Skip to content

Fireworks AI API Endpoints

High-performance inference platform with support for custom deployments and fine-tuning.

463 个模型可用fireworks.ai

Fireworks AI is an inference provider. All models listed here can be accessed through Fireworks AI via OpenRouter's unified API.

模型总数
463
最便宜(输出)
Mistral Nemo
最贵
$350000.00
Veo 2
平均价格
$1682.51
每百万输出令牌

所有模型(按评分排序)

模型评分输出$/百万
Claude Fable 596$50.00
Claude Fable 5 (batch)96$25.00
Claude Fable 5.196$50.00
Claude Fable 5.1 (batch)96$25.00
Claude Opus 4.795$25.00
Claude Opus 4.895$25.00
Claude Opus 595$25.00
Claude Opus 5.595$20.00
GPT-5.593$30.00
GPT-5.5 Pro93$180.00
GPT-5.5 Pro (batch)93$90.00
Gemini 3.1 Pro Preview92$12.00
Gemini 3.1 Pro Preview (batch)92$6.00
Gemini 3.1 Pro Preview Custom Tools92$12.00
GPT-5.492$15.00
GPT-5.4 Pro92$180.00
GPT-5.4 Pro (batch)92$90.00
GPT-5.291$14.00
GPT-5.2 Chat91$14.00
GPT-5.2 Pro91$168.00
GPT-5.2 Pro (batch)91$84.00
GPT-5.2-Codex91$14.00
GPT-5.3-Codex91$14.00
Claude Opus 4.690$25.00
GPT-5.4 (batch)89$7.50
GPT-5.5 (batch)89$15.00
GPT-5.6 Luna89$1.20
GPT-5.6 Luna (batch)89$0.600
GPT-5.6 Luna Pro89$1.20
GPT-5.6 Luna Pro (batch)89$0.600
GPT-5.6 Sol89$20.00
GPT-5.6 Sol (batch)89$10.00
GPT-5.6 Sol Pro89$20.00
GPT-5.6 Sol Pro (batch)89$10.00
GPT-5.6 Terra89$12.00
GPT-5.6 Terra (batch)89$6.00
GPT-5.6 Terra Pro89$12.00
GPT-5.6 Terra Pro (batch)89$6.00
Grok 4.2089$2.50
Grok 4.389$2.50
Grok 4.589$6.00
Grok 4.689$6.00
Grok 4.789$6.00
GPT-589$10.00
GPT-5 (batch)89$5.00
GPT-5 Pro89$120.00
GPT-5 Pro (batch)89$60.00
GPT-5.189$10.00
GPT-5.1 (batch)89$5.00
GPT-5.1-Codex89$10.00
GPT-5.1-Codex-Max89$10.00
GPT-5.1-Codex-Mini89$2.00
GPT-5.2 (batch)89$7.00
Grok 4.3 (batch)89$2.00
Gemini 3 Flash Preview88$3.00
Gemini 3 Flash Preview (batch)88$1.50
Grok 4.6 (batch)88$4.80
Grok 4.7 (batch)88$4.80
Grok 4.20 Multi-Agent88$2.50
o387$8.00
o3 (batch)87$4.00
o3 Pro87$80.00
Claude Sonnet 4.685$15.00
Claude Sonnet 585$10.00
Claude Sonnet 5.585$10.00
Claude Opus 4.585$25.00
Claude Opus 4.5 (batch)85$12.50
Claude Opus 4.6 (batch)84$12.50
Claude Opus 4.7 (batch)84$12.50
Claude Opus 4.8 (batch)84$12.50
Gemini 2.5 Pro84$10.00
Gemini 2.5 Pro Preview 06-0584$10.00
DeepSeek V3.283$0.380
Claude Opus 4.1 (batch)83$37.50
Claude Sonnet 4.582$15.00
Claude Opus 4.182$75.00
GPT-6 Astra82$50.00
GPT-6 Astra (batch)82$25.00
GPT-6 Astra Pro82$50.00
GPT-6 Astra Pro (batch)82$25.00
o4 Mini (batch)81$2.20
Gemini 3.8 Flash81$4.13
Gemini 3.8 Flash (batch)81$1.88
R1 052879$2.15
GPT-5.4 Mini79$4.50
GPT-5.4 Mini (batch)79$2.25
GPT-5.4 Nano79$1.25
GPT-5.4 Nano (batch)79$0.625
Gemini 2.5 Flash79$2.50
Gemini 2.5 Flash Lite79$0.400
Gemini 3.5 Flash79$9.00
Gemini 3.5 Flash (batch)79$4.50
Gemini 3.5 Flash Lite79$2.50
Gemini 3.5 Flash Lite (batch)79$1.25
Gemma 2 27B77$0.650
GPT-5 Mini (batch)77$1.00
GPT-5 Nano77$0.400
GPT-5 Nano (batch)77$0.200
Gemma 4 31B76$0.400
Gemma 4 31B (free)76Free
Claude Sonnet 4.5 (batch)75$7.50
Claude Sonnet 4.6 (batch)75$7.50
o3 Mini (batch)74$2.20
GPT-4o (batch)72$5.00
DeepSeek V3 032472$1.14
DeepSeek V3.172$0.950
DeepSeek V3.2 Exp72$0.410
GPT-4o71$10.00
GPT-4o (2024-05-13)71$15.00
GPT-4o (2024-08-06)71$10.00
GPT-4o (2024-11-20)71$10.00
Gemini 3.1 Flash Lite Preview71$1.50
Qwen3.5 397B A17B71$3.60
Llama 4 Maverick70$1.00
Claude Haiku 4.570$5.00
Claude Haiku 4.5 (batch)70$2.50
Claude Haiku 5.570$0.500
Qwen3.5-122B-A10B70$2.08
GLM 5.3 Flash70$0.500
GLM 5.3 Flash (batch)70$0.180
GLM 5.3 FlashX70$1.25
GLM 5.3 FlashX Legal70$1.25
DeepSeek V370$0.890
GPT-4o-mini69$0.600
Qwen3.5-27B69$2.60
GLM 5V Turbo69$4.00
GLM 5.269$6.80
GLM 5.369$1.40
GLM 5.3 (batch)69$2.00
GLM 5.3 Prime69$8.80
Qwen3.5-35B-A3B69$1.00
GLM 568$3.20
GLM 5 Turbo68$4.00
GLM 5.168$4.40
Mistral Large 468$2.10
GLM 4.5V68$1.80
GPT-4.168$8.00
GPT-4.1 (batch)68$4.00
GLM 4.567$2.20
GLM 4.667$2.00
GLM 4.767$2.20
Mistral Large 3 251267$1.50
Llama 3.3 70B Instruct67$0.790
Qwen3.5-9B67$0.250
Mistral Large66$6.00
Mistral Large 240766$6.00
Composer 266$2.50
Composer 2 Fast66$7.50
Qwen3 235B A22B Instruct 250765$0.800
Qwen3 235B A22B Thinking 250765$3.50
MiniMax M164$2.20
GLM 4.5 Air64$0.850
Llama 3.1 70B Instruct64$0.720
MiniMax M2.564$0.950
MiniMax M2.764$0.840
Mixtral 8x22B Instruct63$6.00
GPT-4o-mini (batch)63$0.300
Phi 461$0.140
Llama 4 Scout60$0.300
GPT-460$60.00
GPT-4.1 Mini (batch)59$0.800
GPT-4.1 Nano (batch)59$0.200
Claude Haiku 5.5 (batch)58$0.250
GPT-4 Turbo (batch)57$15.00
Command A51$10.00
Command A+51$1.50
Kimi K2.548$2.50
Kimi K2.648$3.41
GPT-4o-mini (2024-07-18)46$0.600
GPT-4.1 Mini44$1.60
Llama 3.1 8B Instruct41$0.080
Command R (08-2024)41$0.600
Command R+ (08-2024)41$10.00
GPT-5 Mini41$2.00
Aion 3.540$6.00
Aion 3.5 Mini40$1.40
Aion-2.040$1.60
Aion-3.040$6.00
Aion-3.0-Mini40$1.40
ALLaM 2 7B Instruct40Free
ALLaM 34B40Free
Beam 1.0 501B A23B40$1.00
Claude Fable Latest40$50.00
Claude Haiku Latest40$0.500
Claude Opus 5 (batch)40$12.50
Claude Opus 5.5 (batch)40$10.00
Claude Opus Latest40$20.00
Claude Sonnet 5 (batch)40$5.00
Claude Sonnet 5.5 (batch)40$5.00
Claude Sonnet Latest40$10.00
Codestral 250840$0.900
DeepSeek Flash Latest40$0.500
DeepSeek Pro Latest40$8.00
DeepSeek V3.1 Terminus40$1.00
DeepSeek V4 Flash 042340$0.182
DeepSeek V4 Flash 073140$0.300
DeepSeek V4 Flash Latest40$0.300
DeepSeek V4 Flash Vision Exp40$1.32
DeepSeek V4 Pro 042340$1.78
DeepSeek V4 Pro 081340$4.66
DeepSeek V4.1 Flash40$0.567
DeepSeek V4.1 Flash (batch)40$0.336
DeepSeek V4.1 Flash 101740$0.600
Devstral 2 251240$2.00
Dots3-Note Preview (free)40Free
Ember-140$15.00
Extract40Free
Falcon Arabic 7B Instruct40Free
Falcon-H1-Arabic 34B Instruct40Free
Falcon-H1-Arabic 3B Instruct40Free
Falcon-H1-Arabic 7B Instruct40Free
Falcon3 10B Instruct40Free
Falcon3 7B Instruct40Free
Flint (free)40Free
Fugu Max40$6.00
Fugu Ultra40$30.00
Fugu Ultra v240$30.00
Gemini 3.6 Flash40$3.75
Gemini 3.6 Flash (batch)40$1.88
Gemini 3.7 Flash40$3.75
Gemini 3.7 Flash (batch)40$1.88
Gemini 4 Argon40$10.00
Gemini 4 Argon (batch)40$5.00
Gemini Flash Latest40$3.75
Gemini Pro Latest40$10.00
Gemma 3 12B40$0.150
Gemma 3 27B40$0.350
Gemma 3 4B40$0.100
Gemma 4 26B A4B 40$0.300
Gemma 4 26B A4B (free)40Free
Glimpse40$3.00
GLM Flash Latest40$0.092
GLM Latest40$1.40
GPT Astra Latest40$50.00
GPT Audio40$10.00
GPT Audio Mini40$2.40
GPT Chat Latest40$30.00
GPT Luna Latest40$0.500
GPT Mini Latest40$4.50
GPT Sol Latest40$10.00
GPT Terra Latest40$5.00
GPT-3.5 Turbo (older v0613)40$2.00
GPT-3.5 Turbo 16k40$4.00
GPT-6 Luna40$0.500
GPT-6 Luna (batch)40$0.250
GPT-6 Luna Pro40$0.500
GPT-6 Luna Pro (batch)40$0.250
GPT-6 Sol40$10.00
GPT-6 Sol (batch)40$5.00
GPT-6 Sol Pro40$10.00
GPT-6 Sol Pro (batch)40$5.00
GPT-6.1 Sol40$10.00
GPT-6.1 Sol (batch)40$5.00
GPT-6.1 Sol Pro40$10.00
GPT-6.1 Sol Pro (batch)40$5.00
GPT-6.1 Terra40$5.00
GPT-6.1 Terra (batch)40$2.50
GPT-6.1 Terra Pro40$5.00
GPT-6.1 Terra Pro (batch)40$2.50
gpt-oss-120b40$0.091
gpt-oss-120b (batch)40$0.136
gpt-oss-20b40$0.130
gpt-oss-20b (batch)40$0.112
gpt-oss-safeguard-20b40$0.300
Granite 4.2 8B40$0.250
Grok Build 0.140$2.00
Grok Latest40$6.00
Hunyuan A13B Instruct40$0.570
Hy-MT2-1.8B40$0.177
Hy-MT2-30B-A3B40$0.295
Hy-MT2-7B40$0.295
Hy340$0.528
Hy3 preview40$0.600
Hy440$1.25
Hy4 preview40$2.50
Inkling40$4.05
Inkling Small40$1.20
Jev Router40$-1000000.0000
Kimi K2 071140$2.30
Kimi K2 090540$2.50
Kimi K2 Thinking40$2.50
Kimi K2.7 Code40$3.50
Kimi K340$16.00
Kimi K3 (batch)40$11.40
Kimi K3.1 Pro40$10.00
Kimi Latest40$9.34
LFM2.5-2.6B40$0.500
LFM2.5-2.6B (free)40Free
LFM2.5-24B-A2B40$0.700
Ling 3.0 Flash40$0.063
Ling 3.0 Flash VL40$0.180
Ling 3.0 Tiny40$0.045
Ling 3.1 Flash40$0.225
Llama Guard 4 12B40$0.180
LongCat 2.040$1.20
Lyria 3 Clip Preview40Free
Lyria 3 Pro Preview40Free
Mercury 240$0.750
Mercury 2.540$0.150
Mercury 340$0.350
MiMo-V2.540$2.00
MiMo-V2.5-Pro40$1.80
MiMo-V2.6-Flash40$0.280
MiMo-V2.6-Pro40$0.870
MiMo-V2.6-Pro-UltraSpeed40$8.70
MiniMax M340$1.20
MiniMax M3.1 Flash40$0.600
Ministral 3 14B 251240$0.200
Ministral 3 3B 251240$0.100
Ministral 3 8B 251240$0.150
Mistral Medium 3.140$2.00
Mistral Medium 3.540$7.50
Mistral Medium 3.5 (batch)40$3.75
Mistral Nemo40$0.030
Mistral Small 340$0.080
Mistral Small 3.1 24B40$0.555
Mistral Small 3.2 24B40$0.200
Mistral Small 440$0.600
Moondream 3 Preview40$2.50
Moondream 3.140$2.50
Muse Glimmer 30B40$1.20
Muse Spark 1.140$4.25
Muse Spark 1.240$4.25
Muse Spark 1.2 Contributor40$0.200
Muse Spark 1.340$4.25
Muse Spark 1.3 Contributor40$0.200
Muse Spark Open40$4.25
Muse Wonder40$20.00
Nemotron 3 Nano 30B A3B40$0.240
Nemotron 3 Nano Omni (free)40Free
Nemotron 3 Super40$0.400
Nemotron 3 Ultra40$2.40
Nemotron 3 Ultra (free)40Free
Nemotron 3.5 Content Safety40$0.200
Nemotron 3.5 Lightning40$0.200
Nemotron 3.5 Lightning (free)40Free
Nemotron 3.5 Super VL40$0.500
Nemotron 3.5 Super VL (free)40Free
North Mini Code (free)40Free
Nova 2 Lite40$2.50
Nova Lite 1.040$0.240
Nova Micro 1.040$0.140
Nova Premier 1.040$12.50
Nova Pro 1.040$3.20
Palmyra X540$6.00
Pareto 26.1040$3.20
Pareto 26.940$7.50
Pareto Latest40$3.20
Particle-140$0.500
Perceptron Mk140$1.50
Perceptron Mk1.540$1.50
Qwen-Plus40$0.780
Qwen2.5 72B Instruct40$0.400
Qwen2.5 Coder 32B Instruct40$1.00
Qwen2.5 VL 72B Instruct40$1.00
Qwen3 14B40$0.240
Qwen3 30B A3B40$0.500
Qwen3 30B A3B Instruct 250740$0.300
Qwen3 32B40$0.280
Qwen3 Coder 30B A3B Instruct40$0.600
Qwen3 Coder 480B A35B40$1.00
Qwen3 Coder Flash40$0.975
Qwen3 Coder Next40$0.800
Qwen3 Next 80B A3B Instruct40$1.10
Qwen3 VL 235B A22B Instruct40$1.90
Qwen3 VL 30B A3B Instruct40$0.600
Qwen3 VL 30B A3B Thinking40$1.00
Qwen3 VL 8B Instruct40$0.750
Qwen3.5 Plus 2026-02-1540$1.56
Qwen3.5 Plus 2026-04-2040$1.80
Qwen3.5-Flash40$0.260
Qwen3.6 27B40$2.70
Qwen3.6 35B A3B40$0.900
Qwen3.6 Flash40$1.13
Qwen3.6 Plus40$1.95
Qwen3.7 Flash40$0.130
Qwen3.7 Max40$4.42
Qwen3.7 Plus40$1.28
Qwen3.7 Plus (batch)40$0.920
Qwen3.8 2.4T A95B40$6.00
Qwen3.8 27B40$1.88
Qwen3.8 Flash40$0.470
Qwen3.8 Max (0902)40$6.00
Qwen3.8 Max Prime40$12.00
Qwen3.8 Omni Flash40$0.470
Reka Edge40$0.100
Reka Flash 340$0.200
ricursiveAI/Ripple-65B-Preview40$0.600
Saba40$0.600
Sakana Namazu40$4.00
Schematron V2 Small40$0.230
Schematron V2 Turbo40$0.150
Seed 1.640$2.00
Seed 1.6 Flash40$0.300
Seed 2.1 Turbo40$2.50
Seed-2.0-Code40$3.00
Seed-2.0-Lite40$2.00
Seed-2.0-Mini40$0.400
Solar Mini 440$0.200
Solar Pro 440$0.600
Sonar40$1.00
Sonar Deep Research40$8.00
Sonar Pro40$15.00
Sonar Pro Search40$15.00
Sonar Reasoning Pro40$8.00
Step 3.5 Flash40$0.300
Step 3.7 Flash40$1.15
Step 5 Preview40$2.70
Summarize40Free
Switchyard40$-1000000.0000
Ternary Bonsai 2 27B40$0.500
Ternary Bonsai 2 9B40$0.130
UI-TARS 7B 40$0.200
Voxtral Small 24B 250740$0.300
Xing4.0 29B A4B (free)40Free
Qwen2.5 7B Instruct38$0.200
Command R7B (12-2024)36$0.150
SWE-1.534Free
ALLaM 7B Instruct (preview)33Free
Falcon Mamba 7B Instruct33Free
ALLaM 1 13B Instruct30$1.80
GPT-4.1 Nano29$0.400
Llama 3.2 3B Instruct29$0.335
autofixer-0124Free
Gemini 3.1 Flash Lite24$1.50
Gemini 3.1 Flash Lite (batch)24$0.750
GLM 4.6V22$0.900
GLM 4.7 Flash21$0.400
Crouton Alpha20Free
Mellum18Free
Mistral Medium 315$2.00
Llama 3.2 1B Instruct11$0.201
Adobe Firefly 3--Free
DALL-E 3--$40000.00
FLUX.1 Pro--$50000.00
Gemini Omni 1.1 Flash--$9.00
Gemini Omni 1.2 Flash--$9.00
GPT-5 Image--$10.00
GPT-5 Image Mini--$2.00
GPT-5.4 Image 2--$15.00
Ideogram 2.0--$80000.00
Imagen 3--$40000.00
Kling 1.6--$70000.00
Leonardo Phoenix--Free
LTX-Video 2--Free
Luma Dream Machine--Free
Midjourney v6.1--Free
MiniMax Video-01--Free
Nano Banana (Gemini 2.5 Flash Image)--$2.50
Nano Banana 2 (Gemini 3.1 Flash Image Preview)--$3.00
Nano Banana 2 (Gemini 3.1 Flash Image)--$3.00
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)--$1.50
Nano Banana 2.1--$7.50
Nano Banana Pro (Gemini 3 Pro Image Preview)--$12.00
Nano Banana Pro (Gemini 3 Pro Image)--$12.00
Pika 2.0--Free
Recraft V3--$40000.00
Runway Gen-3 Alpha--Free
Sora--Free
Stable Diffusion 3.5--$35000.00
Stable Video Diffusion--Free
Veo 2--$350000.00
Wan 2.1 T2V--Free

其他API端点

Frequently Asked Questions

Fireworks AI currently offers 463 AI models accessible via API. This includes various sizes and specializations to fit different use cases and budgets.

Pricing varies by model. See our pricing table above sorted by cost - the cheapest option is shown at the top. Some models may have free tiers available.

Use our provider comparison tool to see how Fireworks AI's pricing stacks up against competitors like OpenAI, Anthropic, and Google across similar model tiers.

Fireworks AI API Endpoints - AI Models, Pricing & Capabilities | LM Market Cap