Skip to main content

Embed v3 vs GPT OSS 120B (Fireworks): API Cost Comparison

Compare the API pricing, context windows, features, and real-world cost projections for Embed v3 (Cohere) and GPT OSS 120B (Fireworks) (Fireworks AI). Use the interactive calculator below to compute your exact monthly cost based on your token usage and request volume.

Prices verified Mar 10, 2026

Interactive Cost Calculator

CohereEmbed v3Fireworks AIGPT OSS 120B (Fireworks)

Fills in typical token counts for a workload type

Tokens in each prompt sent to the model

Tokens generated in each response

Total API calls per month

Showing costs for 2 models. Cheapest: Embed v3 at $1.50/month.

Cheapest: Embed v3 at $1.50/mo — save 66.7% vs GPT OSS 120B (Fireworks)
Alert
BestEmbed v3
Cohere$1.50$0.000150$1.00$0.5066.7%Alerts coming soon
GPT OSS 120B (Fireworks)
Fireworks AI$4.50$0.000450$1.50$3.00Alerts coming soon

Monthly Cost Comparison

Price Comparison at a Glance

All prices are in USD per 1 million tokens ($/M tokens). Lower is cheaper.

Pricing TypeEmbed v3GPT OSS 120B (Fireworks)Cheaper
Input (standard)$0.10/M$0.15/MEmbed v3
Output$0.10/M$0.60/MEmbed v3
Cached inputN/A$0.08/M
Batch inputN/A$0.08/M
Batch outputN/A$0.30/M

Prices last verified: 2026-03-06 – 2026-03-10

Cost Breakdown by Usage Volume

Estimated monthly costs at different request volumes, assuming 1,000 input tokens and 500 output tokens per request. Adjust in the calculator above for your specific use case.

VolumeEmbed v3MonthlyGPT OSS 120B (Fireworks)MonthlyEmbed v3Per requestGPT OSS 120B (Fireworks)Per request
1K requests/mo$0.15$0.45$0.000150$0.000450
10K requests/mo$1.50$4.50$0.000150$0.000450
100K requests/mo$15.00$45.00$0.000150$0.000450
1M requests/mo$150.00$450.00$0.000150$0.000450

Green values indicate the lower-cost option at each volume tier. Cost per request is calculated at 1,000 input + 500 output tokens using standard (non-batch, non-cached) pricing.

Price History

Input price per 1M tokens

When to Choose Embed v3

by Cohere

  • RAG / Semantic search

Input / 1M tokens

$0.10/M

Output / 1M tokens

$0.10/M

Context window

512

Tier

budget

When to Choose GPT OSS 120B (Fireworks)

by Fireworks AI

  • Code generation
  • Document summarization
  • RAG / Semantic search

Input / 1M tokens

$0.15/M

Output / 1M tokens

$0.60/M

Context window

131,072

Tier

mid

Key Differences Beyond Price

Cost is only one factor in choosing an AI model. Context window size, rate limits, supported features, and latency all affect whether a model fits your use case.

CapabilityEmbed v3GPT OSS 120B (Fireworks)
Context window512 tokens131,072 tokens
Max output tokens1,024 tokens16,384 tokens
Performance tierBudgetMid
Vision / image inputNoNo
Function callingNoYes
JSON modeNoYes
Prompt cachingNoYes
Batch API (50% discount)NoYes
Extended reasoningNoNo
Fine-tuningNoNo

Embed v3 notes

Embedding model only. Output tokens represent embedding dimensions, not text. Multilingual variant also available.

GPT OSS 120B (Fireworks) notes

Fireworks serverless pricing. Cached input 50% discount. Batch at 50% of serverless.

Frequently Asked Questions

Is Embed v3 cheaper than GPT OSS 120B (Fireworks)?

At standard usage (1,000 input tokens, 500 output tokens, 100,000 requests/month), Embed v3 costs $15.00/month versus $45.00/month for GPT OSS 120B (Fireworks) — a 67% saving. Your actual savings will vary based on your token profile; output-heavy workloads amplify differences in output pricing.

Which model has a larger context window, Embed v3 or GPT OSS 120B (Fireworks)?

GPT OSS 120B (Fireworks) has a larger context window at 131,072 tokens, compared to 512 tokens for Embed v3. A larger context window is important for processing long documents, multi-turn conversations, or large codebases without truncation.

Do Embed v3 and GPT OSS 120B (Fireworks) support the Batch API?

GPT OSS 120B (Fireworks) supports the Batch API (50% discount for async processing), while Embed v3 does not. If your workload tolerates up to 24-hour latency, routing to GPT OSS 120B (Fireworks) with batch pricing could significantly cut costs versus Embed v3's standard rate.

Which model offers better prompt caching?

GPT OSS 120B (Fireworks) supports prompt caching at $0.08/M for cached input, while Embed v3 does not offer prompt caching. For RAG applications or chatbots with large, repeated context, GPT OSS 120B (Fireworks)'s caching capability can substantially reduce effective costs.

What are the best use cases for Embed v3 vs GPT OSS 120B (Fireworks)?

Both models are well-suited for RAG / Semantic search. Embed v3 is particularly strong for overlapping tasks. GPT OSS 120B (Fireworks) is favored for Code generation, Document summarization. At the same quality level, the lower-cost model is usually preferable; use this page's calculator to compare total monthly spend at your volume.

What is the cost per request for Embed v3 vs GPT OSS 120B (Fireworks)?

At 1,000 input tokens and 500 output tokens per request — a typical conversational workload — Embed v3 costs $0.000150 per request and GPT OSS 120B (Fireworks) costs $0.000450 per request. At 100,000 requests/month, that translates to $15.00 and $45.00 respectively. Use the interactive calculator to adjust these parameters for your actual workload.

Embed v3 vs GPT OSS 120B (Fireworks): Summary

When comparing Embed v3 and GPT OSS 120B (Fireworks) for API cost, the right choice depends on your workload's token profile, required features, and tolerance for latency. Embed v3 offers lower total cost at standard usage volumes (1,000 input + 500 output tokens per request at 100,000 requests/month) at $15.00/month, compared to $45.00/month for GPT OSS 120B (Fireworks).

Both models are priced in USD per million tokens, the standard unit across all major AI API providers. Embed v3 charges $0.10/M for input tokens and $0.10/M for output tokens. GPT OSS 120B (Fireworks) charges $0.15/M input and $0.60/M output. If your workload is output-heavy (more tokens generated than consumed as input), the model with the lower output price compounds cost savings significantly at scale.

Prompt caching is supported by GPT OSS 120B (Fireworks) but not Embed v3. For workloads with large, repeated system prompts or document context — such as RAG pipelines or multi-turn conversations with a fixed knowledge base — prompt caching can reduce effective input costs by 60–90%, which may change the cost ranking between these two models at your specific usage pattern.

Context window capacity differs between the two: GPT OSS 120B (Fireworks) supports up to 131,072 tokens in a single request, versus 512 tokens for Embed v3. A larger context window is essential for document summarization, large codebase analysis, and multi-document retrieval-augmented generation (RAG) applications.

Use the interactive calculator at the top of this page to enter your actual token usage and monthly request volume for a precise cost comparison tailored to your workload. Adjust for batch API discounts and prompt caching to find the most cost-effective option for your specific deployment.

Explore other model comparisons from the same providers or performance tiers.

Related Provider Pages

View complete pricing tables and model lineups for the providers behind these models.

Relevant Use Cases

See cost recommendations for workloads where Embed v3 or GPT OSS 120B (Fireworks) is recommended.