Fireworks AI

Fireworks AI

meta

Access Fireworks AI models through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

https://api.fireworks.ai/inference/v1
Models
38
Max context
1.0M
Input range
$0.050 - $4.50
Discovery
static

Activity

Managed-cloud usage across this serving provider.

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Fireworks AI models

38 shown
Fireworks AI: DeepSeek V4 Pro 0813 (Fireworks)stable

DeepSeek V4 Pro 0813 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworksAug 12, 20261M context$1.32 input$3.96 output
ChatFunction CallingReasoning
Fireworks AI: Nemotron 3.5 Lightning 30B A3B (Fireworks)stable

Nemotron 3.5 Lightning 30B A3B (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworksAug 11, 2026262.1K context$0.050 input$0.20 output
ChatFunction CallingReasoning
Fireworks AI: Muse Glimmer 30B (Fireworks)stable

Muse Glimmer 30B (Fireworks) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by fireworksAug 10, 2026131.1K context$0.35 input$1.50 output
ChatFunction CallingVision
Fireworks AI: Qwen3.8 Max (Fireworks)stable

Qwen3.8 Max (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworksAug 3, 2026262.1K context$2.00 input$6.00 output
ChatFunction CallingReasoning
Fireworks AI: DeepSeek V4 Flash 0731 (Fireworks)stable

DeepSeek V4 Flash 0731 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworksJul 31, 20261M context$0.14 input$0.28 output
ChatFunction CallingReasoning
Fireworks AI: Kimi K3 (Fireworks)stable

Kimi K3 (Fireworks) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by fireworksJul 27, 20261.0M context$3.00 input$15.00 output
ChatFunction CallingVision
Fireworks AI: Kimi K3 Fast (Fireworks)stable

Kimi K3 Fast (Fireworks) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by fireworksJul 27, 20261.0M context$4.50 input$22.50 output
ChatFunction CallingVision
Fireworks AI: Inkling (Fireworks)stable

Inkling (Fireworks) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by fireworksJul 15, 20261.0M context$1.00 input$4.05 output
ChatFunction CallingVision
Fireworks AI: GLM 5.2 Fast (Fireworks)stable

GLM 5.2 Fast (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworksJun 26, 20261.0M context$2.10 input$6.60 output
ChatFunction CallingReasoning
Fireworks AI: GLM 5.2 (Fireworks)stable

GLM 5.2 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworksJun 16, 20261.0M context$1.40 input$4.40 output
ChatFunction CallingReasoning
Fireworks AI: Kimi K2.7 Code (Fireworks)stable

Kimi K2.7 Code (Fireworks) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by fireworksJun 12, 2026262K context$0.95 input$4.00 output
ChatFunction CallingVision
Fireworks AI: Kimi K2.7 Code Fast (Fireworks)stable

Kimi K2.7 Code Fast (Fireworks) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by fireworksJun 12, 2026262K context$1.90 input$8.00 output
ChatFunction CallingVision
Fireworks AI: MiniMax-M3 (Fireworks)stable

MiniMax-M3 (Fireworks) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by fireworksJun 12, 2026512K context$0.30 input$1.20 output
ChatFunction CallingVision
Fireworks AI: Qwen 3.7 Plus (Fireworks)stable

Qwen 3.7 Plus (Fireworks) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by fireworksJun 12, 2026262.1K context$0.40 input$1.60 output
ChatFunction CallingVision
Fireworks AI: DeepSeek V4 Pro (Fireworks)stable

DeepSeek V4 Pro (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworksApr 24, 20261M context$1.74 input$3.48 output
ChatFunction CallingReasoning
Fireworks AI: Kimi K2.6 (Fireworks)stable

Kimi K2.6 (Fireworks) supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by fireworksApr 17, 2026262K context$0.95 input$4.00 output
ChatFunction CallingVision
Fireworks AI: MiniMax M2.7 (Fireworks)stable

MiniMax M2.7 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworksApr 12, 2026196.6K context$0.30 input$1.20 output
ChatFunction CallingReasoning
Fireworks AI: GPT OSS 120B (Fireworks)stable

GPT OSS 120B (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworksAug 5, 2025131.1K context$0.15 input$0.60 output
ChatFunction CallingReasoning
Fireworks AI: GPT OSS 20B (Fireworks)stable

GPT OSS 20B (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworksAug 5, 2025131.1K context$0.070 input$0.30 output
ChatFunction CallingReasoning
Fireworks AI: DeepSeek V3deprecated

DeepSeek V3 supports Chat, Function Calling workloads through Everstack.

by fireworks131.1K context$1.20 input$1.20 output
ChatFunction Calling
Fireworks AI: DeepSeek V3.1 (Fireworks)stable

DeepSeek V3.1 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks163.8K context$0.56 input$1.68 output
ChatFunction CallingReasoning
Fireworks AI: DeepSeek V3.2 (Fireworks)stable

DeepSeek V3.2 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks160K context$0.56 input$1.68 output
ChatFunction CallingReasoning
Fireworks AI: GLM-4.5 (Fireworks)stable

GLM-4.5 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks131.1K context$0.55 input$2.19 output
ChatFunction CallingReasoning
Fireworks AI: GLM-4.5 Air (Fireworks)stable

GLM-4.5 Air (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks131.1K context$0.22 input$0.88 output
ChatFunction CallingReasoning
Fireworks AI: GLM-4.7 (Fireworks)stable

GLM-4.7 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks198K context$0.60 input$2.20 output
ChatFunction CallingReasoning
Fireworks AI: GLM-5 (Fireworks)stable

GLM-5 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks202.8K context$1.00 input$3.20 output
ChatFunction CallingReasoning
Fireworks AI: GLM-5.1 (Fireworks)stable

GLM-5.1 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks202.8K context$1.40 input$4.40 output
ChatFunction CallingReasoning
Fireworks AI: Kimi K2 Instruct (Fireworks)stable

Kimi K2 Instruct (Fireworks) supports Chat, Function Calling workloads through Everstack.

by fireworks128K context$1.00 input$3.00 output
ChatFunction Calling
Fireworks AI: Kimi K2 Thinking (Fireworks)stable

Kimi K2 Thinking (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks256K context$0.60 input$2.50 output
ChatFunction CallingReasoning
Fireworks AI: Kimi K2.5 (Fireworks)stable

Kimi K2.5 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks256K context$0.60 input$3.00 output
ChatFunction CallingReasoning
Fireworks AI: Llama v3.1 8B Instructdeprecated

Llama v3.1 8B Instruct supports Chat, Function Calling workloads through Everstack.

by fireworks131.1K context$0.20 input$0.20 output
ChatFunction Calling
Fireworks AI: Llama v3.2 90B Vision Instructdeprecated

Llama v3.2 90B Vision Instruct supports Chat, Vision workloads through Everstack.

by fireworks131.1K context$0.95 input$0.95 output
ChatVision
Fireworks AI: Llama v3.3 70B Instructdeprecated

Llama v3.3 70B Instruct supports Chat, Function Calling workloads through Everstack.

by fireworks131.1K context$0.90 input$0.90 output
ChatFunction Calling
Fireworks AI: MiniMax M2.1 (Fireworks)stable

MiniMax M2.1 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks200K context$0.30 input$1.20 output
ChatFunction CallingReasoning
Fireworks AI: MiniMax M2.5 (Fireworks)stable

MiniMax M2.5 (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks196.6K context$0.30 input$1.20 output
ChatFunction CallingReasoning
Fireworks AI: Nomic Embed Text v1.5stable

Nomic Embed Text v1.5 supports Embeddings workloads through Everstack.

by fireworks8.2K context$0.080 input- output
Embeddings
Fireworks AI: Qwen 2.5 72B Instructdeprecated

Qwen 2.5 72B Instruct supports Chat, Function Calling workloads through Everstack.

by fireworks131.1K context$1.20 input$1.20 output
ChatFunction Calling
Fireworks AI: Qwen 3.6 Plus (Fireworks)stable

Qwen 3.6 Plus (Fireworks) supports Chat, Function Calling, Reasoning workloads through Everstack.

by fireworks128K context$0.50 input$3.00 output
ChatFunction CallingReasoning