AI pricing · November 2026
Fireworks AI API pricing
| Provider | Cached in | Context | ||||
|---|---|---|---|---|---|---|
| OpenAI GPT OSS 120B serverless standard mode; batch 50% off | Fireworks AIopen model | $0.150 | $0.600 | $0.015 | — | $2.70 |
| DeepSeek V4.1 Flash serverless standard mode; batch 50% off | Fireworks AIopen model | $0.300 | $1.20 | $0.006 | — | $5.40 |
| GLM 5.3 serverless standard mode; batch 50% off | Fireworks AIopen model | $1.40 | $4.40 | $0.260 | — | $22.80 |
| Qwen 3.8 Max serverless standard mode; batch 50% off | Fireworks AIopen model | $2.00 | $6.00 | $0.250 | — | $32.00 |
| Kimi K3 serverless standard mode; batch 50% off | Fireworks AIopen model | $3.00 | $15.00 | $0.300 | — | $60.00 |
Cached input and batch discounts
| Model | Input $/1M | Cached input $/1M | Cache saving | Batch |
|---|---|---|---|---|
| OpenAI GPT OSS 120B | $0.15 | $0.015 | 90% off | 50% off |
| DeepSeek V4.1 Flash | $0.30 | $0.006 | 98% off | 50% off |
| Kimi K3 | $3 | $0.30 | 90% off | 50% off |
| GLM 5.3 | $1.40 | $0.26 | 81% off | 50% off |
| Qwen 3.8 Max | $2 | $0.25 | 88% off | 50% off |
What a typical workload costs
An app that sends 1,000 requests a day, each with a 2,000-token prompt and a 500-token answer, uses 60M input and 15M output tokens in 30 days. If 1,500 of those prompt tokens are the same system prompt and context every time, prompt caching bills 45M of them at the cached rate (cache writes and storage not included). Batch is the same traffic sent as asynchronous batch jobs.
| Model | Per month | With caching | With batch |
|---|---|---|---|
| OpenAI GPT OSS 120B | $18.00 | $11.93 | $9.00 |
| DeepSeek V4.1 Flash | $36.00 | $22.77 | $18.00 |
| Kimi K3 | $405 | $284 | $203 |
| GLM 5.3 | $150 | $98.70 | $75.00 |
| Qwen 3.8 Max | $210 | $131 | $105 |
Closest-priced models from other providers
Matched on a 3:1 mix of input to output tokens. Open models are compared with every provider.
| Fireworks AI model | In / out $/1M | Closest elsewhere |
|---|---|---|
| OpenAI GPT OSS 120B | $0.15 / $0.60 | Mistral Small 4 (Mistral) $0.15 / $0.60 · GPT-OSS 120B (Groq) $0.15 / $0.60 |
| DeepSeek V4.1 Flash | $0.30 / $1.20 | DeepSeek V4.1 Flash (DeepSeek) $0.30 / $1.20 · Gemini 3.1 Flash-Lite (Google) $0.25 / $1.50 |
| Kimi K3 | $3 / $15 | Claude Sonnet 4.6 (Anthropic) $3 / $15 · GPT-5.3 Codex (OpenAI) $1.75 / $14 |
| GLM 5.3 | $1.40 / $4.40 | GLM-5.3 (Together AI) $1.40 / $4.40 · Claude Haiku 4.5 (Anthropic) $1 / $5 |
| Qwen 3.8 Max | $2 / $6 | Grok 4.7 (xAI) $2 / $6 · Gemini 2.5 Pro (Google) $1.25 / $10 |
Source: Fireworks AI pricing, checked 2026-11-02. To price a real prompt, paste it into the token counter.
FAQ
How much does the Fireworks AI API cost?+
Fireworks AI charges per token. On 2026-11-02 its official pricing page listed, per 1M tokens: OpenAI GPT OSS 120B $0.15 input / $0.60 output, DeepSeek V4.1 Flash $0.30 input / $1.20 output, Kimi K3 $3 input / $15 output, GLM 5.3 $1.40 input / $4.40 output and Qwen 3.8 Max $2 input / $6 output.
What is the cheapest Fireworks AI model?+
OpenAI GPT OSS 120B: $0.15 per 1M input tokens and $0.60 per 1M output tokens. For the example workload on this page (30,000 requests a month) that is about $18.00 a month, against $405 on Kimi K3, the most expensive Fireworks AI model here.
Does Fireworks AI have prompt caching or cheaper cached input?+
Yes. Cached input tokens cost $0.015 on OpenAI GPT OSS 120B (90% less than regular input), $0.006 on DeepSeek V4.1 Flash (98% less than regular input), $0.30 on Kimi K3 (90% less than regular input) and $0.26 on GLM 5.3 (81% less than regular input).
Does Fireworks AI offer a batch discount?+
Yes: 50% off for asynchronous batch requests on all 5 models here. Batch requests are processed in the background instead of answered right away, so they suit evals, backfills and bulk summaries rather than chat.
How does OpenAI GPT OSS 120B compare on price with other AI APIs?+
At $0.15 input / $0.60 output per 1M tokens, the closest-priced models from other providers are Mistral Small 4 (Mistral, $0.15 / $0.60) and GPT-OSS 120B (Groq, $0.15 / $0.60). Price per token isn't the whole bill: compare quality on your own prompts, and how many tokens each model uses for the same task.
How current are these prices?+
They were copied from Fireworks AI's official pricing page on 2026-11-02, and the month in this page's title is that check date. Prices change often, so confirm on the official page before you commit to a budget.
Other providers
Claude API pricing · OpenAI API pricing · Gemini API pricing · Grok API pricing · Mistral API pricing · DeepSeek API pricing · Groq API pricing · Together AI API pricing · All AI model prices compared