APIs and SDKs

Call Fireworks from custom agents, background jobs, or services with curl, the OpenAI SDK, the Anthropic SDK, or the Fireworks SDK. Send requests to https://api.fireworks.ai/inference and use the same model ID across each supported API.

Compatible APIs

Choose the endpoint your SDK or client already uses:

API	Base URL to configure	Full endpoint	Typical clients
Anthropic Messages	`https://api.fireworks.ai/inference`	`https://api.fireworks.ai/inference/v1/messages`	Anthropic SDK, Claude Code
OpenAI Chat Completions	`https://api.fireworks.ai/inference/v1`	`https://api.fireworks.ai/inference/v1/chat/completions`	OpenAI SDK, Fireworks SDK, most gateways and harnesses
OpenAI Responses	`https://api.fireworks.ai/inference/v1`	`https://api.fireworks.ai/inference/v1/responses`	OpenAI SDK, Codex

Anthropic-style clients add /v1/messages to the base URL themselves, so their base URL stops at /inference. For client setup, see OpenAI compatibility, Anthropic compatibility, or the Responses API.

Call the API

Send your Fireworks key and any model ID:

curl https://api.fireworks.ai/inference/v1/chat/completions \
  -H "Authorization: Bearer $FIREWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-latest",
    "messages": [{"role": "user", "content": "Say pong in one word."}]
  }'

auto works the same way on all three APIs.

Nexus Auto examples for every API and SDK

cURL, OpenAI, Anthropic, and Fireworks SDK examples for Chat Completions, Responses, and Messages, with provider-key headers.

Read the serving model

For a Nexus Auto request, the response model field names the model that served the turn, such as glm-5p3 or claude-opus-5-5, not the Nexus Auto ID you sent. See Check which model served a turn.

Credentials

Credential	How to provide it	When
Fireworks API key (`fw_...`)	`Authorization` bearer token or `X-Fireworks-Api-Key` header	Every request; bills open-model traffic to your Fireworks account
Anthropic	Connect an Anthropic Provider Key if enabled, or send `x-anthropic-api-key`	You want `auto` to use Claude Opus
OpenAI	Connect an OpenAI Provider Key if enabled, or send `x-openai-api-key`	You want `auto` to use GPT Sol
Amazon Bedrock	Amazon Bedrock Provider Key	You want `auto` to use a model you mapped there. Usage bills to your AWS account.

An Anthropic or OpenAI key in a request header applies only to that request. A key connected through Provider Keys is available at the account level, so clients and gateways do not need to send it with every call. With both credentials, auto picks its closed model by API. You can combine an account-level key for one provider with a request header for the other. Fireworks also accepts Anthropic credentials in x-api-key or Authorization: Bearer. One Authorization header cannot carry both the Fireworks and Anthropic keys. If it carries the Anthropic key, send the Fireworks key in X-Fireworks-Api-Key. Prefer x-anthropic-api-key for new integrations. In every SDK, api_key is the Fireworks key. Pass provider keys as extra headers, as shown in Nexus Auto.

Limitations

Accounts with data residency enabled must use a residency-compatible pinned serverless model. Nexus Auto requests are rejected.
Nexus Auto is not available through Microsoft Foundry.
See What happens without a closed-model credential.

Errors

Response	Cause	Fix
`401`	Fireworks key is missing or invalid	Send a valid `fw_...` key with `Authorization: Bearer` or `X-Fireworks-Api-Key`
Request rejected for data residency	The requested route is not residency-compatible	Pin a residency-compatible serverless model
`404` `Model id not found`	Unknown id, or the account cannot use this router	Check the model id and account access
`400` `no_credential`	The closed model you named has no provider key	Connect Provider Keys where available. For Anthropic or OpenAI, you can instead send the provider header.
Upstream provider authentication failure	The provider credential is wrong, revoked, or lacks permission	Check the Anthropic, OpenAI, or Amazon Bedrock credential and its permissions; exact status and message come from that provider

Nexus Auto and deployment routers

auto is the Nexus Auto model ID. Routers load-balance traffic across your own Fireworks deployments.

Get started

Nexus CLI

Model Orchestration

Harness Support

Nexus settings

More

Compatible APIs

Call the API

Nexus Auto examples for every API and SDK

Read the serving model

Credentials

Limitations

Errors

Nexus Auto and deployment routers

See also

​Compatible APIs

​Call the API

Nexus Auto examples for every API and SDK

​Read the serving model

​Credentials

​Limitations

​Errors

​Nexus Auto and deployment routers

​See also

Compatible APIs

Call the API

Read the serving model

Credentials

Limitations

Errors

Nexus Auto and deployment routers

See also