OpenRouter vs Fireworks AI. Compare a fixed OpenRouter DeepInfra backend with Fireworks Standard hosting, not OpenAI direct API pricing.
USD token-only estimates using each offering’s published default tier. 1M tokens are an aggregate workload, not a single request. Cache savings, batch discounts, long-context surcharges, tools, taxes and negotiated rates are excluded. Tokenizers and capabilities may differ; lower price does not establish equivalent quality.
OpenRouter · OpenAI: gpt-oss-120b · OpenRouter / deepinfra/bf16 is 72.4% cheaper for this workload. Absolute difference: $0.543.
| Metric | OpenAI: gpt-oss-120b · OpenRouter / deepinfra/bf16OpenRouter | OpenAI GPT OSS 120BFireworks AI |
|---|---|---|
| Input / 1M tokens | $0.037 | $0.15 |
| Output / 1M tokens | $0.17 | $0.60 |
| Cached input / 1M | Not published | $0.015 |
| Context window | 131,072 | Not published |
| Maximum output | 117,964 | Not published |
| 1M input + 1M output | $0.207 | $0.75 |
| Default pricing basis | standard | standard |
| Last verified (UTC) | 2026-09-05T10:40:32.086Z | 2026-09-05T17:44:18.028Z |
Each calculator uses the same default-tier assumption described above.
OpenRouter route quote for API model openai/gpt-oss-120b, fixed backend deepinfra/bf16 (bf16). Not the upstream developer's direct API price or an OpenRouter-wide minimum. Text-token estimate only; pin this backend and disable fallbacks to match this quote. Taxes, credit-purchase fees and optional tools are excluded.
Official pricing sourceLast verified:
All tiers and model details →Fireworks AI Standard global serverless token rates, not the model developer's direct API price. Priority, Fast, US-only serving, dedicated hosting and optional tools are excluded. Model identifier is the official Fireworks catalog slug.
Official pricing sourceLast verified:
All tiers and model details →