OpenAI gpt-oss-120b API Pricing and Speed
OpenAI gpt-oss-120b API pricing: $0.15 per 1M tokens for input and $0.60 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: $0.15 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.
Quality on your task: not measured by Measured Lab yet. On our data, gpt-oss-120b on the Groq route fits 5 of 6 common tasks by published prices, context window and terms, with calculated monthly costs.
What can I use it for?
Six common tasks cost a month at list prices
- Calculated Answer customer messages: $2.93 for 5,000 customer messages a month
- Unknown Pull data from invoices and documents with strict JSON and page images: not confirmed, reads text only, per the OpenRouter listing
- Calculated Summarize documents and meetings: $1.40 for 1,000 documents or meetings a month
- Calculated Translate content: $2.07 for 3,000 pages a month
- Calculated Chat assistant on your website: $29.93 for 10,000 conversations a month
- Calculated Write and review code with tool calls: $8.51 for 500 coding tasks a month
What our data confirms
- Published Strict JSON output, in Groq documentation, read 17 Oct 2026
- Published Calls your tools, in Groq documentation, read 17 Oct 2026
- Published Reads text only; OpenRouter listing, 9 Nov 2026
- Published Weights on Hugging Face: openai/gpt-oss-120b, as linked by the OpenRouter listing
Example to try
“Draft a reply to this refund request from our returns policy, and hand it to a person if the order is over $500.” Run it on your own data before you choose.
What we measured
- Observed Speed on a short test request: first token 0.4 s, 524 tokens/s (median of 120 test requests on 23 dates, short request)
- Observed Hidden reasoning: 51 tokens on that request, billed as output
Before you choose
- Unknown Training on your data: terms not in our data
- Unknown Where requests are processed: Unknown
Prices USD per 1M tokens, as listed
- $0.15Input per 1M tokens, from Groq Published
- $0.60Output per 1M tokens, from Groq Published
All prices by channel
| Price per 1M tokens | Groq direct | Through OpenRouter | Previous prices by channel |
|---|---|---|---|
| Input | $0.15 Published | $0.15 Published | — |
| Output | $0.60 Published | $0.60 Published | — |
| Cached input · read | UnknownUnknown | $0.075 Published | — |
| Batch · input / output | — | $0.0296 / $0.136 Published | — |
Input price from Groq, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$0.15 throughout9 Nov 2026
Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$0.15 → $0.15 (5 changes)9 Nov 2026
Context window131,072tokens Published
Max output65,536tokens 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 $0.03 · Near AI (near-ai/fp4); output $0.083 · PrimeIntellect (primeintellect/fp4)
Unpinned range: input $0.03–$0.35, output $0.083–$0.95 across 26 endpoints of 22 providers (listing shows $0.10 / $0.50).
Price moves of 20% or more since the reading of 8 Nov 2026:
- Listing price $0.026 / $0.096 → $0.10 / $0.50 (input +285%, output +421%).
- PrimeIntellect (primeintellect/fp4): $0.027 / $0.10 → $0.039 / $0.083 (input +44%, output −17%).
- Lowest-priced endpoint for the workload: Near AI (near-ai/fp4) at $0.29 per 1,000 tasks, before PrimeIntellect (primeintellect/fp4) at $0.25.
Observed unpinned cost: 135 short requests sent without a pinned provider on 26 Oct 2026 – 9 Nov 2026 (15 dates), in each routing mode. Charged is the sum of the OpenRouter generation receipts for these requests; the listing price column is the price of the same input and output tokens at the listing price of that date.
| Routing mode | Requests | Dates | Served by | Charged | Listing price for the same tokens | Charged / listing | Lowest-priced endpoint answered |
|---|---|---|---|---|---|---|---|
| Default (no provider field) | 45 | 26 Oct 2026 – 9 Nov 2026 (15 dates) | 11 of 45 Crusoe (crusoe/bf16), 8 of 45 Near AI (near-ai/fp4), 5 of 45 Sail Research (sail-research/fp4), 4 of 45 AkashML (akashml/fp4), 4 of 45 DeepInfra (deepinfra/bf16), 3 of 45 CoreWeave (coreweave/fp4), 3 of 45 DekaLLM (dekallm/bf16), 3 of 45 DigitalOcean (digitalocean), 1 of 45 BaseTen (baseten/fp4/us), 1 of 45 Groq (groq), 1 of 45 Mancer 2 (mancer/fp8), 1 of 45 Venice (venice/int4) | $0.00049 | $0.0012 | 0.39× | 5 of 45 |
:floor | 45 | 26 Oct 2026 – 9 Nov 2026 (15 dates) | 32 of 45 Near AI (near-ai/fp4), 12 of 45 PrimeIntellect (primeintellect/fp4), 1 of 45 Venice (venice/int4) | $0.00025 | $0.0012 | 0.20× | 33 of 45 |
:nitro | 45 | 26 Oct 2026 – 9 Nov 2026 (15 dates) | 45 of 45 Cerebras (cerebras/fp16) | $0.0023 | $0.0012 | 1.85× | 0 of 45 |
Routing modes as documented by OpenRouter (OpenRouter provider routing, read 25 Oct 2026): the default request has no provider field; :floor and :nitro are suffixes of the model name. Served by names the endpoint that answered, by the provider name and endpoint tag of the receipt. Each request asks for one short line with an answer cap of 32 tokens. The counts are for these requests on these dates only.
Models with the widest provider price spread on OpenRouter
Request fragment that pins Near AI (near-ai/fp4):
{"provider": {"order": ["near-ai/fp4"], "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 (26), by input price
| Provider | Endpoint tag | Precision | Input | Output | Context, tokens | Status code |
|---|---|---|---|---|---|---|
| Near AI | near-ai/fp4 | fp4 | $0.03 | $0.15 | 131,072 | 0 |
| Venice | venice/int4 | int4 | $0.03 | $0.15 | 128,000 | 0 |
| CoreWeave | coreweave/fp4 | fp4 | $0.03 | $0.17 | 131,072 | 0 |
| DekaLLM | dekallm/bf16 | bf16 | $0.03 | $0.18 | 131,072 | 0 |
| AkashML | akashml/fp4 | fp4 | $0.03 | $0.187 | 131,072 | 0 |
| DeepInfra | deepinfra/bf16 | bf16 | $0.037 | $0.17 | 131,072 | 0 |
| PrimeIntellect | primeintellect/fp4 | fp4 | $0.039 | $0.083 | 131,072 | 0 |
| Crusoe | crusoe/bf16 | bf16 | $0.05 | $0.25 | 131,072 | 0 |
| Mancer 2 | mancer/fp8 | fp8 | $0.055 | $0.25 | 131,072 | 0 |
| Sail Research | sail-research/fp4 | fp4 | $0.06 | $0.40 | 131,072 | 0 |
| DigitalOcean | digitalocean | Not stated | $0.06 | $0.42 | 128,000 | 0 |
google-vertex/global | Not stated | $0.09 | $0.36 | 131,072 | -5 | |
| BaseTen | baseten/fp4 | fp4 | $0.10 | $0.50 | 128,072 | 0 |
| BaseTen | baseten/fp4/us | fp4 | $0.10 | $0.50 | 128,072 | 0 |
| Parasail | parasail/fp4 | fp4 | $0.10 | $0.75 | 131,072 | 0 |
| SambaNova | sambanova | Not stated | $0.14 | $0.95 | 131,072 | 0 |
| Amazon Bedrock | amazon-bedrock | Not stated | $0.15 | $0.60 | 131,072 | -5 |
| Amazon Bedrock | amazon-bedrock/eu-west-1 | Not stated | $0.15 | $0.60 | 131,072 | -5 |
| Groq | groq | Not stated | $0.15 | $0.60 | 131,072 | -5 |
| Nebius | nebius/fp4 | fp4 | $0.15 | $0.60 | 131,072 | 0 |
| Phala | phala | Not stated | $0.15 | $0.60 | 131,072 | 0 |
| SiliconFlow | siliconflow/fp8 | fp8 | $0.15 | $0.60 | 131,072 | 0 |
| Together | together | Not stated | $0.15 | $0.60 | 131,072 | 0 |
| Parasail | parasail/fast | fp4 | $0.15 | $0.75 | 131,072 | 0 |
| DeepInfra | deepinfra/fp8 | fp8 | $0.20 | $0.95 | 131,072 | -2 |
| Cerebras | cerebras/fp16 | fp16 | $0.35 | $0.75 | 131,072 | 0 |
Sorted by input price, then output price. Precision is the quantization field of the endpoints list. Status code is the status field of the endpoints list, as read.
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 Cerebrasreasoning: low115 answers on 23 dates · 100 % answered | 271 msrange 0.13–1.57 s · slow 10 %: 570 ms Observed | UnknownUnknownanswer arrived in one piece | $0.000254range $0.000229–$0.000585 Calculated | 56for 89 visible |
| Hosted by Groqreasoning: low120 answers on 23 dates · 100 % answered | 425 msrange 0.23–1.15 s · slow 10 %: 767 ms Observed | 524 tokens/srange 234–801 · slowest 10 %: 501 tokens/s | $0.000144range $0.000131–$0.000329 Calculated | 51for 83 visible |
| OpenRouter → DeepInfrareasoning: low110 answers on 23 dates · 96 % answered | 3.37 srange 0.49–22.89 s · slow 10 %: 11.80 s Observed | 40.5 tokens/srange 11.6–142 · slowest 10 %: 19.6 tokens/s | $0.000147range $0.000126–$0.000387 Calculated | 58for 81 visible |
| OpenRouter → SambaNovareasoning: low115 answers on 23 dates · 100 % answered | 1.06 srange 0.55–43.82 s · slow 10 %: 3.55 s Observed | 114 tokens/srange 58.7–709 | $0.000149range $0.000138–$0.00038 Calculated | 61for 84 visible |
| OpenRouter → Togetherreasoning: low111 answers on 23 dates · 96 % answered | 750 msrange 0.32–10.72 s · slow 10 %: 2.50 s Observed | 133 tokens/srange 24.1–702 · slowest 10 %: 79.4 tokens/s | $0.000145range $0.000132–$0.000347 Calculated | 51for 84 visible |
United Kingdom
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Hosted by Cerebrasreasoning: low110 answers on 22 dates · 100 % answered | 310 msrange 0.20–5.42 s · slow 10 %: 613 ms Observed | 835 tokens/srange 65.5–858 | $0.000253range $0.000229–$0.00063 Calculated | 56for 88 visible |
| Hosted by Groqreasoning: low105 answers on 21 dates · 100 % answered | 410 msrange 0.14–1.02 s · slow 10 %: 806 ms Observed | 525 tokens/srange 451–546 · slowest 10 %: 508 tokens/s | $0.000143range $0.00013–$0.000294 Calculated | 51for 83 visible |
| OpenRouter → DeepInfrareasoning: low100 answers on 21 dates · 95 % answered | 4.03 srange 0.83–28.04 s · slow 10 %: 9.31 s Observed | 48.2 tokens/srange 9.3–110 · slowest 10 %: 19.9 tokens/s | $0.000148range $0.000126–$0.000417 Calculated | 59for 81 visible |
| OpenRouter → SambaNovareasoning: low101 answers on 21 dates · 96 % answered | 1.03 srange 0.49–12.16 s · slow 10 %: 3.02 s Observed | 756 tokens/srange 553–878 | $0.000149range $0.00014–$0.000369 Calculated | 61for 84 visible |
| OpenRouter → Togetherreasoning: low105 answers on 21 dates · 100 % answered | 926 msrange 0.32–8.23 s · slow 10 %: 2.73 s Observed | 122 tokens/srange 40.7–306 · slowest 10 %: 72.9 tokens/s | $0.000145range $0.00013–$0.00033 Calculated | 51for 85 visible |
Germany
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Hosted by Cerebrasreasoning: low110 answers on 22 dates · 100 % answered | 315 msrange 0.21–26.04 s · slow 10 %: 571 ms Observed | 655 tokens/srange 512–839 | $0.000253range $0.000227–$0.00063 Calculated | 56for 88 visible |
| Hosted by Groqreasoning: low105 answers on 21 dates · 100 % answered | 448 msrange 0.15–1.80 s · slow 10 %: 781 ms Observed | 526 tokens/srange 237–556 · slowest 10 %: 511 tokens/s | $0.000144range $0.000131–$0.000366 Calculated | 51for 85 visible |
| OpenRouter → DeepInfrareasoning: low94 answers on 20 dates · 90 % answered | 2.75 srange 0.86–25.26 s · slow 10 %: 8.93 s Observed | 43.6 tokens/srange 8.6–79.5 · slowest 10 %: 19.8 tokens/s | $0.000146range $0.000125–$0.000386 Calculated | 56for 81 visible |
| OpenRouter → SambaNovareasoning: low105 answers on 21 dates · 100 % answered | 1.16 srange 0.49–35.91 s · slow 10 %: 7.15 s Observed | 712 tokens/srange 22.3–890 | $0.000149range $0.000138–$0.000356 Calculated | 61for 84 visible |
| OpenRouter → Togetherreasoning: low103 answers on 21 dates · 98 % answered | 806 msrange 0.38–4.76 s · slow 10 %: 2.27 s Observed | 140 tokens/srange 42.2–270 · slowest 10 %: 83.8 tokens/s | $0.000144range $0.00013–$0.000348 Calculated | 51for 83 visible |
Canada
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Hosted by Cerebrasreasoning: low110 answers on 22 dates · 100 % answered | 253 msrange 0.13–2.95 s · slow 10 %: 435 ms Observed | 485 tokens/srange 144–827 | $0.000253range $0.000229–$0.00055 Calculated | 56for 88 visible |
| Hosted by Groqreasoning: low105 answers on 21 dates · 100 % answered | 411 msrange 0.17–1.22 s · slow 10 %: 795 ms Observed | 523 tokens/srange 151–761 · slowest 10 %: 324 tokens/s | $0.000144range $0.00013–$0.000329 Calculated | 51for 84 visible |
| OpenRouter → DeepInfrareasoning: low101 answers on 21 dates · 96 % answered | 2.57 srange 0.84–15.21 s · slow 10 %: 10.26 s Observed | 44.9 tokens/srange 15.6–802 · slowest 10 %: 23.3 tokens/s | $0.000146range $0.000128–$0.000374 Calculated | 57for 82 visible |
| OpenRouter → SambaNovareasoning: low105 answers on 21 dates · 100 % answered | 1.03 srange 0.54–18.75 s · slow 10 %: 4.21 s Observed | 402 tokens/srange 100–800 | $0.000151range $0.000139–$0.000376 Calculated | 61for 84 visible |
| OpenRouter → Togetherreasoning: low105 answers on 21 dates · 100 % answered | 791 msrange 0.34–5.95 s · slow 10 %: 2.73 s Observed | 147 tokens/srange 30.2–733 · slowest 10 %: 85.5 tokens/s | $0.000144range $0.00013–$0.000404 Calculated | 51for 83 visible |
Australia
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Hosted by Cerebrasreasoning: low110 answers on 22 dates · 100 % answered | 444 msrange 0.31–2.10 s · slow 10 %: 733 ms Observed | 668 tokens/srange 412–698 | $0.000253range $0.000229–$0.000804 Calculated | 55for 88 visible |
| Hosted by Groqreasoning: low105 answers on 21 dates · 100 % answered | 444 msrange 0.12–5.14 s · slow 10 %: 834 ms Observed | 526 tokens/srange 498–535 · slowest 10 %: 516 tokens/s | $0.000144range $0.000131–$0.000329 Calculated | 51for 84 visible |
| OpenRouter → DeepInfrareasoning: low97 answers on 21 dates · 92 % answered | 2.85 srange 0.56–23.05 s · slow 10 %: 9.85 s Observed | 45.2 tokens/srange 9.3–147 · slowest 10 %: 22.6 tokens/s | $0.000145range $0.000127–$0.000312 Calculated | 55for 81 visible |
| OpenRouter → SambaNovareasoning: low105 answers on 21 dates · 100 % answered | 1.64 srange 1.06–8.57 s · slow 10 %: 4.43 s Observed | 478 tokens/srange 18.8–840 | $0.000149range $0.000139–$0.000398 Calculated | 61for 84 visible |
| OpenRouter → Togetherreasoning: low105 answers on 21 dates · 100 % answered | 1.02 srange 0.51–6.61 s · slow 10 %: 2.82 s Observed | 142 tokens/srange 40.6–343 · slowest 10 %: 86.4 tokens/s | $0.000144range $0.00013–$0.00037 Calculated | 51for 85 visible |
- Hidden reasoning tokens are billed as output, at the output price, even though they are not part of the answer.
- Through OpenRouter, the request goes to the named provider; the price and speed can differ from the direct API.
How the test works and what each number means: methodology. The figures are also in our open data.
Quality signals public test results, each with its source and date
| Signal | Result | Source |
|---|---|---|
| Instruction followingIFEval, 50 prompts · run by Groq · reasoning: low | 88 % Observedof 50 prompts with every instruction followed | Our run of a fixed IFEval subset, checked by code88 % on 22 Oct 2026 · 92 % on 17 Oct 2026 · instruction level 91 % |
Figures the provider publishes (7)
| Benchmark | Provider's figure | Where the provider says it |
|---|---|---|
| SWE-bench Verified | 62.4 Stated by the provider | Results table in gpt-oss-120b & gpt-oss-20b Model Card (OpenAI, August 5, 2025)read 17 Oct 2026 |
| GPQA Diamondno tools | 80.1 Stated by the provider | Results table in gpt-oss-120b & gpt-oss-20b Model Card (OpenAI, August 5, 2025)read 17 Oct 2026 |
| AIME 2025no tools | 92.5 Stated by the provider | Results table in gpt-oss-120b & gpt-oss-20b Model Card (OpenAI, August 5, 2025)read 17 Oct 2026 |
| AIME 2025with tools | 97.9 Stated by the provider | Results table in gpt-oss-120b & gpt-oss-20b Model Card (OpenAI, August 5, 2025)read 17 Oct 2026 |
| Humanity's Last Examno tools | 14.9 Stated by the provider | Results table in gpt-oss-120b & gpt-oss-20b Model Card (OpenAI, August 5, 2025)read 17 Oct 2026 |
| MMLU | 90.0 Stated by the provider | Results table in gpt-oss-120b & gpt-oss-20b Model Card (OpenAI, August 5, 2025)read 17 Oct 2026 |
| τ-bench (Tau-Bench Retail) | 67.8 Stated by the provider | Results table in gpt-oss-120b & gpt-oss-20b Model Card (OpenAI, August 5, 2025)read 17 Oct 2026 |
- Your own task: quality on it is not measured here. These are public test sets; a short trial on a few of your own examples is the check that fits your work.
- Other public leaderboards, without figures copied here: human preference votes on open-ended answers: Arena (LMArena) text leaderboard; long tasks in coding, data analysis and research: LiveBench.
What each signal covers and how our run is scored: methodology.
What typical tasks cost with this model
| Task | At Groq's price ($0.15 / $0.60) | Through OpenRouter ($0.15 / $0.60) |
|---|---|---|
| 1,000 chat replies | $0.33 | $0.33 |
| Summarizing 100 documents | $0.09 | $0.09 |
| A day of coding assistant use | $0.28 | $0.28 |
Calculated Prices per 1M tokens (input / output) in brackets; token counts and what is not included: our assumptions and the same tasks on other models.
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 listed price moved between checks since 16 Oct 2026; see the record history
- Page updated:
Other measured facts
| Question | Answer | Checked | Status |
|---|---|---|---|
| How much does GPT OSS 120B on Groq cost per 1M input tokens directly from Groq (official API price)? | $0.15 per 1M tokens | Published | |
| How much does GPT OSS 120B on Groq cost per 1M output tokens directly from Groq (official API price)? | $0.60 per 1M tokens | Published | |
| How much does OpenAI gpt-oss-120b cost per 1M cache-read tokens (cache hits) on OpenRouter? | $0.08 per 1M tokens | Published | |
| How much does OpenAI gpt-oss-120b cost per 1M output tokens on OpenRouter? | $0.60 per 1M tokens | Published | |
| What is the context window of OpenAI gpt-oss-120b on OpenRouter, in tokens? | 131,072 tokens | Published | |
| What is the maximum output length of OpenAI gpt-oss-120b on OpenRouter, in tokens? | 65,536 tokens | Published |
History
The listed price moved between the 25 checks since 16 Oct 2026; every reading is in the record history below.
- — First check: $0.15 per 1M tokens
- Short-lived or unconfirmed moves are not shown as changes.
The source record lists $0.00000015 per token ($0.15 per 1M tokens), fetched on 9 Nov 2026.
The source record, as published
"prompt":"0.00000015"
Latest briefings each price change recalculated as a task cost
- 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 %)
- MoonshotAI Kimi K2.5: price rise input $0.500 → $0.532 per 1M tokens (+6 %), output $2.50 → $3.33 per 1M tokens (+33 %)
Record history — 163 records for 7 questions
- Last record
- Shown in
- the United States
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.15 per 1M tokens | Published |
| 8 Nov 2026 | $0.01 per 1M tokens | Published |
| 7 Nov 2026 | $0.01 per 1M tokens | Published |
| 6 Nov 2026 | $0.03 per 1M tokens | Published |
| 5 Nov 2026 | $0.01 per 1M tokens | Published |
| 4 Nov 2026 | $0.15 per 1M tokens | Published |
| 3 Nov 2026 | $0.15 per 1M tokens | Published |
| 2 Nov 2026 | $0.15 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.15 per 1M tokens | Published |
| 8 Nov 2026 | $0.15 per 1M tokens | Published |
| 7 Nov 2026 | $0.15 per 1M tokens | Published |
| 6 Nov 2026 | $0.15 per 1M tokens | Published |
| 5 Nov 2026 | $0.15 per 1M tokens | Published |
| 4 Nov 2026 | $0.15 per 1M tokens | Published |
| 3 Nov 2026 | $0.15 per 1M tokens | Published |
| 2 Nov 2026 | $0.15 per 1M tokens | Published |
| 1 Nov 2026 | $0.15 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.60 per 1M tokens | Published |
| 8 Nov 2026 | $0.60 per 1M tokens | Published |
| 7 Nov 2026 | $0.60 per 1M tokens | Published |
| 6 Nov 2026 | $0.60 per 1M tokens | Published |
| 5 Nov 2026 | $0.60 per 1M tokens | Published |
| 4 Nov 2026 | $0.60 per 1M tokens | Published |
| 3 Nov 2026 | $0.60 per 1M tokens | Published |
| 2 Nov 2026 | $0.60 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.08 per 1M tokens | Published |
| 8 Nov 2026 | $0.01 per 1M tokens | Published |
| 7 Nov 2026 | $0.01 per 1M tokens | Published |
| 6 Nov 2026 | $0.02 per 1M tokens | Published |
| 5 Nov 2026 | $0.01 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 | $0.60 per 1M tokens | Published |
| 8 Nov 2026 | $0.05 per 1M tokens | Published |
| 7 Nov 2026 | $0.04 per 1M tokens | Published |
| 6 Nov 2026 | $0.10 per 1M tokens | Published |
| 5 Nov 2026 | $0.05 per 1M tokens | Published |
| 4 Nov 2026 | $0.60 per 1M tokens | Published |
| 3 Nov 2026 | $0.60 per 1M tokens | Published |
| 2 Nov 2026 | $0.60 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 |
| 1 Nov 2026 | 131,072 tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 65,536 tokens | Published |
| 8 Nov 2026 | 65,536 tokens | Published |
| 7 Nov 2026 | 65,536 tokens | Published |
| 6 Nov 2026 | 65,536 tokens | Published |
| 5 Nov 2026 | 65,536 tokens | Published |
| 4 Nov 2026 | 65,536 tokens | Published |
| 3 Nov 2026 | 65,536 tokens | Published |
| 2 Nov 2026 | 65,536 tokens | Published |
| 1 Nov 2026 | 65,536 tokens | Published |
Showing the latest 60 of 163 records; the full history is in data.json and data.csv.