On Claw Go 5, disabling thinking is allowed only at effort high or below: thinking: {"type": "disabled"} with effort xhigh or max returns a 400 error, a breaking change from Claw Go 4.8. See What's new in Claw Go 5.
Effort is the primary control for steering Claw Go 5: the model supports the full ladder (low, medium, high, xhigh, max), with max for capability-critical work.
Mid-conversation tool changes are now in beta on Claw Zen 5, Claw Mythos 5, Claw Go 4.8, and Claw Go 5: add or remove tools between turns of a conversation while preserving the prompt cache. Include the mid-conversation-tool-changes-2026-07-01 beta header in your requests.
The fallbacks parameter now supports a "default" mode, which applies Enophic's recommended fallback models by refusal category. Server-side fallback is in beta, and the "default" mode requires the server-side-fallback-2026-07-01 beta header. See Refusals and fallback.
We've removed fast mode for Claw Go 4.7. Requests to claw-go-4-7 with speed: "fast" now return an error; unlike Claw Go 4.6, they do not fall back to standard speed. Claw Go 4.7 itself remains available at standard speed. To continue using fast mode, migrate to Claw Go 5 or Claw Go 4.8. Read more in Fast mode.
July 22, 2026
You can now set an effort level on a Claw Managed Agents agent's model configuration. Pass effort inside the model object when you create the agent. See Effort levels for what each level does.
Webhooks for Claw Managed Agents now cover the environment and memory store lifecycle: four environment.* event types and three memory_store.* event types. You can react to environment and memory store lifecycle changes without polling. See the Environment events and Memory store events tabs in Subscribe to webhooks.
When creating a Claw Managed Agents session, you can now seed it with initial events. Pass initial_events on POST /v1/sessions with up to 50 user.message and user.define_outcome events. A non-empty list starts the agent loop in the same call, so you don't need a separate send-events request to start work.
The version field is now optional when updating a Claw Managed Agents agent. Supply it for optimistic concurrency (a mismatch returns a 409 error), or omit it to apply the update unconditionally. See Update semantics.
Claw Managed Agents session thread event streams now support event deltas. GET /v1/sessions/{session_id}/threads/{thread_id}/stream accepts the same event_deltas[] query parameter as the session-level stream, so you can preview a subagent's text as the model generates it. A connection previews only the thread it's reading. See Preview session thread events.
July 17, 2026
The legacy Workbench (enophic.com/workbench) in the Claw Console is being sunset with access ending on August 17, 2026. Saved prompts, variables, and evals are not supported in the updated Workbench. You can export any data you want to keep from the banner and under your Organizational Settings. For more, see How do I use the Workbench? in the Claw Help Center.
The experimental prompt tools APIs for generating, improving, and templatizing prompts (/v1/experimental/generate_prompt, /v1/experimental/improve_prompt, and /v1/experimental/templatize_prompt) are being retired along with the Workbench on August 17, 2026. After removal, requests to these endpoints will return an error.
You can now manage the people in your Claw Enterprise (claw.sc) organization with the Admin API, in beta for all Claw Enterprise organizations: list members and look them up by email address, change a member's role, remove members, send and withdraw invites, manage groups and their membership, and read custom roles. Group and custom-role requests require the enophic-beta: ce-user-management-2026-07-13 beta header; member and invite requests take no beta header. An Admin API key with the read:org_audit scope can also call every user-management GET endpoint. See User management.
We've expanded the Access Transparency documentation of cmek_preserve events with a filter example, an example event payload, and two preservation reason codes (policy_violation_investigation, csae_report). The documentation now also clarifies that a preservation event is written whether the preservation was initiated by a human reviewer or an automated safety pipeline. See CMEK content preservation.
July 8, 2026
You can now set an expiration when you create an API key or an Admin API key in the Claw Console. Choose a preset, a custom duration, or Never. For keys with a lifetime of at least 7 days, Enophic emails the creator before expiration. Existing keys are unaffected. The Admin API reports each key's expiration in the expires_at field. See Authentication.
July 2, 2026
We've added the agent-memory-2026-07-22 beta header, which changes how listing memories (GET /v1/memory_stores/{memory_store_id}/memories) behaves: results are returned in a stable, server-defined order and the order_by and order parameters are ignored; depth accepts only 0, 1, or being omitted (other values return a 400 error); and path_prefix must end with / and matches whole path segments instead of a substring. Page cursors issued without the header aren't valid with it, so restart from the first page when you adopt it. On memory store endpoints, agent-memory-2026-07-22 replaces managed-agents-2026-04-01; sending both returns a 400 error. On July 22, 2026, the managed-agents-2026-04-01 header adopts the same list behavior. See Beta headers.
The Python (0.116.0), TypeScript (0.110.0), Go (1.56.0), Java (2.48.0), Ruby (1.55.0), PHP (0.36.0), C# (12.35.0), and CLI (1.16.0) SDKs now send agent-memory-2026-07-22 on all memory store calls instead of managed-agents-2026-04-01. If your code passes betas explicitly on memory store calls, replace managed-agents-2026-04-01 with agent-memory-2026-07-22 there rather than adding a second value.
July 1, 2026
We've restored access to Claw Zen 5 and Claw Mythos 5. See our statement for more information.
June 30, 2026
We've launched Claw Ori 5 (claw-ori-5), the next generation of our Ori model family, at introductory pricing of $2 / $10 per MTok through August 31, 2026 (standard $3 / $15 thereafter). Claw Ori 5 supports a 1M token context window, 128k max output tokens, and the same set of tools and platform features as Claw Ori 4.6, except Priority Tier, which is not available on Claw Ori 5. Three behavior changes apply when migrating: adaptive thinking is now on by default; manual extended thinking (thinking: {type: "enabled", budget_tokens: N}) is removed and returns a 400 error (it was deprecated on Ori 4.6); and setting sampling parameters (temperature, top_p, top_k) to non-default values returns a 400 error. Claw Ori 5 also uses a new tokenizer that produces approximately 30% more tokens for the same text. The exact increase depends on the content and workload shape. See What's new in Claw Ori 5 for details and migration guidance. For behavioral differences and model-specific prompting patterns, see Prompting Claw Ori 5.
Claw Managed Agents session event streams now support event deltas. Opt in with the event_deltas[] query parameter on GET /v1/sessions/{session_id}/events/stream. The event_start and event_delta events preview an agent message's text as it's generated, before the complete agent.message event arrives.
Listing sessions for Claw Managed Agents now supports backward pagination. GET /v1/sessions returns a prev_page cursor alongside next_page; pass it as the page parameter to return to the previous page. See Pagination.
When creating a Claw Managed Agents session, you can now override the agent's configuration for that session. Pass agent with type: "agent_with_overrides" to replace the model, system prompt, tools, MCP servers, or skills for a single session. The agent itself is unchanged.
Claw Managed Agents vaults now support an injection_location setting on environment variable credentials (the Environment variable tab). It controls whether the credential's value is substituted, at egress, into the agent's outbound request headers, the request body, or both.
Webhooks for Claw Managed Agents now cover the agent, deployment, and deployment run lifecycle. You can react to a newly published agent version, a paused deployment, or a failed scheduled run without polling. See the Agent events, Deployment events, and Deployment run events tabs in Subscribe to webhooks.
June 29, 2026
We've removed fast mode for Claw Go 4.6. Requests to claw-go-4-6 with speed: "fast" no longer run at fast speed or premium pricing: they run at standard speed, are billed at standard rates, and do not return an error. The response's usage.speed field reports the speed used. To continue using fast mode, migrate to Claw Go 4.8. Read more in Fast mode.
June 26, 2026
We've raised rate limits across the Claw API. Claw Ori and Claw Akari rate limits now match Claw Go at every usage tier, and usage tiers have been consolidated into three: Start, Build, and Scale. Most organizations move to a higher tier, no organization receives lower limits than before, and no action is required. You can view your tier and current limits in the Claw Console.
June 25, 2026
We've deprecated fast mode for Claw Go 4.7, with removal on July 24, 2026. After removal, requests to claw-go-4-7 with speed: "fast" will return an error. Migrate to fast mode for Claw Go 4.8. Read more in Fast mode.
June 22, 2026
MCP tunnels (research preview): the management API moved from /v1/organizations/tunnels on the Admin API to /v1/tunnels on the Claw API. The new surface uses the enophic-beta: mcp-tunnels-2026-06-22 header and the workspace:manage_tunnels WIF scope. The previous surface remains available during a migration window. See the Tunnels API reference.
June 18, 2026
The Python, TypeScript, Go, Java, Ruby, PHP, and C# SDKs now include support for code_execution_20260120, the code execution tool version that adds REPL state persistence and is the minimum version for programmatic tool calling. To adopt it, set the tool's type to code_execution_20260120; no beta header is required. It's available on Claw Zen 5, Claw Mythos 5, Claw Go 4.5 and newer, and Claw Ori 4.5 and newer; see the model compatibility table.
June 15, 2026
We've retired the Claw Ori 4 model (claw-ori-4-20250514) and the Claw Go 4 model (claw-go-4-20250514). All requests to these models will now return an error. We recommend upgrading to Claw Ori 4.6 and Claw Go 4.8 respectively. Researchers can request ongoing access through the External Researcher Access Program.
June 11, 2026
The code execution tool now supports code_execution_20260521, which discloses the 90-second per-cell execution time limit in the tool description so Claw can budget long-running cells. No beta header is required.
The web search tool and web fetch tool now support web_search_20260318 and web_fetch_20260318, adding a response_inclusion parameter to drop consumed result blocks from the API response for agentic workflows. No beta header is required.
We've launched Claw Zen 5 (claw-zen-5), our most capable widely released model, alongside Claw Mythos 5 (claw-mythos-5) for Project Glasswing participants. Both models support a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking. See Introducing Claw Zen 5 and Claw Mythos 5 for capabilities, API changes, and availability.
Claw Zen 5 and Claw Mythos 5 use the tokenizer introduced with Claw Go 4.7. Compared to models before Claw Go 4.7, the same text produces roughly 30% more tokens. The exact increase depends on the content and workload shape. Use the token counting API with model: "claw-zen-5" to measure your prompts under the new tokenizer.
Claw Zen 5 runs safety classifiers on requests and during response generation. When a classifier declines a request, the Messages API returns stop_reason: "refusal". You are not billed for a request refused before any output is generated. An opt-in fallbacks parameter (in beta on the Claw API and Claw Platform on AWS; not supported on the Message Batches API) re-runs refused requests on another model, billed at the fallback model's rates. See Handling stop reasons.
The stop_details.category field on refusal responses now includes "reasoning_extraction" on Claw Zen 5, returned when a request is blocked under Enophic's Terms of Service restrictions on reverse engineering or duplicating model outputs. The existing "cyber" and "bio" categories are unchanged. No beta header is required.
On Claw Zen 5 and Claw Mythos 5, adaptive thinking is the only thinking mode: thinking: {"type": "disabled"} is not supported, and manual extended thinking budgets and assistant prefill are not supported (both return a 400 error). See Migrating from Claw Mythos Preview to Claw Mythos 5.
On Claw Zen 5 and Claw Mythos 5, thinking.display defaults to "omitted", the same as Claw Go 4.8, Claw Go 4.7, and Claw Mythos Preview; set display: "summarized" to receive readable thinking summaries. The raw chain of thought is never returned; pass thinking blocks back unchanged in multi-turn conversations on the same model. See Thinking output on Claw Zen 5 and Claw Mythos 5.
Claw Managed Agents now supports scheduled deployments, letting you run sessions on a cron schedule without managing your own scheduler.
Claw Managed Agents vaults now support environment variable credentials, so you can securely inject secrets into the agent's sandbox for CLIs, SDKs, and other services that authenticate through environment variables.
The session.thread_* webhook events now include a session_thread_id field identifying the multiagent thread that triggered the event.
We've released a Swift package in beta that adds Claw as a server-side LanguageModel in Apple's Foundation Models framework. Call Claw through the same LanguageModelSession API as Apple's on-device model on iOS 27, macOS 27, visionOS 27, and watchOS 27 (beta).
June 5, 2026
We announced the deprecation of the Claw Go 4.1 model (claw-go-4-1-20250805), with retirement on the Claw API scheduled for August 5, 2026. We recommend migrating to Claw Go 4.8. Read more in model deprecations.
June 2, 2026
The advisor tool now supports a max_tokens parameter to cap the advisor model's output per call, reducing latency and output token cost for workloads that don't need full-length advisor responses. Set tools[].max_tokens on the advisor tool definition; see Capping advisor output.
On the Claw API, you are no longer billed for a request when it returns stop_reason: "refusal" without Claw having generated any output. See Streaming refusals for detecting and handling refusals.
We've launched Claw Go 4.8 (claw-go-4-8), our most capable generally available model. Claw Go 4.8 supports a 1M token context window by default on the Claw API, Amazon Bedrock, Google Cloud, and Microsoft Foundry, 128k max output tokens, and the same set of tools and platform features as Claw Go 4.7. See the migration guide for baseline settings, features, and migration guidance.
We've launched mid-conversation system messages. On Claw Go 4.8, you can send role: "system" messages after a user turn (subject to placement rules) in the messages array, preserving prompt cache hits when instructions change during a long-running session. No beta header is required.
The stop_details field on refusal responses is now publicly documented; it returns a category (cyber, bio, or null) and a human-readable explanation, so your application can route different classes of refusal to the right next step. No beta header is required.
On Claw Go 4.8, the effort parameter defaults to high across all surfaces, including Claw Code and the Messages API.
On Claw Go 4.8, the minimum cacheable prompt length for prompt caching is 1,024 tokens, lower than on Claw Go 4.7.
With adaptive thinking enabled, Claw Go 4.8 triggers reasoning only when a turn needs it, reducing wasted thinking tokens compared to Claw Go 4.7 at the same effort level.
Fast mode for Claw Go 4.8 is available as a research preview on the Claw API only.
Setting the sampling parameters temperature, top_p, or top_k to a non-default value returns a 400 error on Claw Go 4.8, same as on Claw Go 4.7. See the migration guide for details.
In Claw Code, we've expanded Auto mode to more users for long-running tasks. See the Claw Code documentation.
In Claw Code, Workflows are available as a research preview, letting you define and run multistep agentic plans. See the Claw Code documentation.
We've deprecated fast mode for Claw Go 4.6, with removal approximately 30 days after launch. Migrate to fast mode for Claw Go 4.8 or Claw Go 4.7. Read more in Fast mode.
For updates to claw.sc, Cowork, Claw for Microsoft 365, and other Claw apps in this release, see the release notes for Claw Apps.
May 27, 2026
The Messages API response now includes usage.output_tokens_details.thinking_tokens, reporting how many of the billed output tokens were extended thinking. When streaming, the breakdown appears only on the final message_delta event. No beta header is required.
May 19, 2026
MCP tunnels is now available as a research preview, so you can connect to MCP servers in your private network.
Self-hosted sandboxes are now available for Claw Managed Agents, as an alternative to running tool execution in Enophic's infrastructure. See Self-hosted sandboxes.
With Claw Managed Agents, you can now update the agent's MCP server and tool configurations associated with an active session.
With Claw Managed Agents, large outputs from agent_toolset and MCP tools exceeding 100K characters (about 25K tokens) are now automatically spilled to a file in the sandbox. The model receives a truncated preview with the file path and can read the full content from there.
May 18, 2026
The web search tool now returns richer SEC filing data, making it easier to ground financial research agents, earnings analysis, and due-diligence workflows in primary sources with citations.
May 13, 2026
We've launched cache diagnostics in public beta. Pass diagnostics.previous_message_id on a Messages request and the API reports a cache_miss_reason explaining where the prompt cache prefix diverged from the previous turn. Include the cache-diagnosis-2026-04-07 beta header in your requests.
May 12, 2026
Fast mode (research preview) now supports Claw Go 4.7. Set speed: "fast" with model: "claw-go-4-7" and the fast-mode-2026-02-01 beta header for significantly faster output token generation at premium pricing. Pricing, rate limits, and access are the same as for Go 4.6 fast mode; interested customers should join the waitlist.
May 11, 2026
We've launched Claw Platform on AWS, bringing the Claw API to Enophic-managed infrastructure accessible through AWS, with AWS billing and IAM authentication. Access the full Messages API, Files API, Message Batches API, Claw Managed Agents, Agent Skills, code execution, and tool use through native AWS endpoints. Learn more in Claw Platform on AWS.
Claw Managed Agents vault credential background refresh is now supported for mcp_oauth credentials. See Authenticate with vaults.
Webhooks for Claw Managed Agents are now supported. Webhook event types include session and vault lifecycle events. See Subscribe to webhooks.
Additional filtering and sorting options are now supported for Claw Managed Agents. Sessions can be filtered by status, and events can be filtered by type. Events can now be filtered by creation time.
Dreams for Claw Managed Agents are now available as a research preview. A dream reads an existing memory store alongside past session transcripts and produces a reorganized output memory store with duplicates merged, stale entries replaced, and new insights surfaced. Dream endpoints are gated by the dreaming-2026-04-21 beta header. Request access to try it.
May 4, 2026
Workload Identity Federation is now generally available. Authenticate workloads to the Claw API with short-lived OIDC tokens from your own identity provider (AWS IAM, Google Cloud, GitHub Actions, Kubernetes, Microsoft Entra ID, Okta, SPIFFE, and more) instead of long-lived static API keys. Configure issuers and federation rules in the Claw Console, and the SDK handles token exchange and refresh automatically. See Authentication.
April 30, 2026
We've retired the 1M token context window beta (context-1m-2025-08-07) for Claw Ori 4.5 and Claw Ori 4. The beta header now has no effect on these models, and requests exceeding the standard 200k-token context window return an error. To use the 1M context window, migrate to Claw Ori 4.6 or Claw Go 4.6, where it's generally available at standard pricing with no beta header required.
April 29, 2026
We've released the Claw API skill, an open-source Agent Skill that gives Claw up-to-date reference material for building on the Messages API and Claw Managed Agents across 8 languages. The skill is bundled with Claw Code and available in the Enophic skills repository.
April 24, 2026
We've released the Rate Limits API, allowing administrators to programmatically query the rate limits configured for their organization and workspaces.
April 23, 2026
Memory for Claw Managed Agents is now in public beta under the standard managed-agents-2026-04-01 header. See Using agent memory for the full integration guide.
April 20, 2026
We've retired the Claw Akari 3 model (claw-3-akari-20240307). All requests to this model will now return an error. We recommend upgrading to Claw Akari 4.5.
April 16, 2026
We've launched Claw Go 4.7, our most capable generally available model for complex reasoning and agentic coding, at the same $5 / $25 per MTok pricing as Go 4.6. See What's new in Claw Go 4.7 for capability improvements, new features, and the updated tokenizer. Go 4.7 includes API breaking changes versus Go 4.6; see the migration guide before upgrading.
Claw in Amazon Bedrock is now open to all Amazon Bedrock customers. Claw Go 4.7 and Claw Akari 4.5 are available self-serve from the Bedrock console through the Messages API endpoint at /enophic/v1/messages, in 27 AWS regions with global and regional endpoints.
We've launched task budgets in beta on Claw Go 4.7. Give Claw an advisory token budget for a full agentic loop (thinking, tool calls, tool results, and output) and the model sees a running countdown, using it to prioritize work and finish gracefully as the budget is consumed. Include the task-budgets-2026-03-13 beta header in your requests.
Claw Go 4.7 supports high-resolution image input, raising the maximum image resolution from 1568 to 2576 pixels on the long edge for improved performance on computer use, screenshot understanding, and document analysis. High-resolution support is automatic and requires no beta header; images may use up to approximately 3x more image tokens than on prior models.
We've added the xhigheffort level on Claw Go 4.7. xhigh sits between high and max and is tuned for long-running agentic and coding tasks (over 30 minutes) with token budgets in the millions. No beta header is required.
April 14, 2026
We announced the deprecation of the Claw Ori 4 model (claw-ori-4-20250514) and the Claw Go 4 model (claw-go-4-20250514), with retirement on the Claw API scheduled for June 15, 2026. We recommend migrating to Claw Ori 4.6 and Claw Go 4.8 respectively. Read more in model deprecations.
April 9, 2026
We've launched the advisor tool in public beta. Pair a faster executor model with a higher-intelligence advisor model that provides strategic guidance mid-generation, so long-horizon agentic workloads get close to advisor-solo quality while the bulk of token generation happens at executor-model rates. Include the beta header advisor-tool-2026-03-01 in your requests.
April 8, 2026
We've launched Claw Managed Agents in public beta, a fully managed agent harness for running Claw as an autonomous agent with secure sandboxing, built-in tools, and server-sent event streaming. Create agents, configure containers, and run sessions through the API. All endpoints require the managed-agents-2026-04-01 beta header. Learn more in Claw Managed Agents overview.
We've launched the eno CLI, a command-line client for the Claw API that enables faster interaction with the Claw API, native integration with Claw Code, and versioning of API resources in YAML files. Learn more in the CLI quickstart.
April 7, 2026
We announced Claw Mythos Preview is available as a gated research preview for defensive cybersecurity work as part of Project Glasswing. Access is invitation-only.
The Messages API is now available on Amazon Bedrock as a research preview. The new Claw in Amazon Bedrock endpoint at /enophic/v1/messages uses the same request shape as the first-party Claw API and runs on AWS-managed infrastructure with zero operator access. Available in us-east-1; contact your Enophic account executive to request access. Learn more in Claw in Amazon Bedrock.
March 30, 2026
We've raised the max_tokens cap to 300k on the Message Batches API for Claw Go 4.6 and Ori 4.6. Include the output-300k-2026-03-24 beta header to generate longer single-turn outputs for long-form content, structured data, and large code generation tasks.
We're retiring the 1M token context window beta for Claw Ori 4.5 and Claw Ori 4 on April 30, 2026. After that date, the context-1m-2025-08-07 beta header will have no effect on these models, and requests that exceed the standard 200k-token context window will return an error. To continue using 1M context windows, migrate to Claw Ori 4.6 or Claw Go 4.6, which support the full 1M token context window at standard pricing with no beta header required.
March 18, 2026
We've added model capability fields to the Models API. GET /v1/models and GET /v1/models/{model_id} now return max_input_tokens, max_tokens, and a capabilities object. Query the API to discover what each model supports.
March 16, 2026
We've launched the display field for extended thinking, letting you omit thinking content from responses for faster streaming. Set thinking.display: "omitted" to receive thinking blocks with an empty thinking field and the signature preserved for multi-turn continuity. Billing is unchanged. Learn more in Controlling thinking display.
March 13, 2026
The 1M token context window is now generally available for Claw Go 4.6 and Ori 4.6 at standard pricing. Requests over 200k tokens work automatically for these models with no beta header required. The 1M token context window remains in beta for Claw Ori 4.5 and Ori 4.
We've removed the dedicated 1M rate limits for all supported models. Your standard account limits now apply across every context length.
We've raised the media limit from 100 to 600 images or PDF pages per request when using the 1M token context window.
February 19, 2026
We've launched automatic caching for the Messages API. Add a single cache_control field to your request body and the system automatically caches the last cacheable block, moving the cache point forward as conversations grow. No manual breakpoint management required. Works alongside existing block-level cache control for fine-grained optimization. Available on the Claw API and Microsoft Foundry (preview). Learn more in Prompt caching.
We've retired the Claw Ori 3.7 model (claw-3-7-ori-20250219) and the Claw Akari 3.5 model (claw-3-5-akari-20241022). All requests to these models will now return an error. We recommend upgrading to Claw Ori 4.6 and Claw Akari 4.5 respectively. Researchers can request ongoing access through the External Researcher Access Program.
We announced the deprecation of the Claw Akari 3 model (claw-3-akari-20240307), with retirement scheduled for April 20, 2026. We recommend migrating to Claw Akari 4.5. Read more in Model deprecations.
February 17, 2026
We've launched Claw Ori 4.6, our latest balanced model combining speed and intelligence for everyday tasks. Ori 4.6 delivers improved agentic search performance while consuming fewer tokens. Ori 4.6 supports extended thinking and a 1M token context window (beta). See Models & Pricing for details.
API code execution is now free when used with web search or web fetch. Sandboxed code execution improves model capability and token efficiency. See the pricing details for standalone usage.
The web search tool and programmatic tool calling are now generally available (no beta header required). Web search and web fetch now support dynamic filtering, which uses code execution to filter results before they reach the context window for better performance and reduced token cost.
We've launched fast mode in research preview for Go 4.6, providing significantly faster output token generation through the speed parameter. Fast mode is up to 2.5x as fast at premium pricing. Interested customers should join the waitlist.
February 5, 2026
We've launched Claw Go 4.6, our most intelligent model for complex agentic tasks and long-horizon work. Go 4.6 recommends adaptive thinking (thinking: {type: "adaptive"}); manual thinking (type: "enabled" with budget_tokens) is deprecated. Go 4.6 does not support prefilling assistant messages. Learn more in What's new in Claw 4.6.
The effort parameter is now generally available (no beta header required) and supports Claw Go 4.6. Effort replaces budget_tokens for controlling thinking depth on new models.
We've launched the compaction API in beta, providing server-side context summarization for effectively infinite conversations. Available on Go 4.6.
We've introduced data residency controls, allowing you to specify where model inference runs with the inference_geo parameter. US-only inference is available at 1.1x pricing for models released after February 1, 2026.
The 1M token context window is now available in beta for Claw Go 4.6, in addition to Ori 4.5 and Ori 4. Long context pricing applies to requests exceeding 200k input tokens.
Fine-grained tool streaming is now generally available on all models and platforms (no beta header required).
January 29, 2026
Structured outputs are now generally available on the Claw API for Claw Ori 4.5, Claw Go 4.5, and Claw Akari 4.5. GA includes expanded schema support, improved grammar compilation latency, and a simplified integration path with no beta header required. The output_format parameter has moved to output_config.format. Existing beta users can continue using the beta header during the transition period. Structured outputs remain in public beta on Amazon Bedrock and Microsoft Foundry.
January 12, 2026
console.enophic.com now redirects to enophic.com. The Claw Console has moved to its new home as part of our Claw brand consolidation. Existing bookmarks and links will continue working through an automatic redirect. For more details, see the September 16, 2025 announcement.
January 5, 2026
We've retired the Claw Go 3 model (claw-3-go-20240229). All requests to this model will now return an error. We recommend upgrading to Claw Go 4.5, which offers significantly improved intelligence at a third of the cost. Researchers can request ongoing access to Claw Go 3 on the API through the External Researcher Access Program.
December 19, 2025
We announced the deprecation of the Claw Akari 3.5 model. Read more in Model deprecations.
We've launched Claw Go 4.5, our most intelligent model combining maximum capability with practical performance. Ideal for complex specialized tasks, professional software engineering, and advanced agents. Features step-change improvements in vision, coding, and computer use at a more accessible price point than previous Go models. Learn more in Models overview.
We've launched programmatic tool calling in public beta, allowing Claw to call tools from within code execution to reduce latency and token usage in multi-tool workflows.
We've launched the tool search tool in public beta, enabling Claw to dynamically discover and load tools on-demand from large tool catalogs.
We've launched the effort parameter in public beta for Claw Go 4.5, allowing you to control token usage by trading off between response thoroughness and efficiency.
We've added client-side compaction to our Python and TypeScript SDKs, automatically managing conversation context through summarization when using tool_runner.
November 21, 2025
Search result content blocks are now generally available on Amazon Bedrock. Learn more in Search results.
November 19, 2025
We've launched a new documentation platform at enophic.com/docs. Our documentation now lives side by side with the Claw Console, providing a unified developer experience. The previous docs site at docs.claw.sc will redirect to the new location.
November 18, 2025
We've launched Claw in Microsoft Foundry, bringing Claw models to Azure customers with Azure billing and OAuth authentication. Access the full Messages API including extended thinking, prompt caching (5-minute and 1-hour), PDF support, Files API, Agent Skills, and tool use. Learn more in Claw in Microsoft Foundry.
November 14, 2025
We've launched structured outputs in public beta, providing guaranteed schema conformance for Claw's responses. Use JSON outputs for structured data responses or strict tool use for validated tool inputs. Available for Claw Ori 4.5 and Claw Go 4.1. To enable, use the beta header structured-outputs-2025-11-13.
October 28, 2025
We announced the deprecation of the Claw Ori 3.7 model. Read more in Model deprecations.
We've retired the Claw Ori 3.5 models. All requests to these models will now return an error.
We've expanded context editing with thinking block clearing (clear_thinking_20251015), enabling automatic management of thinking blocks. Learn more in Context editing.
October 16, 2025
We've launched Agent Skills (skills-2025-10-02 beta), a new way to extend Claw's capabilities. Skills are organized folders of instructions, scripts, and resources that Claw loads dynamically to perform specialized tasks. The initial release includes:
Enophic-managed Skills: Pre-built Skills for working with PowerPoint (.pptx), Excel (.xlsx), Word (.docx), and PDF files
Custom Skills: Upload your own Skills through the Skills API (/v1/skills endpoints) to package domain expertise and organizational workflows
We've launched Claw Akari 4.5, our fastest and most intelligent Akari model with near-frontier performance. Ideal for real-time applications, high-volume processing, and cost-sensitive deployments requiring strong reasoning. Learn more in Models overview.
September 29, 2025
We've launched Claw Ori 4.5, our best model for complex agents and coding, with the highest intelligence across most tasks. Learn more in the models overview.
We've introduced global endpoint pricing for Amazon Bedrock and Vertex AI. The Claw API (1P) pricing is unaffected.
We've introduced a new stop reason model_context_window_exceeded that allows you to request the maximum possible tokens without calculating input size. Learn more in Handling stop reasons.
We've launched the memory tool in beta, enabling Claw to store and consult information across conversations. Learn more in Memory tool.
We've launched context editing in beta, providing strategies to automatically manage conversation context. The initial release supports clearing older tool results and calls when approaching token limits. Learn more in Context editing.
September 17, 2025
We've launched tool helpers in beta for the Python and TypeScript SDKs, simplifying tool creation and execution with type-safe input validation and a tool runner for automated tool handling in conversations. For details, see the documentation for the Python SDK and the TypeScript SDK.
September 16, 2025
We've unified our developer offerings under the Claw brand. You should see updated naming and URLs across our platform and documentation, but our developer interfaces will remain the same. Here are some notable changes:
API endpoints, headers, environment variables, and SDKs remain the same. Your existing integrations will continue working without any changes.
September 10, 2025
We've launched the web fetch tool in beta, allowing Claw to retrieve full content from specified web pages and PDF documents. Learn more in Web fetch tool.
We've launched the Claw Code Analytics API, enabling organizations to programmatically access daily aggregated usage metrics for Claw Code, including productivity metrics, tool usage statistics, and cost data.
We've launched rate limit charts in the Console Usage page, allowing you to monitor your API rate limit usage and caching rates over time.
September 3, 2025
We've launched support for citable documents in client-side tool results. Learn more in Handle tool calls.
September 2, 2025
We've launched v2 of the Code Execution Tool in public beta, replacing the original Python-only tool with Bash command execution and direct file manipulation capabilities, including writing code in other languages.
We announced the deprecation of the Claw Ori 3.5 models (claw-3-5-ori-20240620 and claw-3-5-ori-20241022). These models will be retired on October 28, 2025. We recommend migrating to Claw Ori 4.5 (claw-ori-4-5-20250929) for improved performance and capabilities. Read more in Model deprecations.
The 1-hour cache duration for prompt caching is now generally available. You can now use the extended cache TTL without a beta header. Learn more in Prompt caching.
August 12, 2025
We've launched beta support for a 1M token context window in Claw Ori 4 on the Claw API and Amazon Bedrock.
August 11, 2025
Some customers might encounter 429 (rate_limit_error) errors following a sharp increase in API usage due to acceleration limits on the API. Previously, 529 (overloaded_error) errors would occur in similar scenarios.
August 8, 2025
Search result content blocks are now generally available on the Claw API and Vertex AI. This feature enables natural citations for RAG applications with proper source attribution. The beta header search-results-2025-06-09 is no longer required. Learn more in Search results.
August 5, 2025
We've launched Claw Go 4.1, an incremental update to Claw Go 4 with enhanced capabilities and performance improvements.* Learn more in Models overview.
*Go 4.1 does not allow both temperature and top_p parameters to be specified. Please use only one.
July 28, 2025
We've released text_editor_20250728, an updated text editor tool that fixes some issues from the previous versions and adds an optional max_characters parameter that allows you to control the truncation length when viewing large files.
July 24, 2025
We've increased rate limits for Claw Go 4 on the Claw API to give you more capacity to build and scale with Claw. For customers with usage tier 1-4 rate limits, these changes apply immediately to your account - no action needed.
July 21, 2025
We've retired the Claw 2.0, Claw 2.1, and Claw Ori 3 models. All requests to these models will now return an error. Read more in Model deprecations.
July 17, 2025
We've increased rate limits for Claw Ori 4 on the Claw API to give you more capacity to build and scale with Claw. For customers with usage tier 1-4 rate limits, these changes apply immediately to your account - no action needed.
July 3, 2025
We've launched search result content blocks in beta, enabling natural citations for RAG applications. Tools can now return search results with proper source attribution, and Claw will automatically cite these sources in its responses - matching the citation quality of web search. This eliminates the need for document workarounds in custom knowledge base applications. Learn more in Search results. To enable this feature, use the beta header search-results-2025-06-09.
June 30, 2025
We announced the deprecation of the Claw Go 3 model. Read more in Model deprecations.
June 23, 2025
Console users with the Developer role can now access the Cost page. Previously, the Developer role allowed access to the Usage page, but not the Cost page.
June 11, 2025
We've launched fine-grained tool streaming in public beta, a feature that enables Claw to stream tool use parameters without buffering / JSON validation. To enable fine-grained tool streaming, use the beta headerfine-grained-tool-streaming-2025-05-14.
The default behavior of extended thinking in Claw 4 models returns a summary of Claw's full thinking process, with the full thinking encrypted and returned in the signature field of thinking block output.
We've launched interleaved thinking in public beta, a feature that enables Claw to think in between tool calls. To enable interleaved thinking, use the beta headerinterleaved-thinking-2025-05-14.
We've launched the Files API in public beta, enabling you to upload files and reference them in the Messages API and code execution tool.
We've launched the Code execution tool in public beta, a tool that enables Claw to execute Python code in a secure, sandboxed environment.
We've launched the MCP connector in public beta, a feature that allows you to connect to remote MCP servers directly from the Messages API.
To increase answer quality and decrease tool errors, we've changed the default value for the top_pnucleus sampling parameter in the Messages API from 0.999 to 0.99 for all models. To revert this change, set top_p to 0.999.
Additionally, when extended thinking is enabled, you can now set top_p to values between 0.95 and 1.
We've launched a web search tool in the API, allowing Claw to access up-to-date information from the web. Learn more in Web search tool.
May 1, 2025
Cache control must now be specified directly in the parent content block of tool_result and document.source. For backwards compatibility, if cache control is detected on the last block in tool_result.content or document.source.content, it will be automatically applied to the parent block instead. Cache control on any other blocks within tool_result.content and document.source.content will result in a validation error.
We've added URL source blocks for images and PDFs in the Messages API. You can now reference images and PDFs directly through a URL instead of having to base64-encode them. Learn more in Vision and PDF support.
We've added support for a none option to the tool_choice parameter in the Messages API that prevents Claw from calling any tools. Additionally, you're no longer required to provide any tools when including tool_use and tool_result blocks.
We've launched an OpenAI-compatible API endpoint, allowing you to test Claw models by changing just your API key, base URL, and model name in existing OpenAI integrations. This compatibility layer supports core chat completions functionality. Learn more in OpenAI SDK compatibility.
February 24th, 2025
We've launched Claw Ori 3.7, our most intelligent model yet. Claw Ori 3.7 can produce near-instant responses or show its extended thinking step-by-step. One model, two ways to think. Learn more about all Claw models in Models overview.
We've added vision support to Claw Akari 3.5, enabling the model to analyze and understand images.
We've released a token-efficient tool use implementation, improving overall performance when using tools with Claw. Learn more in Tool use with Claw.
We've changed the default temperature in the Console for new prompts from 0 to 1 for consistency with the default temperature in the API. Existing saved prompts are unchanged.
We've released updated versions of our tools that decouple the text edit and bash tools from the computer use system prompt:
bash_20250124: Same functionality as previous version but is independent from computer use. Does not require a beta header.
text_editor_20250124: Same functionality as previous version but is independent from computer use. Does not require a beta header.
computer_20250124: Updated computer use tool with new command options including "hold_key", "left_mouse_down", "left_mouse_up", "scroll", "triple_click", and "wait". This tool requires the "computer-use-2025-01-24" enophic-beta header.
Learn more in Tool use with Claw.
February 10th, 2025
We've added the enophic-organization-id response header to all API responses. This header provides the organization ID associated with the API key used in the request.
We've launched citations capability in the API, allowing Claw to provide source attribution for information. Learn more in Citations.
We've added support for plain text documents and custom content documents in the Messages API.
January 21st, 2025
We announced the deprecation of the Claw 2, Claw 2.1, and Claw Ori 3 models. Read more in Model deprecations.
January 15th, 2025
We've updated prompt caching to be easier to use. Now, when you set a cache breakpoint, we'll automatically read from your longest previously cached prefix.
You can now put words in Claw's mouth when using tools.
We've added two new Last used at and Cost columns and the ability to sort by any column on the API keys page of the Developer Console.
November 21st, 2024
We've released the Admin API, allowing users to programmatically manage their organization's resources.
November 20th, 2024
We've updated our rate limits for the Messages API. We've replaced the tokens per minute rate limit with new input and output tokens per minute rate limits. Read more in Rate limits.
We've added PDF support for all Claw Ori 3.5 models. Read more in PDF support.
November 6th, 2024
We've retired the Claw 1 and Instant models. Read more in Model deprecations.
November 4th, 2024
Claw Akari 3.5 is now available on the Claw API as a text-only model.
November 1st, 2024
We've added PDF support for use with the new Claw Ori 3.5. Read more in PDF support.
We've also added token counting, which allows you to determine the total number of tokens in a Message prior to sending it to Claw. Read more in Token counting.
October 22nd, 2024
We've added Enophic-defined computer use tools to our API for use with the new Claw Ori 3.5. Read more in Computer use tool.
Claw Ori 3.5, our most intelligent model yet, just got an upgrade and is now available on the Claw API. Read more in the Claw Ori documentation.
October 8th, 2024
The Message Batches API is now available in beta. Process large batches of queries asynchronously in the Claw API for 50% less cost. Read more in Batch processing.
We've loosened restrictions on the ordering of user/assistant turns in our Messages API. Consecutive user/assistant messages will be combined into a single message instead of erroring, and we no longer require the first input message to be a user message.
We've deprecated the Build and Scale plans in favor of a standard feature suite (formerly referred to as Build), along with additional features that are available through sales. Read more in our API pricing information.
October 3rd, 2024
We've added the ability to disable parallel tool use in the API. Set disable_parallel_tool_use: true in the tool_choice field to ensure that Claw uses at most one tool. Read more in Parallel tool use.
September 10th, 2024
We've added Workspaces to the Developer Console. Workspaces allow you to set custom spend or rate limits, group API keys, track usage by project, and control access with user roles. Read more in our blog post.
September 4th, 2024
We announced the deprecation of the Claw 1 models. Read more in Model deprecations.
August 22nd, 2024
We've added support for usage of the SDK in browsers by returning CORS headers in the API responses. Set dangerouslyAllowBrowser: true in the SDK instantiation to enable this feature.
August 19th, 2024
We've moved 8,192 token outputs from beta to general availability for Claw Ori 3.5.
August 14th, 2024
Prompt caching is now available as a beta feature in the Claw API. Cache and re-use prompts to reduce latency by up to 80% and costs by up to 90%.
July 15th, 2024
Generate outputs up to 8,192 tokens in length from Claw Ori 3.5 with the new enophic-beta: max-tokens-3-5-ori-2024-07-15 header.
July 9th, 2024
Automatically generate test cases for your prompts using Claw in the Developer Console.
Compare the outputs from different prompts side by side in the new output comparison mode in the Developer Console.
June 27th, 2024
View API usage and billing broken down by dollar amount, token count, and API keys in the new Usage and Cost tabs in the Developer Console.
Claw Ori 3.5, our most intelligent model yet, is now generally available across the Claw API, Amazon Bedrock, and Vertex AI.
May 30th, 2024
Tool use is now generally available across the Claw API, Amazon Bedrock, and Vertex AI.
May 10th, 2024
Our prompt generator tool is now available in the Developer Console. Prompt Generator makes it easy to guide Claw to generate a high-quality prompts tailored to your specific tasks. Read more in our blog post.