feat(cerebras): integrate Cerebras cloud SDK for native completion support

- Added support for the Cerebras cloud SDK, enabling native chat completions. - Introduced class for handling requests to the Cerebras API. - Updated to include as a dependency. - Added tests for the new Cerebras provider, including unit tests and VCR tests for API interactions. - Updated existing files to accommodate the new provider and its configurations.
2026-05-07 10:12:38 +00:00 · 2026-05-06 15:40:14 -07:00
parent d165bcb65f
commit b27ab32546
11 changed files with 2195 additions and 2 deletions
--- a/lib/crewai/pyproject.toml
+++ b/lib/crewai/pyproject.toml
@@ -98,6 +98,9 @@ azure-ai-inference = [
 anthropic = [
    "anthropic~=0.73.0",
 ]
+cerebras = [
+    "cerebras-cloud-sdk~=1.67.0",
+]
 a2a = [
     "a2a-sdk~=0.3.10",
     "httpx-auth~=0.23.1",
--- a/lib/crewai/src/crewai/llm.py
+++ b/lib/crewai/src/crewai/llm.py
@@ -606,6 +606,13 @@ class LLM(BaseLLM):

            return BedrockCompletion

+        if provider == "cerebras":
+            from crewai.llms.providers.cerebras.completion import (
+                CerebrasCompletion,
+            )
+
+            return CerebrasCompletion
+
        # OpenAI-compatible providers
        openai_compatible_providers = {
            "openrouter",
--- a/lib/crewai/src/crewai/llms/constants.py
+++ b/lib/crewai/src/crewai/llms/constants.py
@@ -523,6 +523,20 @@ BedrockModels: TypeAlias = Literal[
    "qwen.qwen3-coder-30b-a3b-v1:0",
    "twelvelabs.pegasus-1-2-v1:0",
 ]
+CerebrasModels: TypeAlias = Literal[
+    "llama3.1-8b",
+    "gpt-oss-120b",
+    "qwen-3-235b-a22b-instruct-2507",
+    "zai-glm-4.7",
+]
+CEREBRAS_MODELS: list[CerebrasModels] = [
+    "llama3.1-8b",
+    "gpt-oss-120b",
+    "qwen-3-235b-a22b-instruct-2507",
+    "zai-glm-4.7",
+]
+
+
 BEDROCK_MODELS: list[BedrockModels] = [
    # Inference profiles (regional) - Claude 4
    "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
--- a/lib/crewai/src/crewai/llms/providers/cerebras/init.py
+++ b/lib/crewai/src/crewai/llms/providers/cerebras/init.py
--- a/lib/crewai/src/crewai/llms/providers/cerebras/completion.py
+++ b/lib/crewai/src/crewai/llms/providers/cerebras/completion.py
--- a/lib/crewai/tests/cassettes/llms/cerebras/test_cerebras_basic_completion.yaml
+++ b/lib/crewai/tests/cassettes/llms/cerebras/test_cerebras_basic_completion.yaml
@@ -0,0 +1,233 @@
+interactions:
+- request:
+    body: ''
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - api.cerebras.ai
+      user-agent:
+      - X-USER-AGENT-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.67.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: GET
+    uri: https://api.cerebras.ai/v1/tcp_warming
+  response:
+    body:
+      string: 'This request is being sent by the Cerebras Cloud SDK to warm up your
+        TCP connection so that your requests will have lower TTFT.
+
+        If you don''t want this, please set `"warmTCPConnection": false` (NodeJS)
+        or `warm_tcp_connection=False` (Python) in the SDK constructor.
+
+
+        For more assistance, contact us at support@cerebras.ai
+
+        '
+    headers:
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      cf-ray:
+      - CF-RAY-XXX
+      content-type:
+      - text/plain; charset=utf-8
+      date:
+      - Wed, 06 May 2026 22:33:47 GMT
+      referrer-policy:
+      - REFERRER-POLICY-XXX
+      server:
+      - cloudflare
+      set-cookie:
+      - SET-COOKIE-XXX
+      strict-transport-security:
+      - STS-XXX
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: ''
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - api.cerebras.ai
+      user-agent:
+      - X-USER-AGENT-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.67.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: GET
+    uri: https://api.cerebras.ai/v1/tcp_warming
+  response:
+    body:
+      string: 'This request is being sent by the Cerebras Cloud SDK to warm up your
+        TCP connection so that your requests will have lower TTFT.
+
+        If you don''t want this, please set `"warmTCPConnection": false` (NodeJS)
+        or `warm_tcp_connection=False` (Python) in the SDK constructor.
+
+
+        For more assistance, contact us at support@cerebras.ai
+
+        '
+    headers:
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      cf-ray:
+      - CF-RAY-XXX
+      content-type:
+      - text/plain; charset=utf-8
+      date:
+      - Wed, 06 May 2026 22:33:47 GMT
+      referrer-policy:
+      - REFERRER-POLICY-XXX
+      server:
+      - cloudflare
+      set-cookie:
+      - SET-COOKIE-XXX
+      strict-transport-security:
+      - STS-XXX
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model":"llama3.1-8b","max_completion_tokens":32,"messages":[{"role":"user","content":"Reply
+      with exactly the word: OK"}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '123'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.cerebras.ai
+      user-agent:
+      - X-USER-AGENT-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.67.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.cerebras.ai/v1/chat/completions
+  response:
+    body:
+      string: '{"id":"chatcmpl-63f7fec0-7ac5-4dec-adca-427a39ca8d77","choices":[{"finish_reason":"stop","index":0,"message":{"content":"OK","role":"assistant"}}],"created":1778106827,"model":"llama3.1-8b","system_fingerprint":"fp_96e7e4453bc38316a23a","object":"chat.completion","usage":{"total_tokens":44,"completion_tokens":2,"completion_tokens_details":{"accepted_prediction_tokens":0,"rejected_prediction_tokens":0,"reasoning_tokens":0},"prompt_tokens":42,"prompt_tokens_details":{"cached_tokens":0}},"time_info":{"created":1778106827.7362924,"queue_time":2.178798466,"prompt_time":0.003727911,"completion_time":0.00089246,"total_time":2.1848058700561523}}'
+    headers:
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      cf-ray:
+      - CF-RAY-XXX
+      content-type:
+      - application/json
+      date:
+      - Wed, 06 May 2026 22:33:49 GMT
+      inference-id:
+      - chatcmpl-63f7fec0-7ac5-4dec-adca-427a39ca8d77
+      referrer-policy:
+      - REFERRER-POLICY-XXX
+      server:
+      - cloudflare
+      strict-transport-security:
+      - STS-XXX
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ratelimit-limit-requests-day:
+      - '14400'
+      x-ratelimit-limit-requests-hour:
+      - '900'
+      x-ratelimit-limit-requests-minute:
+      - '30'
+      x-ratelimit-limit-tokens-day:
+      - '1000000'
+      x-ratelimit-limit-tokens-hour:
+      - '1000000'
+      x-ratelimit-limit-tokens-minute:
+      - '60000'
+      x-ratelimit-remaining-requests-day:
+      - '14399'
+      x-ratelimit-remaining-requests-hour:
+      - '899'
+      x-ratelimit-remaining-requests-minute:
+      - '29'
+      x-ratelimit-remaining-tokens-day:
+      - '999961'
+      x-ratelimit-remaining-tokens-hour:
+      - '999961'
+      x-ratelimit-remaining-tokens-minute:
+      - '59961'
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/lib/crewai/tests/cassettes/llms/cerebras/test_cerebras_streaming_completion.yaml
+++ b/lib/crewai/tests/cassettes/llms/cerebras/test_cerebras_streaming_completion.yaml
@@ -0,0 +1,249 @@
+interactions:
+- request:
+    body: ''
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - api.cerebras.ai
+      user-agent:
+      - X-USER-AGENT-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.67.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: GET
+    uri: https://api.cerebras.ai/v1/tcp_warming
+  response:
+    body:
+      string: 'This request is being sent by the Cerebras Cloud SDK to warm up your
+        TCP connection so that your requests will have lower TTFT.
+
+        If you don''t want this, please set `"warmTCPConnection": false` (NodeJS)
+        or `warm_tcp_connection=False` (Python) in the SDK constructor.
+
+
+        For more assistance, contact us at support@cerebras.ai
+
+        '
+    headers:
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      cf-ray:
+      - CF-RAY-XXX
+      content-type:
+      - text/plain; charset=utf-8
+      date:
+      - Wed, 06 May 2026 22:33:50 GMT
+      referrer-policy:
+      - REFERRER-POLICY-XXX
+      server:
+      - cloudflare
+      set-cookie:
+      - SET-COOKIE-XXX
+      strict-transport-security:
+      - STS-XXX
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: ''
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - api.cerebras.ai
+      user-agent:
+      - X-USER-AGENT-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.67.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: GET
+    uri: https://api.cerebras.ai/v1/tcp_warming
+  response:
+    body:
+      string: 'This request is being sent by the Cerebras Cloud SDK to warm up your
+        TCP connection so that your requests will have lower TTFT.
+
+        If you don''t want this, please set `"warmTCPConnection": false` (NodeJS)
+        or `warm_tcp_connection=False` (Python) in the SDK constructor.
+
+
+        For more assistance, contact us at support@cerebras.ai
+
+        '
+    headers:
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      cf-ray:
+      - CF-RAY-XXX
+      content-type:
+      - text/plain; charset=utf-8
+      date:
+      - Wed, 06 May 2026 22:33:50 GMT
+      referrer-policy:
+      - REFERRER-POLICY-XXX
+      server:
+      - cloudflare
+      set-cookie:
+      - SET-COOKIE-XXX
+      strict-transport-security:
+      - STS-XXX
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model":"llama3.1-8b","max_completion_tokens":32,"messages":[{"role":"user","content":"Count:
+      one, two, three."}],"stream":true,"stream_options":{"include_usage":true}}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '169'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.cerebras.ai
+      user-agent:
+      - X-USER-AGENT-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.67.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.cerebras.ai/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-e4b66146-cac9-459a-9909-ddd5fb56b3fd","choices":[{"delta":{"role":"assistant"},"index":0}],"created":1778106830,"model":"llama3.1-8b","system_fingerprint":"fp_96e7e4453bc38316a23a","object":"chat.completion.chunk"}
+
+
+        data: {"id":"chatcmpl-e4b66146-cac9-459a-9909-ddd5fb56b3fd","choices":[{"delta":{"content":"One"},"index":0}],"created":1778106830,"model":"llama3.1-8b","system_fingerprint":"fp_96e7e4453bc38316a23a","object":"chat.completion.chunk"}
+
+
+        data: {"id":"chatcmpl-e4b66146-cac9-459a-9909-ddd5fb56b3fd","choices":[{"delta":{"content":",
+        two, three. What''s next?"},"index":0}],"created":1778106830,"model":"llama3.1-8b","system_fingerprint":"fp_96e7e4453bc38316a23a","object":"chat.completion.chunk"}
+
+
+        data: {"id":"chatcmpl-e4b66146-cac9-459a-9909-ddd5fb56b3fd","choices":[{"delta":{},"finish_reason":"stop","index":0}],"created":1778106830,"model":"llama3.1-8b","system_fingerprint":"fp_96e7e4453bc38316a23a","object":"chat.completion.chunk","usage":{"total_tokens":54,"completion_tokens":11,"completion_tokens_details":{"accepted_prediction_tokens":0,"rejected_prediction_tokens":0,"reasoning_tokens":0},"prompt_tokens":43,"prompt_tokens_details":{"cached_tokens":0}},"time_info":{"created":1778106830.7255669,"queue_time":0.00023963,"prompt_time":0.002608115,"completion_time":0.00474267,"total_time":0.009609460830688477}}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      cf-ray:
+      - CF-RAY-XXX
+      content-type:
+      - text/event-stream; charset=utf-8
+      date:
+      - Wed, 06 May 2026 22:33:50 GMT
+      inference-id:
+      - chatcmpl-e4b66146-cac9-459a-9909-ddd5fb56b3fd
+      referrer-policy:
+      - REFERRER-POLICY-XXX
+      server:
+      - cloudflare
+      strict-transport-security:
+      - STS-XXX
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ratelimit-limit-requests-day:
+      - '14400'
+      x-ratelimit-limit-requests-hour:
+      - '900'
+      x-ratelimit-limit-requests-minute:
+      - '30'
+      x-ratelimit-limit-tokens-day:
+      - '1000000'
+      x-ratelimit-limit-tokens-hour:
+      - '1000000'
+      x-ratelimit-limit-tokens-minute:
+      - '60000'
+      x-ratelimit-remaining-requests-day:
+      - '14398'
+      x-ratelimit-remaining-requests-hour:
+      - '898'
+      x-ratelimit-remaining-requests-minute:
+      - '29'
+      x-ratelimit-remaining-tokens-day:
+      - '999953'
+      x-ratelimit-remaining-tokens-hour:
+      - '999963'
+      x-ratelimit-remaining-tokens-minute:
+      - '59963'
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/lib/crewai/tests/cassettes/llms/cerebras/test_cerebras_temperature_and_seed_passed_to_sdk.yaml
+++ b/lib/crewai/tests/cassettes/llms/cerebras/test_cerebras_temperature_and_seed_passed_to_sdk.yaml
@@ -0,0 +1,234 @@
+interactions:
+- request:
+    body: ''
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - api.cerebras.ai
+      user-agent:
+      - X-USER-AGENT-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.67.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: GET
+    uri: https://api.cerebras.ai/v1/tcp_warming
+  response:
+    body:
+      string: 'This request is being sent by the Cerebras Cloud SDK to warm up your
+        TCP connection so that your requests will have lower TTFT.
+
+        If you don''t want this, please set `"warmTCPConnection": false` (NodeJS)
+        or `warm_tcp_connection=False` (Python) in the SDK constructor.
+
+
+        For more assistance, contact us at support@cerebras.ai
+
+        '
+    headers:
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      cf-ray:
+      - CF-RAY-XXX
+      content-type:
+      - text/plain; charset=utf-8
+      date:
+      - Wed, 06 May 2026 22:33:51 GMT
+      referrer-policy:
+      - REFERRER-POLICY-XXX
+      server:
+      - cloudflare
+      set-cookie:
+      - SET-COOKIE-XXX
+      strict-transport-security:
+      - STS-XXX
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: ''
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      host:
+      - api.cerebras.ai
+      user-agent:
+      - X-USER-AGENT-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.67.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: GET
+    uri: https://api.cerebras.ai/v1/tcp_warming
+  response:
+    body:
+      string: 'This request is being sent by the Cerebras Cloud SDK to warm up your
+        TCP connection so that your requests will have lower TTFT.
+
+        If you don''t want this, please set `"warmTCPConnection": false` (NodeJS)
+        or `warm_tcp_connection=False` (Python) in the SDK constructor.
+
+
+        For more assistance, contact us at support@cerebras.ai
+
+        '
+    headers:
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      cf-ray:
+      - CF-RAY-XXX
+      content-type:
+      - text/plain; charset=utf-8
+      date:
+      - Wed, 06 May 2026 22:33:51 GMT
+      referrer-policy:
+      - REFERRER-POLICY-XXX
+      server:
+      - cloudflare
+      set-cookie:
+      - SET-COOKIE-XXX
+      strict-transport-security:
+      - STS-XXX
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model":"llama3.1-8b","max_completion_tokens":64,"messages":[{"role":"user","content":"Say
+      hi."}],"seed":7,"temperature":0.0}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '126'
+      content-type:
+      - application/json
+      cookie:
+      - COOKIE-XXX
+      host:
+      - api.cerebras.ai
+      user-agent:
+      - X-USER-AGENT-XXX
+      x-stainless-arch:
+      - X-STAINLESS-ARCH-XXX
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - X-STAINLESS-OS-XXX
+      x-stainless-package-version:
+      - 1.67.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.cerebras.ai/v1/chat/completions
+  response:
+    body:
+      string: '{"id":"chatcmpl-5bf61f2f-c4a5-4122-b921-d8cba7d8ebc0","choices":[{"finish_reason":"stop","index":0,"message":{"content":"Hello.
+        How can I assist you today?","role":"assistant"}}],"created":1778106831,"model":"llama3.1-8b","system_fingerprint":"fp_96e7e4453bc38316a23a","object":"chat.completion","usage":{"total_tokens":48,"completion_tokens":10,"completion_tokens_details":{"accepted_prediction_tokens":0,"rejected_prediction_tokens":0,"reasoning_tokens":0},"prompt_tokens":38,"prompt_tokens_details":{"cached_tokens":0}},"time_info":{"created":1778106831.5465255,"queue_time":7.401e-05,"prompt_time":0.001719314,"completion_time":0.003982367,"total_time":0.0068645477294921875}}'
+    headers:
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      cf-ray:
+      - CF-RAY-XXX
+      content-type:
+      - application/json
+      date:
+      - Wed, 06 May 2026 22:33:51 GMT
+      inference-id:
+      - chatcmpl-5bf61f2f-c4a5-4122-b921-d8cba7d8ebc0
+      referrer-policy:
+      - REFERRER-POLICY-XXX
+      server:
+      - cloudflare
+      strict-transport-security:
+      - STS-XXX
+      x-content-type-options:
+      - X-CONTENT-TYPE-XXX
+      x-ratelimit-limit-requests-day:
+      - '14400'
+      x-ratelimit-limit-requests-hour:
+      - '900'
+      x-ratelimit-limit-requests-minute:
+      - '30'
+      x-ratelimit-limit-tokens-day:
+      - '1000000'
+      x-ratelimit-limit-tokens-hour:
+      - '1000000'
+      x-ratelimit-limit-tokens-minute:
+      - '60000'
+      x-ratelimit-remaining-requests-day:
+      - '14397'
+      x-ratelimit-remaining-requests-hour:
+      - '898'
+      x-ratelimit-remaining-requests-minute:
+      - '28'
+      x-ratelimit-remaining-tokens-day:
+      - '999871'
+      x-ratelimit-remaining-tokens-hour:
+      - '999881'
+      x-ratelimit-remaining-tokens-minute:
+      - '59881'
+      x-request-id:
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/lib/crewai/tests/llms/cerebras/init.py
+++ b/lib/crewai/tests/llms/cerebras/init.py
--- a/lib/crewai/tests/llms/cerebras/test_cerebras_completion.py
+++ b/lib/crewai/tests/llms/cerebras/test_cerebras_completion.py
@@ -0,0 +1,284 @@
+"""Tests for the native Cerebras provider.
+
+Two flavors:
+- Unit tests under the ``Test*`` classes — exercise factory routing, field
+  normalization, env-var resolution, client construction, and the fallback
+  to OpenAI-compatible when the SDK extra is not installed. These run with
+  ``CEREBRAS_API_KEY`` / ``CEREBRAS_BASE_URL`` cleared so each test states
+  the env it depends on.
+- Module-level VCR tests — replay real Cerebras API responses from cassettes.
+  To re-record, set ``CEREBRAS_API_KEY`` and run with
+  ``PYTEST_VCR_RECORD_MODE=new_episodes`` (or delete the target cassette
+  and use the default ``once`` mode).
+"""
+
+from __future__ import annotations
+
+import builtins
+import sys
+from unittest.mock import patch
+
+import pytest
+
+from crewai.llm import LLM
+from crewai.llms.providers.cerebras.completion import CerebrasCompletion
+from crewai.llms.providers.openai_compatible.completion import (
+    OpenAICompatibleCompletion,
+)
+
+
+@pytest.fixture
+def clear_cerebras_env(monkeypatch):
+    monkeypatch.delenv("CEREBRAS_API_KEY", raising=False)
+    monkeypatch.delenv("CEREBRAS_BASE_URL", raising=False)
+
+
+@pytest.mark.usefixtures("clear_cerebras_env")
+class TestCerebrasFactoryRouting:
+    def test_provider_prefix_routes_to_native(self):
+        llm = LLM(model="cerebras/gpt-oss-120b", api_key="sk-test")
+        assert isinstance(llm, CerebrasCompletion)
+        assert llm.llm_type == "cerebras"
+        assert llm.provider == "cerebras"
+        assert llm.is_litellm is False
+
+    def test_explicit_provider_kwarg_routes_to_native(self):
+        llm = LLM(model="gpt-oss-120b", provider="cerebras", api_key="sk-test")
+        assert isinstance(llm, CerebrasCompletion)
+
+    def test_falls_back_to_openai_compat_when_sdk_missing(self, monkeypatch):
+        # Drop any cached imports so the factory re-imports the cerebras module.
+        for mod_name in list(sys.modules):
+            if mod_name.startswith(
+                "crewai.llms.providers.cerebras"
+            ) or mod_name.startswith("cerebras"):
+                monkeypatch.delitem(sys.modules, mod_name, raising=False)
+
+        real_import = builtins.__import__
+
+        def _import_blocker(name, *args, **kwargs):
+            if name.startswith("cerebras"):
+                raise ImportError(f"simulated missing dep: {name}")
+            return real_import(name, *args, **kwargs)
+
+        monkeypatch.setattr(builtins, "__import__", _import_blocker)
+
+        llm = LLM(model="cerebras/gpt-oss-120b", api_key="sk-test")
+        # Without the SDK, factory falls through to the OpenAI-compatible path.
+        assert isinstance(llm, OpenAICompatibleCompletion)
+
+
+@pytest.mark.usefixtures("clear_cerebras_env")
+class TestCerebrasFieldNormalization:
+    def test_default_base_url_left_unset(self):
+        # We deliberately don't pin a default base URL — the SDK has its own.
+        llm = CerebrasCompletion(model="gpt-oss-120b", api_key="sk-test")
+        assert llm.base_url is None
+        assert llm.api == "completions"
+        assert llm.provider == "cerebras"
+
+    def test_env_var_base_url_override(self, monkeypatch):
+        monkeypatch.setenv("CEREBRAS_BASE_URL", "https://custom.cerebras.example/v1")
+        llm = CerebrasCompletion(model="gpt-oss-120b", api_key="sk-test")
+        assert llm.base_url == "https://custom.cerebras.example/v1"
+
+    def test_explicit_base_url_takes_precedence(self, monkeypatch):
+        monkeypatch.setenv("CEREBRAS_BASE_URL", "https://from-env.example/v1")
+        llm = CerebrasCompletion(
+            model="gpt-oss-120b",
+            api_key="sk-test",
+            base_url="https://explicit.example/v1",
+        )
+        assert llm.base_url == "https://explicit.example/v1"
+
+    def test_api_forced_to_completions(self):
+        # Even if a caller tries to set api="responses", the validator clamps it.
+        llm = CerebrasCompletion(
+            model="gpt-oss-120b", api_key="sk-test", api="responses"
+        )
+        assert llm.api == "completions"
+
+
+@pytest.mark.usefixtures("clear_cerebras_env")
+class TestCerebrasApiKeyResolution:
+    def test_env_var_picked_up(self, monkeypatch):
+        monkeypatch.setenv("CEREBRAS_API_KEY", "env-key")
+        llm = CerebrasCompletion(model="gpt-oss-120b")
+        assert llm.api_key == "env-key"
+
+    def test_explicit_api_key_takes_precedence(self, monkeypatch):
+        monkeypatch.setenv("CEREBRAS_API_KEY", "env-key")
+        llm = CerebrasCompletion(model="gpt-oss-120b", api_key="explicit-key")
+        assert llm.api_key == "explicit-key"
+
+    def test_construction_succeeds_without_key(self):
+        # Lazy client init: missing key should not crash construction.
+        llm = CerebrasCompletion(model="gpt-oss-120b")
+        assert llm.api_key is None
+
+    def test_get_client_params_raises_without_key(self):
+        llm = CerebrasCompletion(model="gpt-oss-120b")
+        with pytest.raises(ValueError, match="CEREBRAS_API_KEY"):
+            llm._get_client_params()
+
+
+@pytest.mark.usefixtures("clear_cerebras_env")
+class TestCerebrasClientBuild:
+    def test_sync_client_uses_cerebras_sdk(self, monkeypatch):
+        monkeypatch.setenv("CEREBRAS_API_KEY", "sk-test")
+        llm = CerebrasCompletion(model="gpt-oss-120b")
+        client = llm._get_sync_client()
+        from cerebras.cloud.sdk import Cerebras
+
+        assert isinstance(client, Cerebras)
+
+    def test_async_client_uses_cerebras_sdk(self, monkeypatch):
+        monkeypatch.setenv("CEREBRAS_API_KEY", "sk-test")
+        llm = CerebrasCompletion(model="gpt-oss-120b")
+        client = llm._get_async_client()
+        from cerebras.cloud.sdk import AsyncCerebras
+
+        assert isinstance(client, AsyncCerebras)
+
+    def test_client_params_threaded_through(self, monkeypatch):
+        monkeypatch.setenv("CEREBRAS_API_KEY", "sk-test")
+        llm = CerebrasCompletion(
+            model="gpt-oss-120b",
+            timeout=30.0,
+            max_retries=5,
+            default_headers={"X-Custom": "yes"},
+        )
+        params = llm._get_client_params()
+        assert params["timeout"] == 30.0
+        assert params["max_retries"] == 5
+        assert params["default_headers"] == {"X-Custom": "yes"}
+        assert params["api_key"] == "sk-test"
+        # base_url omitted so the SDK uses its own default.
+        assert "base_url" not in params
+
+    def test_client_params_includes_base_url_when_set(self, monkeypatch):
+        monkeypatch.setenv("CEREBRAS_API_KEY", "sk-test")
+        llm = CerebrasCompletion(
+            model="gpt-oss-120b", base_url="https://override.example/api"
+        )
+        params = llm._get_client_params()
+        assert params["base_url"] == "https://override.example/api"
+
+
+@pytest.mark.usefixtures("clear_cerebras_env")
+class TestCerebrasConfigDict:
+    def test_specific_fields_included_when_set(self):
+        llm = CerebrasCompletion(
+            model="gpt-oss-120b",
+            api_key="sk-test",
+            service_tier="priority",
+            prompt_cache_key="cache-1",
+            clear_thinking=True,
+            reasoning_effort="high",
+        )
+        config = llm.to_config_dict()
+        assert config["service_tier"] == "priority"
+        assert config["prompt_cache_key"] == "cache-1"
+        assert config["clear_thinking"] is True
+        assert config["reasoning_effort"] == "high"
+
+    def test_specific_fields_omitted_when_unset(self):
+        llm = CerebrasCompletion(model="gpt-oss-120b", api_key="sk-test")
+        config = llm.to_config_dict()
+        assert "service_tier" not in config
+        assert "prompt_cache_key" not in config
+        assert "clear_thinking" not in config
+
+
+@pytest.mark.usefixtures("clear_cerebras_env")
+class TestCerebrasCompletionParams:
+    """Verify Cerebras-specific kwargs reach the chat.completions.create call."""
+
+    def test_reasoning_effort_threaded_for_non_o1_models(self):
+        llm = CerebrasCompletion(
+            model="gpt-oss-120b", api_key="sk-test", reasoning_effort="high"
+        )
+        params = llm._prepare_completion_params(messages=[])
+        # Parent gates this on is_o1_model — Cerebras must thread it regardless.
+        assert params["reasoning_effort"] == "high"
+
+    def test_service_tier_threaded(self):
+        llm = CerebrasCompletion(
+            model="llama3.1-8b", api_key="sk-test", service_tier="priority"
+        )
+        params = llm._prepare_completion_params(messages=[])
+        assert params["service_tier"] == "priority"
+
+    def test_prompt_cache_key_threaded(self):
+        llm = CerebrasCompletion(
+            model="llama3.1-8b", api_key="sk-test", prompt_cache_key="run-42"
+        )
+        params = llm._prepare_completion_params(messages=[])
+        assert params["prompt_cache_key"] == "run-42"
+
+    def test_clear_thinking_threaded(self):
+        llm = CerebrasCompletion(
+            model="zai-glm-4.7", api_key="sk-test", clear_thinking=True
+        )
+        params = llm._prepare_completion_params(messages=[])
+        assert params["clear_thinking"] is True
+
+    def test_cerebras_specific_fields_omitted_when_unset(self):
+        llm = CerebrasCompletion(model="llama3.1-8b", api_key="sk-test")
+        params = llm._prepare_completion_params(messages=[])
+        assert "service_tier" not in params
+        assert "prompt_cache_key" not in params
+        assert "clear_thinking" not in params
+        assert "reasoning_effort" not in params
+
+
+@pytest.mark.vcr(filter_headers=["authorization", "x-api-key"])
+def test_cerebras_basic_completion():
+    """End-to-end completion against Cerebras (replays from cassette)."""
+    llm = LLM(model="cerebras/llama3.1-8b", max_completion_tokens=32)
+    assert isinstance(llm, CerebrasCompletion)
+
+    result = llm.call("Reply with exactly the word: OK")
+
+    assert isinstance(result, str)
+    assert len(result) > 0
+
+
+@pytest.mark.vcr(filter_headers=["authorization", "x-api-key"])
+def test_cerebras_streaming_completion():
+    """Streaming completion against Cerebras (replays from cassette)."""
+    llm = LLM(model="cerebras/llama3.1-8b", stream=True, max_completion_tokens=32)
+    assert isinstance(llm, CerebrasCompletion)
+
+    result = llm.call("Count: one, two, three.")
+
+    assert isinstance(result, str)
+    assert len(result) > 0
+
+
+@pytest.mark.vcr(filter_headers=["authorization", "x-api-key"])
+def test_cerebras_temperature_and_seed_passed_to_sdk():
+    """Deterministic-sampling params reach the Cerebras SDK call."""
+    llm = LLM(
+        model="cerebras/llama3.1-8b",
+        temperature=0.0,
+        seed=7,
+        max_completion_tokens=64,
+    )
+    assert isinstance(llm, CerebrasCompletion)
+
+    original_create = llm._client.chat.completions.create
+    captured: dict = {}
+
+    def capture_and_call(**kwargs):
+        captured.update(kwargs)
+        return original_create(**kwargs)
+
+    with patch.object(
+        llm._client.chat.completions, "create", side_effect=capture_and_call
+    ):
+        llm.call("Say hi.")
+
+    assert captured["model"] == "llama3.1-8b"
+    assert captured["temperature"] == 0.0
+    assert captured["seed"] == 7
--- a/uv.lock
+++ b/uv.lock
@@ -13,7 +13,7 @@ resolution-markers = [
 ]

 [options]
-exclude-newer = "2026-04-27T16:00:00Z"
+exclude-newer = "2026-04-28T07:00:00Z"

 [manifest]
 members = [
@@ -789,6 +789,23 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/06/f3/39cf3367b8107baa44f861dc802cbf16263c945b62d8265d36034fc07bea/cachetools-7.0.5-py3-none-any.whl", hash = "sha256:46bc8ebefbe485407621d0a4264b23c080cedd913921bad7ac3ed2f26c183114", size = 13918, upload-time = "2026-03-09T20:51:27.33Z" },
 ]

+[[package]]
+name = "cerebras-cloud-sdk"
+version = "1.67.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+    { name = "distro" },
+    { name = "httpx", extra = ["http2"] },
+    { name = "pydantic" },
+    { name = "sniffio" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/92/12/c201f07582068141e88f9a523ab02fdc97de58f2f7c0df775c6c52b9d8dd/cerebras_cloud_sdk-1.67.0.tar.gz", hash = "sha256:3aed6f86c6c7a83ee9d4cfb08a2acea089cebf2af5b8aed116ef79995a4f4813", size = 131536, upload-time = "2026-01-29T23:31:27.306Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7a/5e/36a364f3d1bab4073454b75e7c91dc7ec6879b960063d1a9c929f1c7ea71/cerebras_cloud_sdk-1.67.0-py3-none-any.whl", hash = "sha256:658b79ca2e9c16f75cc6b4e5d523ee014c9e54a88bd39f88905c28ecb33daae1", size = 97807, upload-time = "2026-01-29T23:31:25.77Z" },
+]
+
 [[package]]
 name = "certifi"
 version = "2026.2.25"
@@ -1330,6 +1347,9 @@ azure-ai-inference = [
 bedrock = [
    { name = "boto3" },
 ]
+cerebras = [
+    { name = "cerebras-cloud-sdk" },
+]
 docling = [
    { name = "docling" },
 ]
@@ -1383,6 +1403,7 @@ requires-dist = [
    { name = "azure-identity", marker = "extra == 'azure-ai-inference'", specifier = ">=1.17.0,<2" },
    { name = "boto3", marker = "extra == 'aws'", specifier = "~=1.42.79" },
    { name = "boto3", marker = "extra == 'bedrock'", specifier = "~=1.42.79" },
+    { name = "cerebras-cloud-sdk", marker = "extra == 'cerebras'", specifier = "~=1.67.0" },
    { name = "chromadb", specifier = "~=1.1.0" },
    { name = "click", specifier = "~=8.1.7" },
    { name = "crewai-cli", editable = "lib/cli" },
@@ -1426,7 +1447,7 @@ requires-dist = [
    { name = "tomli-w", specifier = "~=1.1.0" },
    { name = "voyageai", marker = "extra == 'voyageai'", specifier = "~=0.3.5" },
 ]
-provides-extras = ["a2a", "anthropic", "aws", "azure-ai-inference", "bedrock", "docling", "embeddings", "file-processing", "google-genai", "litellm", "mem0", "openpyxl", "pandas", "qdrant", "qdrant-edge", "tools", "voyageai", "watson"]
+provides-extras = ["a2a", "anthropic", "aws", "azure-ai-inference", "bedrock", "cerebras", "docling", "embeddings", "file-processing", "google-genai", "litellm", "mem0", "openpyxl", "pandas", "qdrant", "qdrant-edge", "tools", "voyageai", "watson"]

 [[package]]
 name = "crewai-cli"