Monthly Cost
    $0.00

    Which Claude Model Should You Use?

    Decision diagram from task shape to deep reasoning, daily shipping, or high-volume cheap calls
    Which Claude model should you use?

    Answer three questions to get a model recommendation tailored to your use case.

    Model Picker — 3 Questions
    1. How large is your context? (document/codebase size)
    Under 50K tokens
    50K–200K tokens
    200K–1M tokens
    2. How complex is the task?
    Simple / structured (classify, extract, format)
    Moderate (draft, summarize, QA)
    Complex (reason, plan, code, orchestrate)
    3. How cost-sensitive is this workload?
    Very — high volume, every cent counts
    Moderate — quality matters more than cost
    Not sensitive — quality and capability first

    How We Actually Use Each Model

    These are real production workflows mapped to the right tier — built from running Claude in content operations, publishing automation, and knowledge management at scale. No hypotheticals.

    Haiku 4.5 — High Volume
    Daily SEO Refresh Pipeline
    • 25-post-per-day SEO metadata refresh
    • Article classification and tag assignment
    • Structured data extraction from web pages
    • Keyword density checks across large post archives
    • Link validation and redirect flagging
    Sonnet 4.6 — Production Default
    Editorial Content at Scale
    • Desk article writing (1,200–2,500 words)
    • Content brief execution from keyword clusters
    • FAQ and schema markup generation
    • Cross-site content adaptation and localization
    • Monthly client update drafts and summaries
    Opus 4.8 — Complex Reasoning
    Workers & Deep Refreshes
    • Agentic Notion Workers (multi-step pipelines)
    • Deep content refresh with competitive gap analysis
    • Multi-database synthesis and reporting
    • Strategy documents requiring extended reasoning
    • Code generation for automation scripts
    Fable 5 — Max Capability
    Portfolio Audits & Strategy
    • Full-site content audits (500+ posts in single context)
    • Cross-domain strategy synthesis across large corpora
    • Complex multi-agent orchestration at the flagship tier
    • Long-horizon planning requiring deep reasoning depth
    • Codebase-wide analysis and architecture review
    Routing principle: The right model is the cheapest one that reliably completes the task. Haiku handles volume. Sonnet handles production. Opus handles complexity. Fable 5 handles scale + complexity together — specifically the cases where you’d need Opus and more context than Opus can hold.

    The Economics: Routed vs All-Fable

    Smart model routing is where API costs get controlled. Here’s a real-world comparison of a mixed content-and-automation workload at scale — routed vs running everything on Fable 5.

    Workload Monthly Volume Routed Model Routed Cost All-Fable 5 Cost Savings
    SEO metadata batch refresh750 posts/moHaiku 4.5 + Batch$1.20$18.7593% less
    Article drafting90 articles/moSonnet 4.6$8.10$67.5088% less
    Agentic worker runs200 runs/moOpus 4.8$22.50$45.0050% less
    Full-site portfolio audits4 audits/moFable 5$24.00$24.00—
    Total—Routed$55.80$155.2564% less

    Stacking Discounts: Caching + Batch API

    Two discount mechanisms compound independently:

    • Prompt caching: Cache your system prompt and shared context once. Subsequent requests pay ~10% of the input price for cache reads. On Fable 5, that’s $1.00/M instead of $10.00/M on cached tokens — a 90% reduction on your largest cost lever.
    • Batch API: Submit requests asynchronously (results within 24 hours) for a flat 50% discount on both input and output. Works on all four models. Best for non-real-time workloads like overnight refreshes, audits, or bulk classification.
    • Stacked: Caching + Batch combined can bring effective Fable 5 input cost from $10/M to ~$0.50/M on cached tokens — making it economically viable for high-volume tasks that previously only fit Haiku’s budget.

    See our Claude context window guide for more on how to structure prompts to maximize cache hit rates.

    Related Claude Resources

    Claude Context Window Guide Claude Projects Deep Dive Claude Code Plan Mode Claude MCP Setup Guide Opus 4.7 Feature Deep Dive Claude Code vs Cursor (2026)

    Claude Fable 5 FAQ

    Claude Fable 5 sits above Opus 4.8 in the lineup. The primary difference is context window size — Fable 5 offers 1 million tokens vs Opus 4.8’s 200K — and the depth of extended reasoning for highly complex tasks. Opus 4.8 remains the right choice for most complex agentic workflows at half the cost. Fable 5 is best when you need both maximum context and maximum reasoning depth simultaneously, or when a task has routinely hit the limits of what Opus can do reliably.
    Claude Fable 5 is priced at $10 per million input tokens and $50 per million output tokens — 2× Opus 4.8 ($5/$25), 3.3× Sonnet 4.6 ($3/$15), and 10× Haiku 4.5 ($1/$5). Prompt caching drops the effective input cost to $1.00/M on cache reads, and the Batch API adds a 50% discount on all tokens for non-real-time workloads. Stacking both discounts makes Fable 5 viable for higher-volume use cases than the base price suggests.
    Claude Fable 5 has a 1-million-token context window — approximately 750,000 words or roughly 1,500 pages of text. This is 5× the context window of Opus 4.8, Sonnet 4.6, and Haiku 4.5 (all 200K). In practice, a 1M context window lets you pass entire codebases, long research corpora, or full document archives in a single API call without chunking or retrieval workarounds. For more on context window mechanics, see our full context window guide.
    Yes. Claude Fable 5 is available through the Anthropic API using the model ID claude-fable-5-20260101 (check the Anthropic documentation for the exact identifier). It supports the same API surface as the rest of the Claude family — streaming, tool use, prompt caching, vision, the Batch API, and MCP server integration. Access requires an Anthropic API account with Fable 5 enabled on your usage tier.
    Fable 5 is available in Claude.ai on the Pro and Team plans. The interface lets you select it from the model picker when starting a conversation. Like Opus, Fable 5 in claude.ai has message limits that reset on a rolling window — it’s designed for individual complex tasks rather than high-volume API workloads. For production-scale usage, the API with the Batch API discount is the more economical path.
    Yes — and Fable 5’s extended thinking is the deepest in the lineup. Where Opus 4.8 supports extended thinking for complex reasoning tasks, Fable 5 uses a more capable reasoning engine designed for tasks that require longer chains of inference, more working memory, and more reliable self-correction. It’s particularly effective on math, logic, long-horizon planning, and tasks where the model needs to hold and manipulate many interdependent concepts simultaneously.
    For most content production — articles, blog posts, social copy, summaries, SEO content — Sonnet 4.6 is the right call. It produces high-quality output at 3.3× less cost than Fable 5, and for typical content lengths (500–3,000 words), the quality difference is minimal. Reach for Fable 5 when you need to synthesize across a very large corpus (e.g., auditing 200+ posts simultaneously), when the content requires deep domain reasoning that benefits from extended thinking, or when the task involves both large-context ingestion and complex output generation in a single pass.
    Three levers in order of impact: (1) Model routing — only use Fable 5 when the task genuinely requires it; route everything else to Opus, Sonnet, or Haiku based on complexity and volume. (2) Prompt caching — structure your system prompt and shared context so it can be cached; cache reads cost $1.00/M instead of $10.00/M on Fable 5. (3) Batch API — submit non-real-time workloads via the Batch API for a flat 50% discount. Stacking all three — routing + caching + batch — can reduce effective per-task costs by 85–95% compared to unoptimized Fable 5 calls.

    More Claude Guides from Tygart Media

    We run Claude in production every day. These are the guides that come from using it, not just writing about it.

    Context Window Guide Claude Projects Plan Mode MCP Setup Code vs Cursor

    Related on Tygart Media: Claude Fable 5 overview · Fable 5 firsthand · Claude pricing.

  • llms-full.txt vs llms.txt: Why AI Agents Crawl It More (2026)

    llms-full.txt vs llms.txt: Why AI Agents Crawl It More (2026)

    Most conversations about AI crawlability focus on one file: llms.txt. But if you look at what Anthropic, Vercel, and LangGraph actually ship – and what GEO crawler research found AI agents fetching most – the file that matters more is its companion: llms-full.txt.

    Here’s the practical reality: llms.txt is the map. llms-full.txt is the territory. And in 2026, the agents that matter for citation traffic are fetching the territory.

    The Full File Family You Probably Don’t Know About

    The original llms.txt proposal – published by Jeremy Howard in September 2024 – defined one file. Implementers built the rest. The complete family as of mid-2026 is four files, but most sites only need two:

    FileWhat’s in itWhen to use
    /llms.txtCurated index – H1, summary, link sectionsAlways. The orientation layer.
    /llms-full.txtFull content of every linked page, concatenated as MarkdownWhen you want a model to deep-ingest your docs in a single fetch
    /llms-ctx.txtPre-expanded context without URLsFastHTML-style implementations
    /llms-ctx-full.txtPre-expanded context with URLs preservedSame, but URL-aware

    The pattern that works – and the one Anthropic, Vercel, and LangGraph all run – is the index + export pair: llms.txt for orientation, llms-full.txt for deep ingestion.

    Why llms-full.txt Gets Crawled More

    Four ranked rows of AI crawler fleets reading publisher content
    Why llms-full.txt gets crawled more.

    GEO researchers analyzing AI crawler behavior – including work cited by Profound – have noted that agents from Microsoft, OpenAI, and others tend to fetch llms-full.txt more frequently than llms.txt when both are present. The working explanation is structural: when a file contains the full content, it removes one retrieval step. An agent that fetches llms-full.txt gets everything it needs in a single HTTP request instead of fetching the index, parsing the links, then fetching each linked page individually. This is consistent with how developer documentation platforms like Mintlify describe the behavior of IDE agents operating under tight latency budgets.

    For IDE agents (Cursor, Continue, Cline) and MCP integrations, this is even more pronounced. These tools are operating under tight context windows and latency budgets. A single fetch that returns a clean Markdown blob of your entire docs is structurally preferable to a multi-step crawl.

    The implication: if you’ve shipped llms.txt but not llms-full.txt, you’ve done half the job.

    How to Build llms-full.txt

    Desk with laptop, checklist notebook, and billing card ready before creating an Anthropic API key
    How to build llms-full.txt.

    The construction logic is simple: take every URL in your llms.txt, fetch each page, strip HTML to Markdown, and concatenate. In practice, most sites do this in their build pipeline.

    Here’s the minimal Node.js pattern:

    const fs = require('fs');
const fetch = require('node-fetch');
const TurndownService = require('turndown');
const turndown = new TurndownService();

async function buildLlmsFullTxt(llmsIndexPath, outputPath) {
  const index = fs.readFileSync(llmsIndexPath, 'utf8');
  const urlRegex = /\[.*?\]\((https?:\/\/[^\)]+)\)/g;
  const urls = [...index.matchAll(urlRegex)].map(m => m[1]);

  let output = '';
  for (const url of urls) {
    const res = await fetch(url);
    const html = await res.text();
    const markdown = turndown.turndown(html);
    output += \n\n---\n# Source: \n\n;
  }

  fs.writeFileSync(outputPath, output);
  console.log(Built llms-full.txt:  pages,  chars);
}

buildLlmsFullTxt('./public/llms.txt', './public/llms-full.txt');

    One constraint to manage: keep llms-full.txt under roughly 200,000 tokens (about 150K words, around 700KB). That’s the threshold where most models can ingest the file in a single context window. If your docs are larger, segment by product or language the way Supabase does – llms-full-api.txt, llms-full-guides.txt – and list the segmented files in your main llms.txt.

    The 2026 robots.txt Stack That Completes the Picture

    Three cards for Google cautious, Bing speed, OpenAI aggressive crawl styles
    The 2026 robots.txt stack that completes the picture.

    Shipping llms.txt and llms-full.txt is the visibility layer. The access-control layer is robots.txt – and it changed significantly in Q2 2026.

    The key development: Anthropic split its crawler into two separate user-agents. ClaudeBot is the training scraper (high bandwidth, no citation value – block it). Claude-Web is the live-retrieval agent that fetches pages to answer Claude.ai user queries in real time (allow it, because it drives citation traffic). Brands that blanket-block “all Anthropic crawlers” lose Claude citations entirely.

    Meta also shipped two active training scrapers in March 2026 – FacebookBot and Meta-ExternalAgent – at GPTBot-level crawl volume. Most sites have no rules for them yet.

    Here’s the 2026 template:

    # BLOCK: Training scrapers - high bandwidth, zero referral value
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# OPT OUT: Google Gemini training (keeps Search indexing intact)
User-agent: Google-Extended
Disallow: /

# ALLOW: Live-retrieval agents - drive citation traffic
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

    One important caveat on robots.txt enforcement: aggressive training scrapers often ignore the file or spoof their user-agents. The robots.txt rules signal intent and work for compliant bots; a WAF rule at the edge is the only deterministic block for non-compliant crawlers.

    The Honest State of the Technology

    The SERanking study of 300,000 domains (November 2025) found no measurable correlation between having llms.txt and being cited by ChatGPT, Claude, Gemini, or Perplexity. Google’s John Mueller compared the file to the deprecated keywords meta tag – something site owners declare but that search systems derive from the content itself.

    None of that means you shouldn’t ship both files. The cost is low, the optionality is real, and the IDE-agent ecosystem (Cursor, Continue, Cline) does actively use llms.txt. But the robots.txt work is the lever that moves outcomes today. The llms.txt + llms-full.txt pair is infrastructure investment – you want to be correct when major LLM providers start honoring it, and building the build pipeline now costs far less than retrofitting it later.

    The practical sequence for a site that hasn’t done this yet:

    1. Update robots.txt first. Add the Q2 2026 user-agent rules above. This takes twenty minutes and immediately affects how training scrapers treat your content.
    2. Ship llms.txt. Curated index, 20-50 priority pages, one-sentence description per link, sections in priority order.
    3. Build llms-full.txt. Concatenated Markdown of every linked page, under 200K tokens. Run it in your build pipeline so it stays current.
    4. Verify both files are served correctly. curl -I https://yoursite.com/llms.txt should return 200 with Content-Type: text/plain. A 404 on either file is the most common implementation error.
    5. Add an access-log check. Once per month, grep your logs for requests to /llms.txt and /llms-full.txt by user-agent. You want to see live-retrieval agents (Claude-Web, OAI-SearchBot, PerplexityBot) in the results – not just training scrapers.

    The goal isn’t to optimize for a standard that isn’t fully adopted yet. It’s to build the infrastructure correctly now, while the field is still forming, so that adoption changes work in your favor rather than requiring catch-up.

    Related Reading

    Frequently Asked Questions

    What is the difference between llms.txt and llms-full.txt?

    llms.txt is a curated index — an H1, a summary, and link sections that orient an AI agent to your site. llms-full.txt is the full content of every linked page concatenated as Markdown, so an agent can deep-ingest your documentation in a single fetch. The index is the map; the full file is the territory.

    Why do AI agents crawl llms-full.txt more often than llms.txt?

    Fetching llms-full.txt removes a retrieval step: the agent gets everything in one HTTP request instead of fetching the index, parsing links, and fetching each page individually. For IDE agents like Cursor, Continue, and Cline operating under tight latency and context budgets, a single clean Markdown blob is structurally preferable to a multi-step crawl.

    How big should llms-full.txt be?

    Keep it under roughly 200,000 tokens (about 150K words, around 700KB) so most models can ingest it in a single context window. If your docs are larger, segment by product or language — for example llms-full-api.txt and llms-full-guides.txt — and list the segmented files in your main llms.txt.

    Does having llms.txt actually improve AI citations?

    Not measurably on its own. A November 2025 SERanking study of 300,000 domains found no correlation between having llms.txt and being cited by ChatGPT, Claude, Gemini, or Perplexity, and Google’s John Mueller compared it to the deprecated keywords meta tag. The lever that moves outcomes today is robots.txt configuration; llms.txt and llms-full.txt are low-cost infrastructure for when adoption grows.

    Which AI crawlers should I allow in robots.txt in 2026?

    Allow live-retrieval agents that drive citation traffic — Claude-Web, OAI-SearchBot, ChatGPT-User, anthropic-ai, and PerplexityBot. Block high-bandwidth training scrapers with no referral value such as GPTBot, CCBot, ClaudeBot, FacebookBot, and Meta-ExternalAgent, and opt out of Google-Extended to skip Gemini training while keeping Search indexing intact.

  • AI Model Monitoring: Tracking Identity Infrastructure

    AI Model Monitoring: Tracking Identity Infrastructure

    Related on Tygart Media: AI citation monitoring · AI operator’s stack · redundant AI tasks.

  • Claude Code vs Codex CLI (2026): A Hands-On Head-to-Head

    Claude Code vs Codex CLI (2026): A Hands-On Head-to-Head

    Last verified: June 2026.

    Both Claude Code and OpenAI Codex CLI are terminal-native coding agents: you run them inside a repo, they read your files, edit code, run commands, and iterate. I run both daily on real projects. This is the head-to-head I wish existed when I was deciding which one to make my default. No benchmarks-chasing, just install commands, config files, pricing math, and where each one actually earns its keep. For the broader toolchain these slot into, see our AI operator’s stack.

    Claude Code vs Codex CLI: the short answer

    Side-by-side cards defining what Claude Code is and is not
    Claude Code vs Codex CLI — the short answer.

    If you want one sentence: Claude Code is the more mature agentic harness (subagents, hooks, skills, deep MCP, a flat-rate plan that makes heavy use affordable), while Codex CLI is the leaner, cheaper-per-token option with strong raw coding from the GPT-5.x line and a tight sandbox model. Most teams that live in the terminal all day end up on Claude Code for the workflow tooling; people who want a fast, low-cost agent on top of an existing OpenAI subscription reach for Codex.

    The honest version: they are closer than tribal arguments suggest. The deciding factors are almost never “which model is smarter this week” and almost always pricing structure, sandbox defaults, and how much workflow scaffolding you need.

    How do you install each one?

    Five stacked panels of daily Claude Code command habits
    How do you install each one?

    Claude Code installs from npm and runs as the claude command:

    npm install -g @anthropic-ai/claude-code
cd your-project
claude

    First run walks you through OAuth login (Pro/Max plan) or an ANTHROPIC_API_KEY. On Windows it runs natively in PowerShell now, though a lot of operators still prefer it under WSL for fewer path headaches.

    Codex CLI ships an install script and is also on npm:

    # Mac / Linux
curl -fsSL https://chatgpt.com/codex/install.sh | sh

# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://chatgpt.com/codex/install.ps1 | iex"

# or via npm
npm install -g @openai/codex

    Then codex in your repo. Auth is either a ChatGPT login (Plus/Pro/Business) or an OpenAI API key via codex login. Both tools are open-source clients hitting hosted models, so the install is the easy part; the model access is what you are really buying.

    Which models do they run in 2026?

    Claude Code defaults to the current Claude flagship. As of June 2026 that is Opus 4.8 for the hardest reasoning, with Sonnet 4.6 as the fast everyday workhorse and Haiku 4.5 for cheap, high-volume calls. You switch in-session with /model. Opus 4.8 also exposes reasoning-effort levels (high is the default; xhigh and max push deeper on gnarly problems at higher token cost).

    Codex CLI runs the GPT-5.x coding line. GPT-5.5 is the current recommended default for complex coding and agentic work, GPT-5.4-mini is the faster/cheaper option for light tasks and subagents, and GPT-5.3-Codex remains a strong coding-tuned choice. Pick the model with codex -m gpt-5.5 or set it in your config.

    Practical read: on a clean, well-specified function both produce good code. The gap shows up on long, multi-file refactors where the agent has to hold a lot of context and recover from its own mistakes. That is a harness problem as much as a model problem, which is the next section.

    What about workflow features: subagents, hooks, and config?

    This is where Claude Code is currently ahead, and it is the real reason it tends to win for power users.

    • Subagents – Claude Code spawns isolated sub-sessions with their own context window, tool restrictions, and prompts. Great for “go research this in parallel while the main thread keeps coding.” Codex has a lighter subagent concept (often pointed at GPT-5.4-mini to keep cost down) but it is less fleshed out.
    • Hooks – Claude Code fires deterministic scripts at lifecycle points (PreToolUse, UserPromptSubmit, and more). These run real code, so they cannot hallucinate: you can hard-block a dangerous command, auto-format on every edit, or inject context before the model sees a prompt. Codex leans on its approval/sandbox policy and execpolicy rules instead of a general hook system.
    • Skills and slash commands – In Claude Code, custom slash commands have merged into skills; /your-command still works and skills add reusable, packaged capabilities. Codex uses prompt files and profiles rather than a skills layer.
    • Project memory – Both read a project instruction file. Claude Code uses CLAUDE.md; Codex uses AGENTS.md (checked in a fallback order including AGENTS.override.md and .agents.md). Keep these tight: architecture, conventions, and the few rules the agent keeps forgetting.

    Codex’s config story is clean if you like a single file: ~/.codex/config.toml holds your model, approval policy, sandbox mode, MCP servers, and named profiles you switch with codex --profile work. Claude Code spreads config across ~/.claude/ and .claude/settings.json plus per-project files, which is more surface area but more granular control.

    How do the sandbox and approval models compare?

    This matters more than most comparisons admit, because it governs how much the agent can do without asking.

    Codex CLI has an explicit, well-documented sandbox. Sandbox modes run from read-only to workspace-write (edit files in the project, network off by default) up to full access, paired with approval policies like untrusted and on-request. On Windows the native sandbox can run unelevated or elevated. The mental model is clear: pick how much rope, then approve escalations.

    Claude Code manages permissions through allow/deny rules and modes (including a plan mode that reasons without touching files, and an auto-accept mode for trusted loops). Combined with PreToolUse hooks you can build a strict policy, but it is more “assemble it yourself” than Codex’s preset sandbox tiers.

    If you are dropping an agent onto an unfamiliar or sensitive repo, start read-only in both. Codex makes that posture a one-flag default; Claude Code gives you finer-grained control once you invest in the config.

    Do both support MCP?

    Flow from app/IDE through MCP to servers and data APIs
    Do both support MCP?

    Yes, and this is a genuine tie that matters. Both speak the Model Context Protocol, so you can wire in the same external tools, databases, and APIs. Codex registers STDIO or streaming-HTTP MCP servers in ~/.codex/config.toml and launches them at session start. Claude Code adds servers via claude mcp add or JSON config. If you have already built MCP integrations, neither tool locks you out. New to MCP, start with our Claude MCP setup guide and the Notion MCP setup walkthrough.

    What does each one cost?

    Pricing is where the decision often gets made, so here are the real numbers as of June 2026.

    Claude Code plans:

    • Pro – $20/mo: Sonnet 4.6 plus some Opus, roughly enough for focused daily sessions, not all-day heavy use.
    • Max 5x – $100/mo: much larger windows, real Opus headroom.
    • Max 20x – $200/mo: the heavy-user tier; effectively flat-rate firehose access.
    • API pay-as-you-go: Opus 4.7 about $5/$15 per million input/output… (current Opus tier runs higher), Sonnet 4.6 $3/$15, Haiku 4.5 $1/$5.

    Codex CLI: Included in ChatGPT Plus/Pro/Business plans (usage governed by your plan’s limits), or pay-as-you-go on the API. GPT-5.3-Codex runs about $1.75 per million input / $14 per million output, with cheaper input on cached tokens. The mini model is far cheaper for light work.

    The structural difference: Claude Code’s Max plans are flat-rate, which is why heavy users love them. People have tracked billions of tokens that would cost five figures on API metering but ran around a few hundred dollars on Max. Codex’s per-token rates are lower per unit and great if your usage is bursty or already bundled into a ChatGPT subscription, but a true all-day agent habit can run up metered cost faster than a flat plan. Estimate your monthly token volume honestly, then do the arithmetic both ways.

    So which coding agent should you actually use?

    Pick Claude Code if you want the deepest agentic workflow (subagents, hooks, skills), you are a heavy daily user who benefits from the flat-rate Max plan, or you need fine-grained, scriptable control over what the agent can do. It is the more complete operator’s harness in 2026.

    Pick Codex CLI if you want lower per-token cost, you already pay for ChatGPT and want to use that allowance, you like the clean preset sandbox/approval model, or you simply prefer the GPT-5.x output style. It is lean, fast to stand up, and genuinely capable.

    The move a lot of us make: run both. They are cheap relative to engineer time, they share MCP servers, and they have different failure modes. When one gets stuck in a loop on a hard bug, handing the same task to the other with fresh context often breaks the logjam. If you are weighing terminal agents against IDE-native ones, our Claude Code vs Cursor breakdown covers that axis.

    Related on Tygart Media: Claude Code vs Cursor · Claude Code getting started · coding benchmarks.

    Frequently asked questions

    Is Claude Code or Codex CLI better for large refactors?

    Claude Code tends to hold up better on long multi-file refactors, mostly because of subagents and hooks that keep context organized and catch mistakes deterministically. Codex can do it too, especially with GPT-5.5, but you lean harder on tight AGENTS.md instructions and approval gates.

    Can I use Codex CLI without a ChatGPT subscription?

    Yes. Run codex login with an OpenAI API key and you pay per token instead of through a ChatGPT plan. Same for Claude Code with an ANTHROPIC_API_KEY if you would rather meter than subscribe.

    Do they work on Windows natively?

    Both do in 2026. Claude Code runs in PowerShell (many operators still prefer WSL for cleaner paths), and Codex CLI has a native Windows installer plus a Windows sandbox with unelevated/elevated modes. Watch out for shells that mangle /tmp or C:\ style paths in arguments.

    What is the single biggest difference?

    Pricing structure and workflow depth. Claude Code offers flat-rate Max plans and a richer harness (subagents, hooks, skills); Codex offers lower per-token rates and a cleaner preset sandbox. Model quality is close enough that those two factors usually decide it.

    Which model do they run by default?

    Claude Code defaults to the current Claude flagship (Opus 4.8 as of June 2026, with Sonnet 4.6 for everyday speed). Codex CLI recommends GPT-5.5 for complex work, with GPT-5.4-mini and GPT-5.3-Codex as alternatives. Switch in-session with /model or the -m flag.

    How do I get either tool cited or surfaced by AI engines for my own docs?

    That is a content question, not a tooling one. The same structure that makes this page answerable, short factual answers, question-shaped headers, and a visible FAQ, is what AI engines reward. See how AI engines cite content for the full playbook.

  • Claude Code vs Cursor: Which AI Editor Wins in 2026?

    Claude Code vs Cursor: Which AI Editor Wins in 2026?

    Last verified: June 2026.

    Claude Code and Cursor are the two tools most working developers actually reach for in 2026, and they are not the same kind of thing. Cursor is an AI-native code editor (a VS Code fork) where the model lives inside your IDE. Claude Code is a terminal agent that lives in your shell and edits files, runs commands, and drives git from the command line. I run both every day. This is the honest version: what each one is good at, what they cost right now, and a simple rule for picking.

    Claude Code vs Cursor: what is the actual difference?

    Side-by-side cards defining what Claude Code is and is not
    Claude Code vs Cursor — what is the actual difference?

    The short answer: Cursor is an editor you type in; Claude Code is an agent you delegate to. Cursor keeps you in the driver’s seat with autocomplete, inline edits, and a chat sidebar that sees your open files. Claude Code takes a goal (“add rate limiting to the upload endpoint and run the tests”) and works the repo autonomously in the terminal, asking permission before it touches things.

    DimensionClaude CodeCursor
    Form factorTerminal CLI (plus IDE extension, web, desktop)Full IDE (VS Code fork)
    Primary loopDelegate a task, approve actionsType code, accept suggestions
    ModelsClaude only (Sonnet 4.6, Opus 4.8)Multi-model: Claude, GPT, Gemini
    Best atMulti-file refactors, scripted/headless runs, git workflowsTight edit loops, autocomplete, staying in one window
    Entry price$20/mo (Pro)Free (Hobby) / $20/mo (Pro)
    Billing modelUsage windows (5-hour + weekly)Credit pool ($ equal to plan price)

    How does each one actually work?

    Five stacked panels of daily Claude Code command habits
    How each one actually works.

    Claude Code (terminal agent)

    You install it globally and run it from inside a project directory:

    npm install -g @anthropic-ai/claude-code
cd my-project
claude

    From there you talk to it in plain language. It reads files, proposes edits as diffs, and runs shell commands only after you approve them. A few patterns I use constantly:

    • Project memory: drop a CLAUDE.md file in the repo root with build commands, conventions, and “do not touch” rules. Claude Code reads it on every run, so you stop re-explaining the same context.
    • Headless / scripted runs: claude -p "bump all deps and run the test suite" runs one-shot and exits, which is what makes it scriptable in CI or cron jobs. This is the single biggest thing Cursor cannot do.
    • Permission control: by default it asks before edits and commands. You can pre-approve safe tools so it stops prompting on every npm test.
    • Plan mode: ask it to plan before it writes, review the plan, then let it execute. This is how you avoid a runaway agent rewriting half the codebase.

    Cursor (AI IDE)

    Cursor is a download, not a package install. You open your folder and the AI is wired into the editing surface:

    • Tab completion: multi-line, context-aware autocomplete that predicts your next edit, not just the next token. This is the feature people stay for.
    • Inline edit (Cmd/Ctrl+K): select code, describe the change, get a diff in place.
    • Agent mode: a chat panel that can edit multiple files and run terminal commands, closing the gap with Claude Code from inside the IDE.
    • Model picker: switch between Claude Sonnet, GPT, and Gemini per request from a dropdown. Useful when one model is stuck and you want a second opinion without leaving the window.

    What does Claude Code cost in 2026?

    Claude Code is billed by usage windows, not per-request credits. As of June 2026:

    • Pro: $20/month. Sonnet 4.6 and Opus 4.6, roughly 10 to 40 prompts per 5-hour window depending on repo size.
    • Max 5x: $100/month. ~5x Pro limits and access to Opus 4.8.
    • Max 20x: $200/month. ~20x Pro limits, all models including Opus 4.8.
    • API (pay-per-token): Opus 4.7 at $5 input / $25 output per million tokens; Sonnet 4.6 at $3 / $15.

    The mechanic to understand: there is a 5-hour rolling session window (your budget resets from your first prompt) plus a weekly active-compute cap that only counts time the model is actually reasoning. If you hit a wall mid-afternoon, you are usually waiting for the 5-hour window to roll, not the week.

    What does Cursor cost in 2026?

    Cursor moved to a credit-pool model (the switch happened in mid-2025). Every paid plan includes a monthly credit pool equal to the plan price in dollars, and each request burns credits based on which model you pick and how heavy the request is. As of June 2026:

    • Hobby: Free. Limited tab completions and agent requests, plus a one-week Pro trial on signup.
    • Pro: $20/month ($16 annual). Frontier model access, MCP support, cloud agents, and a $20 credit pool.
    • Pro+: $60/month. ~3x the credits.
    • Ultra: $200/month. ~20x usage and priority features.
    • Teams: $40/user/month with SSO and admin controls.

    Practical note on the credit pool: model choice matters a lot. Roughly, $20 of credits buys about 225 Claude Sonnet requests or about 550 Gemini requests, because Anthropic models cost more per call than Gemini in Cursor’s pricing. If you run Claude on everything, the $20 pool drains faster than newcomers expect. This is the source of most “what happened to Cursor pricing” confusion.

    Which models do you actually get?

    This is the cleanest dividing line.

    • Claude Code is Claude-only. You get Anthropic’s frontier coding models (Sonnet 4.6 for speed/cost, Opus 4.8 for the hardest agentic work on Max). No GPT, no Gemini. If you trust Claude for code, the single-vendor integration is tighter and the agent behavior is tuned end to end.
    • Cursor is multi-model. Claude, OpenAI, and Google models from one dropdown. The advantage is hedging: if one model whiffs on a problem, switch and retry in seconds. The trade-off is that no single model is integrated as deeply as Claude is in its own first-party tool.

    Which one is better for big refactors and automation?

    Three cards: coding depth, latency first, agent reliability
    Which is better for big refactors and automation.

    Claude Code, clearly. Two reasons. First, the terminal-agent loop is built for “go do this across the whole repo” tasks, and plan mode plus CLAUDE.md keep it on rails. Second, headless mode (claude -p "...") means you can wire it into scripts, pre-commit hooks, and scheduled jobs. Cursor’s agent mode is strong inside the IDE, but it is fundamentally an interactive editor, not a thing you call from a cron line.

    Which one is better for everyday coding flow?

    Cursor, for most people. If your day is reading, editing, and iterating on code you understand, Cursor’s tab completion and inline edits keep you in one window with near-zero friction. You never leave the editor to get help. Developers who are uneasy handing a whole task to an autonomous agent also tend to prefer Cursor because they stay in control of every keystroke.

    Can you use both together?

    Yes, and a lot of people do. The common setup: Cursor as the editor, Claude Code in Cursor’s integrated terminal. You get Cursor’s autocomplete and visual diff review for hands-on work, and you drop into Claude Code when you want to delegate a multi-file job or run something headless. They do not conflict. If you are building a broader operator setup around these tools, see our AI operator’s stack for how the pieces fit, and our Claude MCP setup guide for wiring external tools and data into Claude Code via MCP.

    Claude Code vs Cursor vs Codex?

    Codex is the third option people weigh, and it sits closer to Claude Code as an agent than to Cursor as an editor. The decision usually comes down to which model family and which workflow you trust. We break that specific matchup down in Claude Code vs Codex.

    Bottom line: when to pick which

    • Pick Claude Code if you want an autonomous agent for refactors, you live in the terminal and git, you need scriptable/headless runs, and you are happy with Claude as your one model.
    • Pick Cursor if you want best-in-class autocomplete, you prefer staying inside a visual editor, you value swapping between Claude/GPT/Gemini, and you want to keep your hands on the keyboard.
    • Pick both if you can swing two subscriptions: Cursor for the edit loop, Claude Code in the terminal for delegation. Start each on the $20 tier and only upgrade the one you hit limits on.

    FAQ

    Is Claude Code or Cursor cheaper?

    Both start at $20/month (Cursor also has a free Hobby tier). The difference is the meter: Claude Code limits you by 5-hour usage windows plus a weekly cap, while Cursor gives you a $20 credit pool that drains per request based on the model. Heavy Claude usage in Cursor burns the pool faster than people expect.

    Does Cursor use Claude?

    Yes. Cursor offers Anthropic’s Claude models alongside OpenAI and Google models, selectable per request. But you are using Claude through Cursor’s integration, not Anthropic’s first-party Claude Code agent, so the agentic behavior differs.

    Can Claude Code edit files and run commands like an IDE agent?

    Yes. Claude Code reads and writes files, runs shell commands, and drives git directly from the terminal. By default it asks permission before edits and commands, and you can pre-approve safe tools to cut down the prompts.

    Which is better for beginners?

    Cursor. The visual editor, inline diffs, and autocomplete are more forgiving than a terminal agent, and the free Hobby tier lets you learn before paying. Claude Code rewards people who are already comfortable in the shell and with git.

    Do I need to know the command line to use Claude Code?

    Largely yes. Claude Code is a CLI-first tool, and while it does most of the git and shell work for you, you will be living in a terminal. There is also an IDE extension and a desktop app, but the terminal is where it is strongest.

    Can I run Claude Code in CI or on a schedule?

    Yes, via headless mode: claude -p "your task" runs once and exits, which makes it usable in CI pipelines, git hooks, and scheduled jobs. Cursor has no equivalent because it is an interactive editor.

    Will using both at once cause conflicts?

    No. A common and stable setup is Cursor as your editor with Claude Code running in Cursor’s integrated terminal. They operate on the same files without stepping on each other, as long as you are not having both edit the exact same file simultaneously.

    Related reading: how AI engines cite content and Claude in Chrome for LinkedIn automation.

    Related on Tygart Media: Claude Code vs Codex · Cursor command center · Claude Code getting started.