Skip to content

Fireworks AI

Fast serving and fine-tuning for open models.

Fireworks AI serves open-weight models with an OpenAI-compatible API, plus LoRA fine-tuning and function calling on its own serving stack. FreeRouter crawls its serverless catalog only — models listed but not deployed answer 404 on a plain key, so they stay out. Fireworks addresses models by resource path (accounts/fireworks/models/glm-5p3), so the site shows both the canonical id and the gateway’s own id.

Open-weight focus Serverless catalog Resource-path model ids
Status
Crawl failing
Models in catalog
20
Text / multimodal
18
Publishes pricing for
No prices published
Largest context window
1M tokens
Model id style
Resource paths with `p` for version dots (`accounts/fireworks/models/glm-5p3`), aligned to canonical ids (`z-ai/glm-5.3`).
Billing
Pay per token.
Catalog last checked
Website
fireworks.ai
Documentation
Developer docs
Catalog

20 models on Fireworks AI

The 20 most widely available are shown; the rest are searchable in the full model list. "Id on this gateway" is what Fireworks AI calls the model — where it differs from the canonical id, that difference is what a router has to translate.

Search all 20 models on Fireworks AI
ModelVendorTypeId on this gatewayAvailable onContextInput / Mtok
DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 DeepSeek Multimodal accounts/fireworks/models/deepseek-v4p1-flash-1017 BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel 1M $0.050–$0.300
GLM 5.3 z-ai/glm-5.3 Z.ai Multimodal accounts/fireworks/models/glm-5p3 BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel 1M $0.078–$1.40
GLM 5.3 Flash z-ai/glm-5.3-flash Z.ai Multimodal accounts/fireworks/models/glm-5p3-flash BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel 1M $0.029–$0.150
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash DeepSeek Multimodal accounts/fireworks/models/deepseek-v4p1-flash BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestyTogetherVercel 1M $0.045–$0.300
Muse Spark Open meta-llama/muse-spark-open Meta Multimodal accounts/fireworks/models/muse-spark-open BasetenCheaper InferenceCloudflareConcentrateExperiential LabsFireworksNanoGPTOpenRouterRampRequestyVercel 1M $1.06–$1.25
Kimi K3 moonshotai/kimi-k3 Moonshot AI Multimodal accounts/fireworks/models/kimi-k3 BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRequestySailTogetherVercel 1M $0.149–$3.00
Qwen3.8 Max qwen/qwen3.8-max Qwen Multimodal accounts/fireworks/models/qwen3p8-max Cheaper InferenceCloudflareConcentrateExperiential LabsFireworksLLM GatewayNanoGPTOrcaRouterRampRequesty 1M $1.41–$2.00
MiniMax M3.1 Flash minimax/minimax-m3.1-flash MiniMax Multimodal accounts/fireworks/models/minimax-m3p1-flash CloudflareFireworksNanoGPTOpenRouterOrcaRouterRequestyTogetherVercel 1M $0.150–$0.300
OpenAI GPT 120B openai/gpt-oss-120b OpenAI Text accounts/fireworks/models/gpt-oss-120b BasetenCloudflareFireworksNanoGPTOpenRouterRequestyTogetherVercel 131.1K $0.030–$0.150
Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b Qwen Text accounts/fireworks/models/qwen3p8-2p4t-a95b Cheaper InferenceCloudflareExperiential LabsFireworksLLM GatewayOpenRouterRequestyTogether 1M $1.70–$2.50
MiniMax M3 minimax/minimax-m3 MiniMax Multimodal accounts/fireworks/models/minimax-m3 CloudflareFireworksNanoGPTOpenRouterOrcaRouterRequestyVercel 1M $0.230–$0.300
Ember 1 ember-1 — Multimodal accounts/fireworks/models/ember-1 Cheaper InferenceCloudflareFireworksNanoGPTOpenRouterVercel 1M $2.55–$3.00
Inkling inkling Thinking Machines Text accounts/fireworks/models/inkling Cheaper InferenceConcentrateExperiential LabsFireworks 1M $0.650–$1.10
Qwen3 Embedding 8B qwen/qwen3-embedding-8b Qwen Embedding accounts/fireworks/models/qwen3-embedding-8b Cheaper InferenceCloudflareFireworksLLM Gateway 41K $0.010–$0.012
Kimi K3 Fast moonshotai/kimi-k3-fast Moonshot AI Multimodal accounts/fireworks/routers/kimi-k3-fast FireworksMorphVercel 1M $4.50–$6.00
GLM 5.3 Fast z-ai/glm-5.3-fast Z.ai Multimodal accounts/fireworks/routers/glm-5p3-fast BasetenFireworksVercel 1M $2.10
nemotron-3-ultra-nvfp4 nvidia/nemotron-3-ultra-nvfp4 NVIDIA Text accounts/fireworks/models/nemotron-3-ultra-nvfp4 FireworksRequesty 262.1K $0.600
nemotron-lightning-3.5-30b-a3b nvidia/nemotron-lightning-3.5-30b-a3b NVIDIA Text accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b FireworksRequesty 262.1K $0.050
qwen3-reranker-8b qwen/qwen3-reranker-8b Qwen Rerank accounts/fireworks/models/qwen3-reranker-8b Fireworks 41K —
rune rune — Text accounts/fireworks/models/rune Fireworks 262.1K —
By model type

What Fireworks AI carries

A gateway with 2,000 models is not necessarily a gateway with 2,000 chat models.

Multimodal 12 Text 6 Embedding 1 Rerank 1
Not exclusive

18 of these models are on other gateways too

Anything in this list can be served from somewhere other than Fireworks AI without changing the model id your application sends.

ModelVendorAvailable onContextInput / MtokSpread
DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 DeepSeek BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel 1M $0.050–$0.300 6x
GLM 5.3 z-ai/glm-5.3 Z.ai BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel 1M $0.078–$1.40 17.95x
GLM 5.3 Flash z-ai/glm-5.3-flash Z.ai BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel 1M $0.029–$0.150 5.26x
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash DeepSeek BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestyTogetherVercel 1M $0.045–$0.300 6.67x
Muse Spark Open meta-llama/muse-spark-open Meta BasetenCheaper InferenceCloudflareConcentrateExperiential LabsFireworksNanoGPTOpenRouterRampRequestyVercel 1M $1.06–$1.25 1.18x
Kimi K3 moonshotai/kimi-k3 Moonshot AI BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRequestySailTogetherVercel 1M $0.149–$3.00 20.07x
Qwen3.8 Max qwen/qwen3.8-max Qwen Cheaper InferenceCloudflareConcentrateExperiential LabsFireworksLLM GatewayNanoGPTOrcaRouterRampRequesty 1M $1.41–$2.00 1.42x
MiniMax M3.1 Flash minimax/minimax-m3.1-flash MiniMax CloudflareFireworksNanoGPTOpenRouterOrcaRouterRequestyTogetherVercel 1M $0.150–$0.300 2x
OpenAI GPT 120B openai/gpt-oss-120b OpenAI BasetenCloudflareFireworksNanoGPTOpenRouterRequestyTogetherVercel 131.1K $0.030–$0.150 5x
Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b Qwen Cheaper InferenceCloudflareExperiential LabsFireworksLLM GatewayOpenRouterRequestyTogether 1M $1.70–$2.50 1.47x
MiniMax M3 minimax/minimax-m3 MiniMax CloudflareFireworksNanoGPTOpenRouterOrcaRouterRequestyVercel 1M $0.230–$0.300 1.30x
Ember 1 ember-1 — Cheaper InferenceCloudflareFireworksNanoGPTOpenRouterVercel 1M $2.55–$3.00 1.18x
Inkling inkling Thinking Machines Cheaper InferenceConcentrateExperiential LabsFireworks 1M $0.650–$1.10 1.69x
Qwen3 Embedding 8B qwen/qwen3-embedding-8b Qwen Cheaper InferenceCloudflareFireworksLLM Gateway 41K $0.010–$0.012 1.18x
Kimi K3 Fast moonshotai/kimi-k3-fast Moonshot AI FireworksMorphVercel 1M $4.50–$6.00 1.33x
GLM 5.3 Fast z-ai/glm-5.3-fast Z.ai BasetenFireworksVercel 1M $2.10 —
nemotron-3-ultra-nvfp4 nvidia/nemotron-3-ultra-nvfp4 NVIDIA FireworksRequesty 262.1K $0.600 —
nemotron-lightning-3.5-30b-a3b nvidia/nemotron-lightning-3.5-30b-a3b NVIDIA FireworksRequesty 262.1K $0.050 —