OpenAI gpt-oss-20b API Pricing and Speed
OpenAI gpt-oss-20b API pricing: $0.075 per 1M tokens for input and $0.30 per 1M tokens for output, from the official API price list of Groq. Official rate checked (source); OpenRouter is a separate channel below. Our measured latency and output speed are shown by route and country below. Published OpenRouter: Last checked · Source (data) · Methodology
OpenRouter: Amount worked out from the source page: $0.03 per 1M tokens, in USD · as shown in the United States on 9 Nov 2026 · the page does not say whether tax is included; we do not assume it is excluded · last price change seen on 3 Nov 2026.
Price changed 3 Nov 2026. input $0.018 → $0.03 (+66.7 %); output $0.09 → $0.13 (+44.4 %) per 1M tokens on OpenRouter. Confirmed by a later check on 4 Nov 2026. Briefing: what it does to task costs
Prices USD per 1M tokens, as listed
- $0.075Input per 1M tokens, from Groq Published
- $0.30Output per 1M tokens, from Groq Published
All prices by channel
| Price per 1M tokens | Groq direct | Through OpenRouter | Previous prices by channel |
|---|---|---|---|
| Input | $0.075 Published | $0.03 Published | OpenRouter: |
| Output | $0.30 Published | $0.13 Published | OpenRouter: |
| Cached input · read | UnknownUnknown | $0.03 Published | — |
| Batch · input / output | — | $0.024 / $0.112 Published | — |
Input price from Groq, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$0.075 throughout9 Nov 2026
Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$0.018 → $0.039 Nov 2026
Context window131,072tokens Published
Max output117,964tokens Published
OpenRouter providers who serves this model through OpenRouter, at what price
OpenRouter sends a call without a pinned provider to one of these endpoints, and each endpoint has its own price. Prices are USD per 1M tokens, input / output.
Pinned min: input $0.018 · Darkbloom (darkbloom/fp8); output $0.03 · PrimeIntellect (primeintellect/fp4)
Unpinned range: input $0.018–$0.075, output $0.03–$0.30 across 11 endpoints of 10 providers (listing shows $0.03 / $0.13).
Price moves of 20% or more since the reading of 8 Nov 2026:
- PrimeIntellect (primeintellect/fp4): $0.004 / $0.017 → $0.02 / $0.03 (input +400%, output +76%).
- Lowest-priced endpoint for the workload, PrimeIntellect (primeintellect/fp4): $0.038 → $0.16 per 1,000 tasks (+327%).
Models with the widest provider price spread on OpenRouter
Request fragment that pins Darkbloom (darkbloom/fp8):
{"provider": {"order": ["darkbloom/fp8"], "allow_fallbacks": false}}Request fragment that pins PrimeIntellect (primeintellect/fp4):
{"provider": {"order": ["primeintellect/fp4"], "allow_fallbacks": false}}With fallbacks turned off, OpenRouter does not move the call to another provider. A full endpoint tag pins that endpoint; the provider name alone covers all of its endpoints (OpenRouter provider routing).
All endpoints (11), by input price
| Provider | Endpoint tag | Precision | Input | Output | Context, tokens |
|---|---|---|---|---|---|
| Darkbloom | darkbloom/fp8 | fp8 | $0.018 | $0.09 | 131,072 |
| PrimeIntellect | primeintellect/fp4 | fp4 | $0.02 | $0.03 | 131,072 |
| AkashML | akashml/fp4 | fp4 | $0.02 | $0.10 | 131,072 |
| DekaLLM | dekallm/bf16 | bf16 | $0.029 | $0.14 | 131,072 |
| CoreWeave | coreweave/fp4 | fp4 | $0.03 | $0.13 | 131,072 |
| DeepInfra | deepinfra/bf16 | bf16 | $0.03 | $0.14 | 131,072 |
| Parasail | parasail/fp4 | fp4 | $0.03 | $0.15 | 131,072 |
| SiliconFlow | siliconflow/fp8 | fp8 | $0.04 | $0.18 | 131,072 |
| Amazon Bedrock | amazon-bedrock | Not stated | $0.07 | $0.15 | 131,072 |
| Amazon Bedrock | amazon-bedrock/eu-west-1 | Not stated | $0.07 | $0.15 | 131,072 |
| Groq | groq | Not stated | $0.075 | $0.30 | 131,072 |
Sorted by input price, then output price. Precision is the quantization field of the endpoints list.
Measured by us our own short test request: about 380 tokens in, a short JSON answer out · medians from answers on two dates or more
United States
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Hosted by Groqreasoning: low70 answers on 14 dates · 100 % answered | 337 msrange 0.13–2.06 s · slow 10 %: 748 ms Observed | 701 tokens/srange 335–871 · slowest 10 %: 375 tokens/s | $0.000063range $0.000062–$0.000067 Calculated | 20for 83 visible |
United Kingdom
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Hosted by Groqreasoning: low70 answers on 14 dates · 100 % answered | 321 msrange 0.08–1.71 s · slow 10 %: 643 ms Observed | 776 tokens/srange 629–813 | $0.000063range $0.000061–$0.000067 Calculated | 20for 83 visible |
Germany
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Hosted by Groqreasoning: low70 answers on 14 dates · 100 % answered | 313 msrange 0.09–2.09 s · slow 10 %: 598 ms Observed | 778 tokens/srange 534–1,007 | $0.000063range $0.000061–$0.000068 Calculated | 20for 83 visible |
Canada
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Hosted by Groqreasoning: low70 answers on 14 dates · 100 % answered | 280 msrange 0.09–1.78 s · slow 10 %: 432 ms Observed | 526 tokens/srange 221–800 · slowest 10 %: 304 tokens/s | $0.000063range $0.000061–$0.000068 Calculated | 20for 83 visible |
Australia
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Hosted by Groqreasoning: low70 answers on 14 dates · 100 % answered | 355 msrange 0.08–3.05 s · slow 10 %: 649 ms Observed | 723 tokens/srange 681–866 | $0.000063range $0.000061–$0.000066 Calculated | 20for 83 visible |
- Hidden reasoning tokens are billed as output, at the output price, even though they are not part of the answer.
How the test works and what each number means: methodology. The figures are also in our open data.
How we got this number
- What we read: the published price on openrouter.ai/api/v1/models
- Checked: ; tracked since 16 Oct 2026
- Shown in: the United States
- Checks so far: 25 checks since 16 Oct 2026
- What changed: the price last changed on ; every change is listed under History
- Page updated:
Other measured facts
| Question | Answer | Checked | Status |
|---|---|---|---|
| How much does GPT OSS 20B on Groq cost per 1M input tokens directly from Groq (official API price)? | $0.08 per 1M tokens | Published | |
| How much does GPT OSS 20B on Groq cost per 1M output tokens directly from Groq (official API price)? | $0.30 per 1M tokens | Published | |
| How much does OpenAI gpt-oss-20b cost per 1M cache-read tokens (cache hits) on OpenRouter? | $0.03 per 1M tokens | Published | |
| How much does OpenAI gpt-oss-20b cost per 1M output tokens on OpenRouter? | $0.13 per 1M tokens | Published | |
| What is the context window of OpenAI gpt-oss-20b on OpenRouter, in tokens? | 131,072 tokens | Published | |
| What is the maximum output length of OpenAI gpt-oss-20b on OpenRouter, in tokens? | 117,964 tokens | Published |
History
- — $0.0090 per 1M tokens → $0.03 per 1M tokens (How much does OpenAI gpt-oss-20b cost per 1M cache-read tokens (cache hits) on OpenRouter?) Confirmed by the check on 4 Nov 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — $0.09 per 1M tokens → $0.13 per 1M tokens (How much does OpenAI gpt-oss-20b cost per 1M output tokens on OpenRouter?) Confirmed by the check on 4 Nov 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — $0.02 per 1M tokens → $0.03 per 1M tokens Confirmed by the check on 4 Nov 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — 32,768 tokens → 117,964 tokens (What is the maximum output length of OpenAI gpt-oss-20b on OpenRouter, in tokens?) Confirmed by the check on 4 Nov 2026. What this means for you: The figure you would rely on has moved; check the evidence before relying on the old one.
- — First check: $0.02 per 1M tokens
The source record lists $0.00000003 per token ($0.03 per 1M tokens), fetched on 9 Nov 2026.
The source record, as published
"prompt":"0.00000003"
Briefings on this model each price change recalculated as a task cost
- OpenAI gpt-oss-20b: price rise input $0.018 → $0.030 per 1M tokens (+67 %), output $0.090 → $0.130 per 1M tokens (+44 %)
- DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
- DeepSeek V4.1 Flash 1017: price cut input $0.300 → $0.0060 per 1M tokens (-98 %), output $1.20 → $0.500 per 1M tokens (-58 %)
Record history — 163 records for 7 questions
- Last record
- Shown in
- the United States
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.03 per 1M tokens | Published |
| 8 Nov 2026 | $0.03 per 1M tokens | Published |
| 7 Nov 2026 | $0.03 per 1M tokens | Published |
| 6 Nov 2026 | $0.03 per 1M tokens | Published |
| 5 Nov 2026 | $0.03 per 1M tokens | Published |
| 4 Nov 2026 | $0.03 per 1M tokens | Published |
| 3 Nov 2026 | $0.03 per 1M tokens | Published |
| 2 Nov 2026 | $0.02 per 1M tokens | Published |
| 1 Nov 2026 | $0.02 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.08 per 1M tokens | Published |
| 8 Nov 2026 | $0.08 per 1M tokens | Published |
| 7 Nov 2026 | $0.08 per 1M tokens | Published |
| 6 Nov 2026 | $0.08 per 1M tokens | Published |
| 5 Nov 2026 | $0.08 per 1M tokens | Published |
| 4 Nov 2026 | $0.08 per 1M tokens | Published |
| 3 Nov 2026 | $0.08 per 1M tokens | Published |
| 2 Nov 2026 | $0.08 per 1M tokens | Published |
| 1 Nov 2026 | $0.08 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.30 per 1M tokens | Published |
| 8 Nov 2026 | $0.30 per 1M tokens | Published |
| 7 Nov 2026 | $0.30 per 1M tokens | Published |
| 6 Nov 2026 | $0.30 per 1M tokens | Published |
| 5 Nov 2026 | $0.30 per 1M tokens | Published |
| 4 Nov 2026 | $0.30 per 1M tokens | Published |
| 3 Nov 2026 | $0.30 per 1M tokens | Published |
| 2 Nov 2026 | $0.30 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.03 per 1M tokens | Published |
| 8 Nov 2026 | $0.03 per 1M tokens | Published |
| 7 Nov 2026 | $0.03 per 1M tokens | Published |
| 6 Nov 2026 | $0.03 per 1M tokens | Published |
| 5 Nov 2026 | $0.03 per 1M tokens | Published |
| 4 Nov 2026 | $0.03 per 1M tokens | Published |
| 3 Nov 2026 | $0.03 per 1M tokens | Published |
| 2 Nov 2026 | $0.0090 per 1M tokens | Published |
| 1 Nov 2026 | $0.0090 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.13 per 1M tokens | Published |
| 8 Nov 2026 | $0.13 per 1M tokens | Published |
| 7 Nov 2026 | $0.13 per 1M tokens | Published |
| 6 Nov 2026 | $0.13 per 1M tokens | Published |
| 5 Nov 2026 | $0.13 per 1M tokens | Published |
| 4 Nov 2026 | $0.13 per 1M tokens | Published |
| 3 Nov 2026 | $0.13 per 1M tokens | Published |
| 2 Nov 2026 | $0.09 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 131,072 tokens | Published |
| 8 Nov 2026 | 131,072 tokens | Published |
| 7 Nov 2026 | 131,072 tokens | Published |
| 6 Nov 2026 | 131,072 tokens | Published |
| 5 Nov 2026 | 131,072 tokens | Published |
| 4 Nov 2026 | 131,072 tokens | Published |
| 3 Nov 2026 | 131,072 tokens | Published |
| 2 Nov 2026 | 131,072 tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 117,964 tokens | Published |
| 8 Nov 2026 | 117,964 tokens | Published |
| 7 Nov 2026 | 117,964 tokens | Published |
| 6 Nov 2026 | 117,964 tokens | Published |
| 5 Nov 2026 | 117,964 tokens | Published |
| 4 Nov 2026 | 117,964 tokens | Published |
| 3 Nov 2026 | 117,964 tokens | Published |
| 2 Nov 2026 | 32,768 tokens | Published |
| 1 Nov 2026 | 32,768 tokens | Published |
Showing the latest 60 of 163 records; the full history is in data.json and data.csv.