Providers

Fireworks

Verified

A speed-focused inference cloud for open models, with strong function-calling and structured-output support.

Start building View requests Official status

Models on Fireworks

Open in catalog

19 of 19

DeepSeek V4 Flash 0731Chatdeepseek-v4-flash-07311M contextWeights Routeprimary$0.22 / $0.66per M input / output

DeepSeek V4 Pro 0813Chatdeepseek-v4-pro-08131M contextRouteprimary$1.32 / $3.96per M input / output

GLM 5.2Chatglm-5.2Released June 20261M contextWeights Routeprimary$1.40 / $4.40per M input / output

GLM 5.2 FastChatglm-5.2-fast1M contextRouteprimary$2.10 / $6.60per M input / output

GLM 5.3Chatglm-5.3Released Aug 18, 20261M contextRoutefallback$1.40 / $4.40per M input / output

GLM 5.3 FlashChatglm-5.3-flashReleased Aug 26, 20261M contextRoutefallback$0.15 / $0.50per M input / output

GPT-OSS 120BChatgpt-oss-120bReleased Aug 5, 2025131K contextWeights Routeprimary$0.35 / $0.75per M input / output

InklingChatinklingReleased Jul 15, 20261M contextRouteprimary$1.00 / $4.05per M input / output

Kimi K2.6Chatkimi-k2.6262K contextRouteprimary$0.95 / $4.00per M input / output

Kimi K2.7 CodeChatkimi-k2.7-codeReleased Jun 12, 2026262K contextRouteprimary$0.95 / $4.00per M input / output

Kimi K3Chatkimi-k3Released Jul 16, 20261M contextRouteprimary$3.00 / $15.00per M input / output

Kimi K3 FastChatkimi-k3-fast1M contextRouteprimary$4.50 / $22.50per M input / output

MiniMax M3Chatminimax-m3Released May 31, 2026512K contextRouteprimary$0.30 / $1.20per M input / output

Muse Glimmer 30BChatmuse-glimmer-30bReleased August 2026131K contextRouteprimary$0.35 / $1.50per M input / output

Nemotron 3 UltraChatnemotron-3-ultraReleased Jun 4, 2026262K contextRouteprimary$0.90 / $2.40per M input / output

Nemotron 3.5 LightningChatnemotron-3.5-lightning262K contextRouteprimary$0.08 / $0.20per M input / output

Qwen 3.7 PlusChatqwen-3.7-plus262K contextRouteprimary$0.50 / $3.00per M input / output

Qwen 3.8 2.4T A95BChatqwen-3.8-2.4t262K contextRouteprimary$2.00 / $6.00per M input / output

Qwen 3.8 MaxChatqwen-3.8-maxReleased Aug 3, 2026262K contextRoutefallback$2.00 / $6.00per M input / output

Performance

Response latency estimates

Time to first token

Generation speed · tok/s

Request success

Text-model timing and speed, plus API request success. Daily latency percentiles are estimates.

Direct routingCall Fireworks explicitly

fireworks· routing

# pin every request to Fireworks
curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash-0731",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "routing": { "providers": { "only": ["fireworks"] } }
  }'